Object Tracking Benchmark
Abstract
Object tracking has been one of the most important and active research areas in the field of computer vision. A large number of tracking algorithms have been proposed in recent years with demonstrated success. However, the set of sequences used for evaluation is often not sufficient or is sometimes biased for certain types of algorithms. Many datasets do not have common ground-truth object positions or extents, and this makes comparisons among the reported quantitative results difficult. In addition, the initial conditions or parameters of the evaluated tracking algorithms are not the same, and thus, the quantitative results reported in literature are incomparable or sometimes contradictory. To address these issues, we carry out an extensive evaluation of the state-of-the-art online object-tracking algorithms with various evaluation criteria to understand how these methods perform within the same framework. In this work, we first construct a large dataset with ground-truth object positions and extents for tracking and introduce the sequence attributes for the performance analysis. Second, we integrate most of the publicly available trackers into one code library with uniform input and output formats to facilitate large-scale performance evaluation. Third, we extensively evaluate the performance of 31 algorithms on 100 sequences with different initialization settings. By analyzing the quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.
AI snapshot
Written from the paper’s full text.
TL;DR
This paper presents a large-scale benchmark for online single-object tracking, with 50 annotated sequences, a code library of 29 trackers, and one-pass, temporal, and spatial robustness evaluations. It uses precision and success plots plus sequence attributes to identify effective tracking components and future research directions.
Key findings
- The benchmark includes 50 fully annotated sequences, 11 attributes, 29 tracking algorithms, and more than 660,000 bounding box outputs; the OCC subset contains 29 sequences.
- In success plots, top-ranked SCM in OPE outperforms Struck by 2.6%, but SCM is 1.9% below Struck in SRE; OPE is described as not the best performance indicator because it is one trial of SRE or TRE.
- Sparse-representation trackers perform well in SRE and TRE; local sparse representations (SCM, ASLA, LSK) outperform holistic sparse templates (MTT, L1APG). On OCC, Struck, SCM, TLD, LSK, and ASLA outperform others; on SV, ASLA, SCM, and Struck perform best; for fast motion, dense-sampling trackers such as Struck, TLD, and CXT perform much better than others.
- Performance often decreases significantly when initialization scale is large (e.g., ×1.2); Struck is less sensitive to scale variation than other well-performing methods, and CSK has the highest speed among the top 10 due to its circulant structure.
Methods
- Built a tracking dataset of 50 fully annotated sequences with 11 attributes and a code library integrating 29 publicly available trackers with uniform input/output formats, plus VIVID testbed methods.
- Used precision plots based on center location error, with representative score at threshold = 20 pixels, and success plots based on bounding box overlap, ranked by area under curve (AUC).
- Evaluated with one-pass evaluation (OPE), temporal robustness evaluation (TRE; each sequence partitioned into 20 segments), and spatial robustness evaluation (SRE; 12 runs per sequence using 8 spatial shifts and 4 scale variations, with shift amount 10% of target size and scale ratios 0.8, 0.9, 1.1, 1.2). OPE tested each tracker on more than 29,000 frames, SRE generated more than 350,000 bounding box results, and TRE performed on around 310,000 frames.
Limitations
- Stated: due to space limitations, the main paper presents only the top 10 trackers and only the OCC, SV, and FM attribute subsets; complete plots are in the supplementary material.
- Stated/evident: evaluation is restricted to trackers whose original source or binary codes are publicly available and uses default parameters from the source code; the work focuses on online single-target tracking, and the paper notes there is no single tracking approach that can successfully handle all scenarios.
- Evident: conclusions are tied to the 50-sequence dataset and its attribute thresholds, such as SV with \(t_s=2\), FM with \(t_m=20\), and LR with \(t_r=400\).
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
0 of 11 cited sources checked · 0 supported · 0 flagged
- Findingreasoning§ 5.1. Overall Performance · p. 5
SCM, ASLA and LSK outperform MTT and L1APG.
“We note that SCM, ASLA and LSK outperform MTT and L1APG.”
Quote in the paperSubstantial claim - Findingown data§ Ming-Hsuan Yang University of California at Merced · p. 1
Each tracker is extensively evaluated by analyzing more than 660,000 bounding box outputs.
“Each tracker is extensively evaluated by analyzing more than 660,000 bounding box outputs.”
Quote in the paperSubstantial claim - Findingreasoning§ 5.1. Overall Performance · p. 4
In the precision plots, the rankings of some trackers are slightly different from the rankings in the success plots because they are based on different metrics which measure different characteristics of trackers.
“In the precision plots, the rankings of some trackers are slightly different from the rankings in the success plots in that they are based on different metrics which measure different characteristics of trackers.”
Quote in the paperSubstantial claim - Findingreasoning§ 5.1. Overall Performance · p. 5
The average performance of SRE is lower than that of OPE.
“On the other hand, the average performance of SRE is lower than that of OPE.”
Quote in the paperNot a substantial claim - Findingnone given§ Ming-Hsuan Yang University of California at Merced · p. 1
Each sequence in the dataset is annotated with attributes that often affect tracking performance, such as occlusion, fast motion, and illumination variation.
“Additionally each sequence in the dataset is annotated with attributes that often affect tracking performance, such as occlusion, fast motion, and illumination variation.”
- Also stated in: § Abstract · p. 1 · plain
“The test image sequences are annotated with different attributes for performance evaluation and analysis.”
Quote in the paperSubstantial claim - Also stated in: § Abstract · p. 1 · plain
- Findingreasoning§ 5.2. Attribute-based Performance Analysis · p. 6
When an object moves fast, dense sampling based trackers (e.g., Struck, TLD and CXT) perform much better than others.
“When an object moves fast, dense sampling based trackers (e.g., Struck, TLD and CXT) perform much better than others.”
Quote in the paperSubstantial claim - Findingown data§ 5.3. Initialization with Different Scale · p. 6
The performance often decreases significantly when the scale factor is large (e.g., ×1.2).
“Figure 6 illustrates the average performance of all trackers for each scale which shows the performance often decreases significantly when the scale factor is large (e.g., × 1 . 2 )”
Quote in the paperNot a substantial claim - Findingreasoning§ 5.1. Overall Performance · p. 5
The average TRE performance is higher than that of OPE.
“The average TRE performance is higher than that of OPE”
Quote in the paperNot a substantial claim - Findingreasoning§ 3. Evaluated Algorithms and Datasets · p. 2
To facilitate fair performance evaluation, we have collected and annotated most commonly used tracking sequences.
“To facilitate fair performance evaluation, we have collected and annotated most commonly used tracking sequences.”
Quote in the paperSubstantial claim- Rests on an assumption: Most sequences do not have the ground truth annotations, and the quantitative evaluation results may be generated with different initial conditions.
- Findingnone given§ Ming-Hsuan Yang University of California at Merced · p. 1
We build a tracking dataset with 50 fully annotated sequences to facilitate tracking evaluation.
“We build a tracking dataset with 50 fully annotated sequences to facilitate tracking evaluation.”
Quote in the paperSubstantial claim- Rests on an assumption: Most sequences do not have the ground truth annotations, and the quantitative evaluation results may be generated with different initial conditions.
- Findingreasoning§ 5.2. Attribute-based Performance Analysis · p. 6
Stochastic search based trackers with high overall performance (e.g., SCM and ASLA) do not perform well in the fast motion subset.
“However, the stochastic search based trackers with high overall performance (e.g., SCM and ASLA) do not perform well in this subset”
Quote in the paperSubstantial claim - Findingreasoning§ 5.3. Initialization with Different Scale · p. 6
Some trackers perform better when the scale factor is smaller, such as L1APG, MTT, LOT and CPF.
“Some trackers perform better when the scale factor is smaller, such as L1APG, MTT, LOT and CPF.”
Quote in the paperNot a substantial claim - Findingown data§ 3. Evaluated Algorithms and Datasets · p. 3
One sequence is often annotated with several attributes.
“It also shows that one sequence is often annotated with several attributes.”
Quote in the paperNot a substantial claim - Findingreasoning§ 5.2. Attribute-based Performance Analysis · p. 6
On the SV subset, ASLA, SCM and Struck perform best.
“On the SV subset, ASLA, SCM and Struck perform best.”
Quote in the paperSubstantial claim - Findingreasoning§ 5.1. Overall Performance · p. 5
These trackers (SCM, ASLA, LSK, MTT, L1APG) perform well in SRE and TRE.
“These trackers perform well in SRE and TRE”
Quote in the paperSubstantial claim - Findingreasoning§ 5.1. Overall Performance · p. 5
The ranking of TLD in TRE is lower than OPE and SRE.
“The ranking of TLD in TRE is lower than OPE and SRE.”
Quote in the paperNot a substantial claim - Findingreasoning§ 5.1. Overall Performance · p. 5
Among the top 10 trackers, CSK has the highest speed.
“Among the top 10 trackers, CSK has the highest speed”
Quote in the paperNot a substantial claim - Findingnone given§ 5.1. Overall Performance · p. 5
Trackers tend to perform well in shorter sequences.
“As the trackers tend to perform well in shorter sequences”
Quote in the paperNot a substantial claim - Findingown data§ 5.2. Attribute-based Performance Analysis · p. 6
On the OCC subset, the Struck, SCM, TLD, LSK and ASLA methods outperform others.
“On the OCC subset, the Struck, SCM, TLD, LSK and ASLA methods outperform others.”
Quote in the paperSubstantial claim - Findingown data§ 3. Evaluated Algorithms and Datasets · p. 3
The OCC subset contains 29 sequences which can be used to analyze the performance of trackers to handle occlusion.
“For example, the OCC subset contains 29 sequences which can be used to analyze the performance of trackers to handle occlusion.”
Quote in the paperNot a substantial claim - Findingreasoning§ 5.3. Initialization with Different Scale · p. 6
The performance of TLD, CXT, DFT and LOT decreases with the increase of initialization scale.
“The performance of TLD, CXT, DFT and LOT decreases with the increase of initialization scale.”
Quote in the paperNot a substantial claim - Findingnone given§ 5.3. Initialization with Different Scale · p. 6
Struck is less sensitive to scale variation than other well-performing methods.
“Overall, Struck is less sensitive to scale variation than other well-performing methods.”
Quote in the paperNot a substantial claim - Findingnone given§ 6. Concluding Remarks · p. 6
Most of the evaluated trackers do not focus on the motion/dynamic model component.
“However, most of our evaluated trackers do not focus on this component.”
Quote in the paperSubstantial claim - Findingreasoning§ 5.3. Initialization with Different Scale · p. 6
Some trackers perform well or even better when the initial bounding box is enlarged, such as Struck, OAB, SemiT, and BSBT.
“On the other hand, some trackers perform well or even better when the initial bounding box is enlarged, such as Struck, OAB, SemiT, and BSBT.”
Quote in the paperNot a substantial claim - Interpretationnone given§ 5.1. Overall Performance · p. 5
The proposed circulant structure plays a key role in CSK's speed.
“where the proposed circulant structure plays a key role.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 5.2. Attribute-based Performance Analysis · p. 6
The poor performance of stochastic search based trackers in the fast motion subset is due to poor dynamic models.
“due to the poor dynamic models”
Quote in the paperSubstantial claim - Interpretationown data§ 5.2. Attribute-based Performance Analysis · p. 6
Structured learning and local sparse representations are effective in dealing with occlusions.
“The results suggest that structured learning and local sparse representations are effective in dealing with occlusions.”
Quote in the paperSubstantial claim - Premisecitation§ Ming-Hsuan Yang University of California at Merced · p. 1
Recently, more tracking source codes have been made publicly available, e.g., the OAB, IVT, MIL, L1, and TLD algorithms, which have been commonly used for evaluation.
“Recently, more tracking source codes have been made publicly available, e.g., the OAB [22], IVT [47], MIL [5], L1 [40], and TLD [31] algorithms, which have been commonly used for evaluation.”
Quote in the paperSubstantial claim0 of 3 sources checked- cites [22] [22] H. Grabner, M. Grabner, and H. Bischof. Real-Time Tracking via On-line Boosting. In BMVC , 2006. - source
Not checked in the free run.
- cites [47] [47] D. Ross, J. Lim, R.-S. Lin, and M.-H. Yang. Incremental Learning for Robust Visual Tracking. IJCV , 77(1):125-141, 2008. - source
Not checked in the free run.
- cites [5] [5] B. Babenko, M.-H. Yang, and S. Belongie. Visual Tracking with Online Multiple Instance Learning. In CVPR , 2009. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Interpretationreasoning§ 5.3. Initialization with Different Scale · p. 6
TLD, CXT, DFT and LOT are more sensitive to background clutters.
“This indicates these trackers are more sensitive to background clutters.”
Quote in the paperSubstantial claim - Premisereasoning§ Ming-Hsuan Yang University of California at Merced · p. 1
For sequences without labeled ground truth, it is difficult to evaluate tracking algorithms as the reported results are based on inconsistently annotated object locations.
“For sequences without labeled ground truth, it is difficult to evaluate tracking algorithms as the reported results are based on inconsistently annotated object locations.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 5.2. Attribute-based Performance Analysis · p. 6
The reason dense sampling based trackers perform better in fast motion is that their search ranges are large and their discriminative models are able to discriminate targets from background clutters.
“One reason is that the search ranges are large and the discriminative models are able to discriminate the targets from the background clutters.”
Quote in the paperSubstantial claim - Interpretationown data§ 5.1. Overall Performance · p. 5
Sparse representations are effective models to account for appearance change (e.g., occlusion).
“which suggests sparse representations are effective models to account for appearance change (e.g., occlusion).”
Quote in the paperSubstantial claim- Rests on an assumption: Sparse representations are used in SCM, ASLA, LSK, MTT and L1APG.
- Interpretationreasoning§ 5.1. Overall Performance · p. 5
The alignment-pooling technique adopted by ASLA is more robust to misalignments and background clutters.
“It indicates the alignmentpooling technique adopted by ASLA is more robust to misalignments and background clutters.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 5.1. Overall Performance · p. 5
The performance bottleneck of VTD and VTS can be attributed to their adopted representation based on sparse principal component analysis, where the holistic templates are used.
“Compared with other higher ranked trackers, the performance bottleneck of them can be attributed to their adopted representation based on sparse principal component analysis, where the holistic templates are used.”
Quote in the paperNot a substantial claim - Interpretationown data§ 5.2. Attribute-based Performance Analysis · p. 6
Trackers with affine motion models (e.g., ASLA and SCM) often handle scale variation better than others designed to account for only translational motion, with a few exceptions such as Struck.
“The results show that trackers with affine motion models (e.g., ASLA and SCM) often handle scale variation better than others that are designed to account for only translational motion with a few exceptions such as Struck.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 5.1. Overall Performance · p. 5
Local sparse representations are more effective than holistic sparse templates.
“The results suggest that local sparse representations are more effective than the ones with holistic sparse templates.”
Quote in the paperSubstantial claim- Rests on an assumption: Sparse representations are used in SCM, ASLA, LSK, MTT and L1APG.
- Interpretationreasoning§ 5.3. Initialization with Different Scale · p. 6
Many background pixels are inevitably included in the initial representations when the scale factor is large.
“as many background pixels are inevitably included in the initial representations.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 5.3. Initialization with Different Scale · p. 6
For L1APG and MTT, the reason they perform better with smaller scale factor is that templates have to be warped to fit the size of the usually smaller canonical template, so if the initial template is small, more appearance details will be kept in the model.
“One reason for this in the case of L1APG and MTT is that the templates have to be warped to fit the size of the usually smaller canonical template so that if the initial template is small, more appearance details will be kept in the model.”
Quote in the paperSubstantial claim- Rests on an assumption: The templates have to be warped to fit the size of the usually smaller canonical template.
- Interpretationown data§ 6. Concluding Remarks · p. 6
Local models are important for tracking.
“Second, local models are important for tracking as shown in the performance improvement of local sparse representation (e.g., ASLA and SCM) compared with the holistic sparse representation (e.g., MTT and L1APG).”
Quote in the paperSubstantial claim - Interpretationreasoning§ 6. Concluding Remarks · p. 6
Local models are particularly useful when the appearance of target is partially changed, such as partial occlusion or deformation.
“They are particularly useful when the appearance of target is partially changed, such as partial occlusion or deformation.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 5.3. Initialization with Different Scale · p. 6
Haar-like features are somewhat robust to background clutters due to the summation operations when computing features.
“This indicates that the Haar-like features are somewhat robust to background clutters due to the summation operations when computing features.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 6. Concluding Remarks · p. 6
Background information can be exploited by using advanced learning techniques to encode it in the discriminative model implicitly (e.g., Struck), or serving as the tracking context explicitly (e.g., CXT).
“It can be exploited by using advanced learning techniques to encode the background information in the discriminative model implicitly (e.g., Struck), or serving as the tracking context explicitly (e.g., CXT).”
Quote in the paperSubstantial claim - Interpretationnone given§ 6. Concluding Remarks · p. 6
Background information is critical for effective tracking.
“First, background information is critical for effective tracking.”
Quote in the paperSubstantial claim
- May combine two claims. 12
- Classified as probably not a substantial claim. 26
May combine two claims.
Findingreasoning§ Ming-Hsuan Yang University of California at Merced · p. 1We build a code library that includes most publicly available trackers and a test dataset with ground-truth annotations to facilitate the evaluation task.
“In this work, we build a code library that includes most publicly available trackers and a test dataset with ground-truth annotations to facilitate the evaluation task.”
Quote in the paperSubstantial claim- Rests on an assumption: The input and output formats of most trackers are different and thus it is inconvenient for large scale performance evaluation.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ 3. Evaluated Algorithms and Datasets · p. 3Some attributes occur more frequently, e.g., OPR and IPR, than others.
“Some attributes occur more frequently, e.g., OPR and IPR, than others.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim. May combine two claims.
Findingreasoning§ 3. Evaluated Algorithms and Datasets · p. 3Aside from summarizing the performance on the whole dataset, we also construct several subsets corresponding to attributes to report specific challenging conditions.
“Aside from summarizing the performance on the whole dataset, we also construct several subsets corresponding to attributes to report specific challenging conditions.”
Quote in the paperSubstantial claimMay combine two claims.
Findingreasoning§ 5.1. Overall Performance · p. 5The AUC score of ASLA decreases less than the other top 5 trackers from OPE to SRE and the ranking of ASLA also increases.
“The AUC score of ASLA deceases less than the other top 5 trackers from OPE to SRE and the ranking of ASLA also increases.”
Quote in the paperSubstantial claimMay combine two claims.
Findingnone given§ 5.1. Overall Performance · p. 5In the success plots, the top ranked tracker SCM in OPE outperforms Struck by 2.6% but is 1.9% below Struck in SRE.
“In the success plots, the top ranked tracker SCM in OPE outperforms Struck by 2.6% but is 1.9% below Struck in SRE.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ Ming-Hsuan Yang University of California at Merced · p. 1The code library includes 29 tracking algorithms.
“At present, it includes 29 tracking algorithms.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingreasoning§ 5.1. Overall Performance · p. 5The success rate of Struck is higher than SCM and ALSA when the overlap threshold is small, but less than SCM and ALSA when the overlap threshold is large.
“The success plots of Struck in TRE and SRE show that the success rate of Struck is higher than SCM and ALSA when the overlap threshold is small, but less than SCM and ALSA when the overlap threshold is large.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Study design and conductreasoning§ Ming-Hsuan Yang University of California at Merced · p. 1The initial bounding boxes for tracking are sampled spatially and temporally to evaluate the robustness and characteristics of trackers.
“The initial bounding boxes for tracking are sampled spatially and temporally to evaluate the robustness and characteristics of trackers.”
Quote in the paperSubstantial claim- Rests on an assumption: The robustness to initialization is a well-known problem in the field, but it is seldom addressed in the literature.
Probably not a substantial claim: may not pass S4 (based). May combine two claims.
Interpretationnone given§ 5.1. Overall Performance · p. 4The AUC score of success plot measures the overall performance which is more accurate than the score at one threshold of the plot.
“Because the AUC score of success plot measures the overall performance which is more accurate than the score at one threshold of the plot”
Quote in the paperNot a substantial claimMay combine two claims.
Premisecitation§ 1. Introduction · p. 1Existing datasets for visual tracking in surveillance scenarios have target objects usually humans or cars of small size and static background.
“the target objects are usually humans or cars of small size in these surveillance sequences, and the background is usually static.”
Quote in the paperSubstantial claim0 of 2 sources checked- cites [14] [14] R. Collins, X. Zhou, and S. K. Teh. An Open Source Tracking Testbed and Evaluation Web Site. In PETS , 2005. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- cites [21] [21] R. B. Fisher. The PETS04 Surveillance Ground-Truth Data Sets. In PETS , 2004. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim: may not pass S4 (based).
Premisenone given§ Ming-Hsuan Yang University of California at Merced · p. 1One common issue in assessing tracking algorithms is that the results are reported based on just a few sequences with different initial conditions or parameters.
“One common issue in assessing tracking algorithms is that the results are reported based on just a few sequences with different initial conditions or parameters.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Study design and conductreasoning§ 4. Evaluation Methodology · p. 4We propose two ways to analyze a tracker's robustness to initialization, by perturbing the initialization temporally (i.e., start at different frames) and spatially (i.e., start by different bounding boxes).
“Therefore, we propose two ways to analyze a tracker's robustness to initialization, by perturbing the initialization temporally (i.e., start at different frames) and spatially (i.e., start by different bounding boxes).”
Quote in the paperSubstantial claim- Rests on an assumption: The robustness to initialization is a well-known problem in the field, but it is seldom addressed in the literature.
Probably not a substantial claim: may not pass S4 (based).
Premisenone given§ 4. Evaluation Methodology · p. 4A tracker may be sensitive to the initialization, and its performance with different initialization at a different start frame may become much worse or better.
“However a tracker may be sensitive to the initialization, and its performance with different initialization at a different start frame may become much worse or better.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based).
Premisenone given§ 1. Introduction · p. 1Numerous factors affect the performance of a tracking algorithm, such as illumination variation, occlusion, as well as background clutters.
“Numerous factors affect the performance of a tracking algorithm, such as illumination variation, occlusion, as well as background clutters”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Study design and conductreasoning§ 3. Evaluated Algorithms and Datasets · p. 3For better evaluation and analysis of the strength and weakness of tracking approaches, we propose to categorize the sequences by annotating them with the 11 attributes shown in Table 2.
“For better evaluation and analysis of the strength and weakness of tracking approaches, we propose to categorize the sequences by annotating them with the 11 attributes shown in Table 2.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S2 (checkable).
Interpretationreasoning§ Ming-Hsuan Yang University of California at Merced · p. 1The results do not provide the holistic view of these algorithms.
“Thus, the results do not provide the holistic view of these algorithms.”
Quote in the paperNot a substantial claimMay combine two claims.
Interpretationreasoning§ 5.1. Overall Performance · p. 5OPE is not the best performance indicator as the OPE is one trial of SRE or TRE.
“The results also show that OPE is not the best performance indicator as the OPE is one trial of SRE or TRE.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given§ 5. Evaluation Results · p. 4To the best of our knowledge, this is the largest scale performance evaluation of visual tracking.
“To the best of our knowledge, this is the largest scale performance evaluation of visual tracking.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Study design and conductreasoning§ Ming-Hsuan Yang University of California at Merced · p. 1We propose to perturb the initial state spatially and temporally from the ground-truth target locations.
“For fair and comprehensive performance evaluation, we propose to perturb the initial state spatially and temporally from the ground-truth target locations.”
Quote in the paperSubstantial claim- Rests on an assumption: The robustness to initialization is a well-known problem in the field, but it is seldom addressed in the literature.
May combine two claims.
Premisecitation§ 4. Evaluation Methodology · p. 3When the tracker loses the target, the output location can be random and the average error value may not measure the tracking performance correctly.
“However, when the tracker loses the target, the output location can be random and the average error value may not measure the tracking performance correctly [6].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [6] [6] B. Babenko, M.-H. Yang, and S. Belongie. Robust Object Tracking with Online Multiple Instance Learning. PAMI , 33(7):1619-1632, 2011. - source
Not checked in the free run.
Classified as probably not a substantial claim.
Study design and conductnone given§ 5. Evaluation Results · p. 4For each tracker, the default parameters with the source code are used in all evaluations.
“For each tracker, the default parameters with the source code are used in all evaluations.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S4 (based).
Premisereasoning§ 1. Introduction · p. 1There exists no single tracking approach that can successfully handle all scenarios.
“there exists no single tracking approach that can successfully handle all scenarios.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given§ 5.2. Attribute-based Performance Analysis · p. 6If parameters are set to large values, more particles are required to make the tracker stable.
“If these parameters are set to large values, more particles are required to make the tracker stable.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given§ Ming-Hsuan Yang University of California at Merced · p. 1To the best of our knowledge, this is the first comprehensive work to address and analyze the initialization problem of object tracking.
“To the best of our knowledge, this is the first comprehensive work to address and analyze the initialization problem of object tracking.”
Quote in the paperNot a substantial claim- Rests on an assumption: The robustness to initialization is a well-known problem in the field, but it is seldom addressed in the literature.
Probably not a substantial claim: may not pass S4 (based).
Interpretationnone given§ 5.1. Overall Performance · p. 5Initialization errors tend to cause trackers to update with imprecise appearance information, thereby causing gradual drifts.
“The initialization errors tend to cause trackers to update with imprecise appearance information, thereby causing gradual drifts.”
Quote in the paperNot a substantial claim- Rests on an assumption: Trackers are often initialized by an object detector, which is likely to introduce initialization errors in terms of position and scale.
Probably not a substantial claim: may not pass S2 (checkable), S4 (based).
Premisenone given§ 3. Evaluated Algorithms and Datasets · p. 3Evaluating trackers is difficult because many factors can affect the tracking performance.
“Evaluating trackers is difficult because many factors can affect the tracking performance.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Premisecitation§ 4. Evaluation Methodology · p. 3The precision plot has been adopted to measure the overall tracking performance.
“Recently the precision plot [6, 27] has been adopted to measure the overall tracking performance.”
Quote in the paperSubstantial claim0 of 2 sources checked- cites [6] [6] B. Babenko, M.-H. Yang, and S. Belongie. Robust Object Tracking with Online Multiple Instance Learning. PAMI , 33(7):1619-1632, 2011. - source
Not checked in the free run.
- cites [27] [27] F. Henriques, R. Caseiro, P. Martins, and J. Batista. Exploiting the Circulant Structure of Tracking-by-Detection with Kernels. In ECCV , 2012. - source
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.
Premisecitation§ 1. Introduction · p. 1Although object tracking has been studied for several decades, and much progress has been made in recent years, it remains a very challenging problem.
“Although object tracking has been studied for several decades, and much progress has been made in recent years [28, 16, 47, 5, 40, 26, 19], it remains a very challenging problem.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites [28] [28] M. Isard and A. Blake. CONDENSATION-Conditional Density Propagation for Visual Tracking. IJCV , 29(1):5-28, 1998. - source
Not checked in the free run.
- cites [16] [16] D. Comaniciu, V. Ramesh, and P. Meer. Kernel-Based Object Tracking. PAMI , 25(5):564-577, 2003. - source
Not checked in the free run.
- cites [47] [47] D. Ross, J. Lim, R.-S. Lin, and M.-H. Yang. Incremental Learning for Robust Visual Tracking. IJCV , 77(1):125-141, 2008. - source
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable).
Interpretationreasoning§ 6. Concluding Remarks · p. 6Improving these components will further advance the state of the art of online object tracking.
“Improving these components will further advance the state of the art of online object tracking.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Interpretationreasoning§ 6. Concluding Remarks · p. 6Motion model or dynamic model is crucial for object tracking, especially when the motion of target is large or abrupt.
“Third, motion model or dynamic model is crucial for object tracking, especially when the motion of target is large or abrupt.”
Quote in the paperSubstantial claimClassified as probably not a substantial claim. May combine two claims.
Interpretationreasoning§ 6. Concluding Remarks · p. 6Good location prediction based on the dynamic model could reduce the search range and thus improve the tracking efficiency and robustness.
“Good location prediction based on the dynamic model could reduce the search range and thus improve the tracking efficiency and robustness.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S2 (checkable). May combine two claims.
Interpretationreasoning§ 6. Concluding Remarks · p. 6This large scale performance evaluation facilitates better understanding of the state-of-the-art online object tracking approaches, and provides a platform for gauging new algorithms.
“This large scale performance evaluation facilitates better understanding of the state-of-the-art online object tracking approaches, and provides a platform for gauging new algorithms.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Interpretationown data§ 6. Concluding Remarks · p. 6Significant progress in the field of object tracking has been made in the last decade.
“The evaluation results show that significant progress in the field of object tracking has been made in the last decade.”
Quote in the paperNot a substantial claim
The paper relies on this without support.
The robustness to initialization is a well-known problem in the field, but it is seldom addressed in the literature.
“While the robustness to initialization is a well-known problem in the field, it is seldom addressed in the literature.”
The paper relies on this without support.
Most sequences do not have the ground truth annotations, and the quantitative evaluation results may be generated with different initial conditions.
“However, most sequences do not have the ground truth annotations, and the quantitative evaluation results may be generated with different initial conditions.”
The paper relies on this without support.
The input and output formats of most trackers are different and thus it is inconvenient for large scale performance evaluation.
“However, the input and output formats of most trackers are different and thus it is inconvenient for large scale performance evaluation.”
The paper relies on this without support.
Trackers are often initialized by an object detector, which is likely to introduce initialization errors in terms of position and scale.
“as a tracker is often initialized by an object detector, which is likely to introduce initialization errors in terms of position and scale.”
The paper relies on this without support.
An object detector may be used to re-initialize a tracker at different time instances.
“In addition, an object detector may be used to re-initialize a tracker at different time instances.”
The paper relies on this without support.
TLD performs well in long sequences with a redetection module.
“This is because TLD performs well in long sequences with a redetection module while there are numerous short segments in TRE.”
The paper relies on this without support.
Struck only estimates the location of target and does not handle scale variation.
“This is because Struck only estimates the location of target and does not handle scale variation.”
The paper relies on this without support.
Sparse representations are used in SCM, ASLA, LSK, MTT and L1APG.
“Sparse representations are used in SCM, ASLA, LSK, MTT and L1APG.”
The paper relies on this without support.
The VTD and VTS methods adopt mixture models to improve the tracking performance.
“The VTD and VTS methods adopt mixture models to improve the tracking performance.”
The paper relies on this without support.
Trackers are often sensitive to initialization variations.
“It has been known that trackers are often sensitive to initialization variations.”
The paper relies on this without support.
The templates have to be warped to fit the size of the usually smaller canonical template.
“the templates have to be warped to fit the size of the usually smaller canonical template”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
TC-128 contains 128 challenging videos.
“TC-128 [34] contains 128 challenging videos.”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [34]
The Evaluated Algorithms and Datasets section (pp. 2–3) describes the paper’s tracking dataset and its challenging conditions, but does not identify TC-128 or say it contains 128 videos. Searches for “TC-128” and “128” found no passage addressing that dataset or count. (LLM, conf=0.75)
Experimental — accuracy not yet measuredOut of the 128 videos in TC-128, 78 are new and the others are repeated in other datasets.
“Out of these 128 videos, 78 videos are new, and others are repeated in other datasets.”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [34]
The dataset discussion in Section 3 (p. 2) says the authors collected and annotated commonly used tracking sequences, but it does not describe TC-128 or how many of its videos are new or repeated. Searches for “TC-128,” “78 videos,” and “128 sequences” found no passage addressing those counts. (LLM, conf=0.76)
Experimental — accuracy not yet measured
Cites
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · see citing works
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599 · see citing works
Multiresolution gray-scale and rotation invariant texture classification with local binary patterns
Ojala, T., Pietikainen, M., & Maenpaa, T. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1017623 · Cited by 15,398 · see citing works
Robust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · see citing works
(1981) · Cited by 11,963 · see citing works
High-Speed Tracking with Kernelized Correlation Filters
Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2345390 · Cited by 5,753 · see citing works
GrabCut: Interactive foreground extraction using iterated graph cuts
Rother, C., Kolmogorov, V., & Blake, A. (2004) · ACM Transactions on Graphics · doi:10.1145/1015706.1015720 · Cited by 5,703 · see citing works
CONDENSATION—Conditional Density Propagation for Visual Tracking
Isard, M., & Blake, A. (1998) · International Journal of Computer Vision · doi:10.1023/a:1008078328650 · Cited by 4,886 · see citing works
Yılmaz, A., Javed, O., & Shah, M. A. (2006) · ACM Computing Surveys · doi:10.1145/1177352.1177355 · Cited by 4,807 · see citing works
The FERET evaluation methodology for face-recognition algorithms
Phillips, P. J., Moon, H., Rizvi, S. A., & Rauss, P. J. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.879790 · Cited by 4,688 · see citing works
Comaniciu, D., Ramesh, V., & Meer, P. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1195991 · Cited by 4,560 · see citing works
Online Object Tracking: A Benchmark
Wu, Y., Lim, J., & Yang, M.-H. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.312 · Cited by 4,138 · see citing works
Self-citationLucas-Kanade 20 Years On: A Unifying Framework
Baker, S., & Matthews, I. A. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000011205.11775.fd · Cited by 3,159 · see citing works
Incremental Learning for Robust Visual Tracking
Ross, D. A., Lim, J., Lin, R.-S., & Yang, M.-H. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0075-7 · Cited by 3,061 · see citing works
Self-citationLearning to detect natural image boundaries using local brightness, color, and texture cues
Martin, D. R., Fowlkes, C. C., & Malik, J. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.1273918 · Cited by 2,424 · see citing works
Exploiting the Circulant Structure of Tracking-by-Detection with Kernels
Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33765-9_50 · Cited by 2,310 · see citing works
A Database and Evaluation Methodology for Optical Flow
Baker, S., Scharstein, D., Lewis, J. P., Roth, S., Black, M. J., & Szeliski, R. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-010-0390-2 · Cited by 2,205 · cited 1× · see citing works
“In recent years, many benchmark datasets have been developed for various vision problems, such as the Berkeley segmentation [38], FERET face recognition [45] and optical flow dataset [9].”
BackgroundScale-Space Theory in Computer Vision
Lindeberg, T. (1994) · Springer eBooks · doi:10.1007/978-1-4757-6465-9 · Cited by 2,185 · see citing works
Robust object tracking with online multiple instance learning
Babenko, B., Yang, M.-H., & Belongie, S. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.226 · Cited by 2,007 · see citing works
Self-citationStruck: Structured output tracking with kernels
Hare, S., Saffari, A., & Torr, P. H. S. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126251 · Cited by 1,831 · see citing works
Adaptive Color Attributes for Real-Time Visual Tracking
Danelljan, M., Khan, F. S., Felsberg, M., & van de Weijer, J. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.143 · Cited by 1,541 · see citing works
Visual Tracking: An Experimental Survey
Smeulders, A. W. M., Chu, D. M., Cucchiara, R., Calderara, S., Dehghan, A., & Shah, M. A. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.230 · Cited by 1,527 · see citing works
Real-Time Compressive Tracking
Zhang, K., Lei Zhang, A., & Yang, M. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33712-3_62 · Cited by 1,442 · see citing works
Self-citationRobust Fragments-based Tracking using the Integral Histogram
Adam, A., Rivlin, E., & Shimshoni, I. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.256 · Cited by 1,397 · see citing works
Color-Based Probabilistic Tracking
Pérez, P., Hue, C., Vermaak, J., & Gangnet, M. (2002) · Lecture notes in computer science · doi:10.1007/3-540-47969-4_44 · Cited by 1,391 · see citing works
Online selection of discriminative tracking features
Collins, R. T., Liu, Y., & Leordeanu, M. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.205 · Cited by 1,211 · see citing works
Visual tracking via adaptive structural local sparse appearance model
Jia, X., Lu, H., & Yang, M. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247880 · Cited by 1,200 · see citing works
Self-citationReal-Time Tracking via On-line Boosting
Grabner, H., Grabner, M., & Bischof, H. (2006) · Procedings of the British Machine Vision Conference 2006 · doi:10.5244/c.20.6 · Cited by 1,198 · see citing works
Kwon, J., & Lee, K. M. (2010) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2010.5539821 · Cited by 1,165 · see citing works
Region Covariance: A Fast Descriptor for Detection and Classification
Tuzel, O., Porikli, F., & Meer, P. (2006) · Lecture notes in computer science · doi:10.1007/11744047_45 · Cited by 1,146 · see citing works
Avidan, S. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.35 · Cited by 1,112 · see citing works
Semi-supervised On-Line Boosting for Robust Tracking
Gräbner, H., Leistner, C., & Bischof, H. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88682-2_19 · Cited by 1,095 · see citing works
Efficient region tracking with parametric models of geometry and illumination
Hager, G. D., & Belhumeur, P. N. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.722606 · Cited by 1,066 · see citing works
Avidan, S. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.53 · Cited by 1,043 · see citing works
EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
Black, M. J., & Jepson, A. D. (1998) · International Journal of Computer Vision · doi:10.1023/a:1007939232436 · Cited by 1,038 · see citing works
P-N learning: Bootstrapping binary classifiers by structural constraints
Kalal, Z., Matas, J., & Mikolajczyk, K. (2010) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2010.5540231 · Cited by 1,030 · see citing works
Rother, C., Kolmogorov, V., & Blake, A. (2004) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/1186562.1015720 · Cited by 935 · see citing works
Robust online appearance models for visual tracking
Jepson, A. D., Fleet, D. J., & El-Maraghi, T. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1233903 · Cited by 922 · see citing works
Real time robust L1 tracker using accelerated proximal gradient approach
Bao, C., Wu, Y., Ling, H., & Ji, H. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247881 · Cited by 839 · see citing works
Self-citationRobust Visual Tracking and Vehicle Classification via Sparse Representation
Mei, X., & Ling, H. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.66 · Cited by 837 · see citing works
Mean-shift blob tracking through scale space
Collins, R. T. (2003) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2003.1211475 · Cited by 801 · see citing works
(2009) · doi:10.1109/iccv.2009.5459292 · Cited by 779 · see citing works
Matthews, L., Ishikawa, T., & Baker, S. J. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.16 · Cited by 763 · see citing works
Elliptical head tracking using intensity gradients and color histograms
Birchfield, S. T. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.1998.698614 · Cited by 743 · see citing works
A survey of appearance models in visual object tracking
Li, X., Hu, W., Shen, C., Zhang, Z., Dick, A., & Hengel, A. V. D. (2013) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2508037.2508039 · Cited by 705 · see citing works
Integral histogram: a fast way to extract histograms in Cartesian spaces
Porikli, F. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.188 · Cited by 701 · see citing works
Robust visual tracking via multi-task sparse learning
Zhang, T., Ghanem, B., Liu, S., & Ahuja, N. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247908 · Cited by 649 · see citing works
A Database and Evaluation Methodology for Optical Flow
Baker, S., Roth, S., Scharstein, D., Black, M. J., Lewis, J. P., & Szeliski, R. (2007) · 2007 IEEE 11th International Conference on Computer Vision · doi:10.1109/iccv.2007.4408903 · Cited by 618 · see citing works
Covariance Tracking using Model Update Based on Lie Algebra
Porikli, F., Tuzel, O., & Meer, P. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.94 · Cited by 566 · see citing works
Distribution fields for tracking
Sevilla-Lara, L., & Miller, E. G. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247891 · Cited by 515 · see citing works
Context tracker: Exploring supporters and distracters in unconstrained environments
Dinh, T. B., Vo, N., & Medioni, G. G. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995733 · Cited by 511 · see citing works
Robust tracking using local sparse appearance model and K-selection
Liu, B., Huang, J., Yang, L., & Kulikowsk, C. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995730 · Cited by 482 · see citing works
Transfer Learning Based Visual Tracking with Gaussian Processes Regression
Gao, J. G., Ling, H., Hu, W., & Xing, J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10578-9_13 · Cited by 452 · see citing works
Robust Visual Tracking via Structured Multi-Task Sparse Learning
Zhang, T., Ghanem, B., Liu, S., & Ahuja, N. (2012) · International Journal of Computer Vision · doi:10.1007/s11263-012-0582-z · Cited by 427 · see citing works
Online Object Tracking With Sparse Prototypes
Wang, D., Lu, H., & Yang, M. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2202677 · Cited by 417 · see citing works
Self-citationSpatiograms versus Histograms for Region-Based Tracking
Birchfield, S. T., & Rangarajan, S. (2005) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2005.330 · Cited by 397 · see citing works
Kwon, J., & Lee, K. M. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126369 · Cited by 383 · see citing works
PROST: Parallel robust online simple tracking
Santner, J., Leistner, C., Saffari, A., Pock, T., & Bischof, H. (2010) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2010.5540145 · Cited by 380 · see citing works
Minimum Error Bounded Efficient ℓ1 Tracker with Occlusion Detection
Mei, X., Ling, H., Wu, Y., Blasch, E., & Bai, L. (2011) · Cited by 333 · see citing works
Self-citationYang, F., Lu, H., & Yan, S. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2300823 · Cited by 319 · see citing works
Notice of Removal: The Visual Object Tracking VOT2013 Challenge Results
Kristan, M., Pflugfelder, R. P., Leonardis, A., Matas, J., Porikli, F., Zajc, L. Č., Nebehay, G., Fernandez, G., Vojíř, T., Gatt, A., et al. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.20 · Cited by 310 · see citing works
Robust Object Tracking via Sparse Collaborative Appearance Model
Zhong, W., Lu, H., & Yang, M. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2313227 · Cited by 309 · see citing works
Self-citationVisual Tracking via Locality Sensitive Histograms
He, S., Yang, Q., Lau, R. W. H., Wang, J., & Yang, M. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.314 · Cited by 309 · see citing works
Self-citationSparse coding based visual tracking: Review and experimental comparison
Zhang, S., Yao, H., Sun, X., & Lu, X. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2012.10.006 · Cited by 284 · see citing works
Oron, S., Bar-Hillel, A., Levi, D., & Avidan, S. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247895 · Cited by 282 · see citing works
Least Soft-Threshold Squares Tracking
Wang, D., Lu, H., & Yang, M. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.307 · Cited by 261 · see citing works
Self-citationCo-Tracking Using Semi-Supervised Support Vector Machines
Tang, F., Brennan, S., Zhao, Q., & Hai, T. (2007) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2007.4408954 · Cited by 252 · see citing works
Yang, M., Wu, Y. N., & Hua, G. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.146 · Cited by 231 · see citing works
Self-citationOnline Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers
Yu, Q., Dinh, T. B., & Medioni, G. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88688-4_50 · Cited by 220 · see citing works
Stalder, S., Gräbner, H., & Gool, L. V. (2009) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2009.5457445 · Cited by 215 · see citing works
Kwon, J., & Lee, K. M. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2009.5206502 · Cited by 215 · see citing works
Tracking the invisible: Learning where the object might be
Gräbner, H., Matas, J., Gool, L. V., & Cattin, P. C. (2010) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2010.5539819 · Cited by 206 · see citing works
Hough-based tracking of non-rigid objects
Godec, M., Roth, P. M., & Bischof, H. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126228 · Cited by 202 · see citing works
Sequential Kernel Density Approximation and Its Application to Real-Time Visual Tracking
Han, B., Comaniciu, D., Zhu, Y., & Davis, L. S. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.70771 · Cited by 168 · see citing works
Adaptive Appearance Modeling for Video Tracking: Survey and Evaluation
Salti, S., Cavallaro, A., & Stefano, L. D. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2206035 · Cited by 140 · see citing works
Online robust image alignment via iterative convex optimization
Wu, Y., Shen, B., & Ling, H. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247878 · Cited by 130 · see citing works
Self-citationPETS2010: Dataset and Challenge
Ferryman, J. M., & Ellis, A. (2010) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2010.90 · Cited by 121 · see citing works
Visual Tracking via Probability Continuous Outlier Model
Wang, D., & Lu, H. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.445 · Cited by 113 · see citing works
Visual tracking with histograms and articulating blocks
Nejhum, S. M. S., Ho, J. C. F., & Yang, M. (2008) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2008.4587575 · Cited by 113 · see citing works
Self-citationRobust tracking via weakly supervised ranking SVM
Bai, Y., & Tang, M. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247884 · Cited by 106 · see citing works
Cannons, K. J. (2008) · Cited by 106 · see citing works
Real-Time Probabilistic Covariance Tracking With Efficient Model Update
Wu, Y., Cheng, J., Wang, J., Lu, H., Wang, J., Ling, H., Blasch, E., & Li, B. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2182521 · Cited by 105 · see citing works
Self-citationDiscriminative Spatial Attention for Robust Tracking
Fan, J., Wu, Y. N., & Dai, S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15549-9_35 · Cited by 96 · see citing works
Self-citationBlurred target tracking by Blur-driven Tracker
Wu, Y., Ling, H., Jingyi Yu, A., Li, F., Mei, X., & Cheng, E. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126357 · Cited by 95 · see citing works
Self-citationVisual Tracking via Online Nonnegative Matrix Factorization
Wu, Y., Shen, B., & Ling, H. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2278199 · Cited by 92 · see citing works
Self-citationKwon, J., Lee, K. M., & Park, F. C. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2009.5206501 · Cited by 88 · see citing works
Tracking of Abrupt Motion Using Wang-Landau Monte Carlo Estimation
Kwon, J., & Lee, K. M. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88682-2_30 · Cited by 75 · see citing works
Pang, Y., & Ling, H. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.346 · Cited by 72 · see citing works
An experimental comparison of online object-tracking algorithms
Wang, Q., Chen, F., Xu, W., & Yang, M. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.895965 · Cited by 69 · see citing works
Self-citationLearning to track with multiple observers
Stenger, B., Woodley, T., & Cipolla, R. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2009.5206634 · Cited by 67 · see citing works
Online Object Tracking, Learning, and Parsing with And-Or Graphs
Yang, L., Wu, T., & Zhu, S. C. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.443 · Cited by 67 · see citing works
Visual Tracking via Adaptive Tracker Selection with Multiple Features
Yoon, J. H., Kim, D. Y., & Yoon, K. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33765-9_3 · Cited by 59 · see citing works
Online visual tracking with histograms and articulating blocks
Nejhum, S. M. S., Ho, J. C. F., & Yang, M. (2010) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2010.04.002 · Cited by 59 · see citing works
Self-citationOnline Empirical Evaluation of Tracking Algorithms
Wu, H., Sankaranarayanan, A. C., & Chellappa, R. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.135 · Cited by 56 · see citing works
Rapid selection of reliable templates for visual tracking
Alt, N., Hinterstoißer, S., & Navab, N. (2010) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2010.5539812 · Cited by 48 · see citing works
Object tracking in low-frame-rate video
Porikli, F., & Tuzel, O. (2005) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.587907 · Cited by 45 · see citing works
王, 楠. (2018) · Computer Science and Application · doi:10.12677/csa.2018.81006 · Cited by 2 · see citing works
Flagged first, then by citations
21 of the 118 references couldn’t be matched to a known paper.
Research works printed but not linked: 5
- vojir, 0, Robustifying the flock of trackers, Proc Comput Vis Winter Workshop
- fisher, 0, The PETS04 surveillance ground-truth data sets, Proc IEEE Int Workshop Perform Eval Tracking Surveillance, 1
- ferryman, 0, PETS 2009: Dataset and challenge, Proc IEEE Int Workshop Perform Eval Tracking Surveillance, 1
- mei, 0, Robust visual tracking using l1 minimization, Proc 12th IEEE Int Conf Comput Vis, 1436
- collins, 0, An open source tracking testbed and evaluation web site, Proc IEEE Int Workshop Perform Eval Tracking Surveillance
Cited by
Sorted by citations
High Performance Visual Tracking with Siamese Region Proposal Network
Li, B., Yan, J., Wu, W., Zhu, Z., & Hu, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00935 · Cited by 3,023 · see citing works
“OTB2015 [37] contains 100 sequences that are collected from commonly used tracking sequences.”
BackgroundMethodLearning Multi-domain Convolutional Neural Networks for Visual Tracking
Nam, H., & Han, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.465 · Cited by 2,806 · see citing works
“(b) OTB100 result Figure 3: Precision and success plots on OTB50 [41] and OTB100 [40].”
BackgroundMethodResultInfluentialECO: Efficient Convolution Operators for Tracking
Danelljan, M., Bhat, G., Khan, F. S., & Felsberg, M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.733 · Cited by 2,805 · see citing works
“We validate our proposed formulation by performing comprehensive experiments on four benchmarks: VOT2016 [23], UAV123 [29], OTB-2015 [37], and TempleColor [26].”
BackgroundMethodInfluentialSiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks
Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., & Yan, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00441 · Cited by 2,607 · see citing works
“The standardized benchmarks [47, 48, 10] provide fair testbeds for comparisons with different algorithms.”
BackgroundMethodInfluentialHierarchical Convolutional Features for Visual Tracking
Ma, C., Huang, J., Yang, X., & Yang, M. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.352 · Cited by 1,811 · see citing works
Self-citationA Benchmark and Simulator for UAV Tracking
Mueller, M., Smith, N., & Ghanem, B. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_27 · Cited by 1,944 · see citing works
“Video captured from low-altitude UAVs is inherently different from video in popular tracking datasets like OTB50 [43], OTB100 [42], VOT2014, VOT2015, TC128 [26], and ALOV300++ [39].”
BackgroundMethodGOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
Huang, L., Zhao, X., & Huang, K. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2957464 · Cited by 1,809 · see citing works
“Figure 4 shows the final distribution of video counts of the 121 object class groups we used in the collection stage, with OTB2015 dataset as a comparison.”
BackgroundMethodInfluentialBeyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
Danelljan, M., Robinson, A., Shahbaz Khan, F., & Felsberg, M. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46454-1_29 · Cited by 1,853 · see citing works
“Table 1 shows the tracking results, in mean overlap precision (OP) and area-under-the-curve (AUC), on the OTB2015 dataset.”
BackgroundMethodInfluentialLearning Spatially Regularized Correlation Filters for Visual Tracking
Danelljan, M., Hager, G., Khan, F. S., & Felsberg, M. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.490 · Cited by 2,171 · see citing works
“We provide a comparison of our approach on the recently introduced OTB-2015.”
MethodInfluentialLaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking
Fan, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, Y., Liao, C., & Ling, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00552 · Cited by 1,742 · see citing works
“Summaries of existing tracking benchmarks with highquality dense (per frame) annotations, including OTB-2013 [52], OTB-2015 [53], TC-128 [35], NUS-PRO [28], UAV123 [39], UAV20L [39], VOT-2014 [26], VOT-2017 [27] and LaSOT.”
BackgroundMethodResultInfluentialATOM: Accurate Tracking by Overlap Maximization
Danelljan, M., Bhat, G., Khan, F. S., & Felsberg, M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00479 · Cited by 1,591 · see citing works
“In visual tracking, the target state is often represented by a bounding box, either axis aligned [9, 37] or rotated [17].”
BackgroundDistractor-Aware Siamese Networks for Visual Object Tracking
Zhu, Z. D., Wang, Q., Li, B., Wu, W., Yan, J., & Hu, W. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01240-3_7 · Cited by 1,575 · see citing works
“A core problem of tracking is how to detect and locate the object accurately and efficiently in challenging scenarios with occlusions, out-of-view, deformation, background cluttering and other variations [38].”
BackgroundMethodLearning Discriminative Model Prediction for Tracking
Bhat, G., Danelljan, M., Van Gool, L., & Timofte, R. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00628 · Cited by 1,515 · see citing works
“Experiments are performed on a combined dataset containing the entire OTB-100 [37], NFS (30 FPS version) [9] and UAV123 [24] datasets.”
BackgroundMethodInfluentialChen, X., Yan, B., Zhu, J., Wang, D., Yang, X., & Lu, H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00803 · Cited by 1,588 · see citing works
Detection and tracking meet drones challenge
Zhu, P., Wen, L., Du, D., Bian, X., Fan, H., Hu, Q., & Ling, H. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3119563 · Cited by 1,336 · see citing works
Learning Background-Aware Correlation Filters for Visual Tracking
Galoogahi, H. K., Fagg, A., & Lucey, S. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.129 · Cited by 1,270 · see citing works
“All sequences in OTB100 are manually annotated by 11 different visual attributes such as occlusion, deformation and motion blur.”
BackgroundMethodInfluentialLearning Spatio-Temporal Transformer for Visual Tracking
Yan, B., Peng, H., Fu, J., Wang, D., & Lu, H. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01028 · Cited by 1,280 · see citing works
Discriminative Correlation Filter with Channel and Spatial Reliability
Lukezic, A., Vojir, T., Zajc, L. C., Matas, J., & Kristan, M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.515 · Cited by 1,153 · see citing works
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
Müller, M., Bibi, A., Giancola, S., Alsubaihi, S., & Ghanem, B. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01246-5_19 · Cited by 1,192 · see citing works
“Third, we show that challenges in OTB100 [5] and VOT17 [11] focus on objects with slightly larger motion, while TrackingNet shows a more natural motion distribution over the fastest moving instances in YT-BB.”
BackgroundMethodResultInfluentialDeeper and Wider Siamese Networks for Real-Time Visual Tracking
Zhang, Z., & Peng, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00472 · Cited by 1,160 · see citing works
“The evaluation on OTB-2013 and OTB-2015 follows the standard protocols proposed in [37, 38].”
MethodThe Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
Du, D., Qi, Y., Yu, H., Yang, Y., Duan, K., Li, G., Zhang, W., Huang, Q., & Tian, Q. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01249-6_23 · Cited by 1,099 · see citing works
“6: The precision and success plots on the UAVDT-SOT benchmark using One-pass Evaluation [49].”
BackgroundMethodInfluentialSiamese Box Adaptive Network for Visual Tracking
Chen, Z., Zhong, B., Li, G., Zhang, S., & Ji, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00670 · Cited by 1,052 · see citing works
“Prior to SiamRPN++, due to the limited representation capabilities of shallow networks, the Siamese network based [52] trackers achieves suboptimal performance on the OTB100.”
BackgroundInfluentialImage Matching from Handcrafted to Deep Features: A Survey
Ma, J.-Y., Jiang, X., Fan, A., Jiang, J., & Yan, J. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-020-01359-2 · Cited by 977 · see citing works
“…referred to a comprehensive evaluation of different feature detectors and descriptors for tracking by Gauglitz et al. (2011), and the recently presented benchmark (Wu et al. 2015b), which covers a review of modern object tracking methods as well as the role played by feature representation methods.”
BackgroundLearning Spatial-Temporal Regularized Correlation Filters for Visual Tracking
Li, F., Tian, C., Zuo, W., Zhang, L., & Yang, M.-H. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00515 · Cited by 935 · see citing works
“One can see that DeepSTRCF ranks the second and outperforms DeepSRDCF with a margin of 5.2% on OTB-2015.”
BackgroundMethodInfluentialSelf-citationTransformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
Wang, N., Zhou, W., Wang, J., & Li, H. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00162 · Cited by 913 · see citing works
Ocean: Object-Aware Anchor-Free Tracking
Zhang, Z., Peng, H., Fu, J., Li, B., & Hu, W. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58589-1_46 · Cited by 894 · see citing works
“The standardized OTB-100 [44] benchmark consists of 100 videos.”
BackgroundMethodInfluentialProbabilistic Regression for Visual Tracking
Danelljan, M., Van Gool, L., & Timofte, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00721 · Cited by 798 · see citing works
“RPN [52 ] [9 12 34 8 28 4 3] OTB-100 65.8 68.2 67.8 69.1 66.9 69.670.2 66.0 68.4 68.0 69.6 NFS - 48.8 42.2 46.6 58.4 - 53.7 61.0 62.0 63.363.5 Table 5. Comparison with state-of-the-art on the OTB-100 [47] and NFS [14] datasets in terms of overall AUC score. The average value over 5 runs is reported for our approach. A…”
MethodInfluentialReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements
Kulkarni, K., Lohit, S., Turaga, P., Kerviche, R., & Ashok, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.55 · Cited by 768 · see citing works
“01 by obtaining frame-wise block CS measurements on 15 publicly available videos [33] (see supplementary for the list of videos) used to benchmark tracking algorithms.”
MethodQi, Y., Zhang, S., Qin, L., Yao, H., Huang, Q., Lim, J., & Yang, M. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.466 · Cited by 735 · see citing works
“For completeness, we also report the results on the benchmark [33], which is a subset of [34].”
BackgroundMethodResultInfluentialSelf-citationThe Visual Object Tracking VOT2016 Challenge Results
Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., Cehovin, L., Vojír, T., Häger, G., Lukežič, A., Fernandez, G., et al. (2016) · ECCV Workshops · doi:10.1007/978-3-319-48881-3_54 · Cited by 776 · see citing works
The Sixth Visual Object Tracking VOT2018 Challenge Results
Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., Zajc, L. Č., Vojír, T., Bhat, G., Lukežič, A., Eldesokey, A., et al. (2018) · ECCV Workshops · doi:10.1007/978-3-030-11009-3_1 · Cited by 805 · see citing works
Self-citationThe Visual Object Tracking VOT2015 Challenge Results
Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., Zajc, L. Č., Vojír, T., Häger, G., Lukežič, A., Eldesokey, A., et al. (2015) · 2015 IEEE International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2015.79 · Cited by 895 · see citing works
“Several works that focus on performance evaluation in short-term visual object tracking [38, 36, 34, 64, 65, 76, 61, 77, 42] have been published over the last three years.”
BackgroundMethodSiamese Neural Networks: An Overview
Chicco, D. (2020) · Methods in molecular biology · doi:10.1007/978-1-0716-0826-5_3 · Cited by 681 · see citing works
A Twofold Siamese Network for Real-Time Object Tracking
He, A., Luo, C., Tian, X., & Zeng, W. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00508 · Cited by 708 · see citing works
“The numbers for BACF [17] is different from the paper because the authors only evaluate 50 videos (no jogging2) for OTB-2013.”
BackgroundInfluentialContext-Aware Correlation Filter Tracking
Mueller, M. F., Smith, N., & Ghanem, B. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.152 · Cited by 662 · see citing works
“All trackers are evaluated according to two measures, precision and success, as defined in OTB-50/OTB-100 [26, 27].”
BackgroundMethodInfluentialTriplet Loss in Siamese Network for Object Tracking
Dong, X., & Shen, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01261-8_28 · Cited by 665 · see citing works
Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey
Han, J., Zhang, D., Cheng, G., Liu, N., & Xu, D. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2749125 · Cited by 618 · see citing works
“Usually, OD algorithms output thousands of object proposals or hypotheses as shown in Figure 1(a), which can benefit a wide range of computer vision tasks like weakly supervised learning [3] and object tracking [4].”
BackgroundMDLatLRR: A Novel Decomposition Method for Infrared and Visible Image Fusion
Li, H., Wu, X., & Kittler, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2975984 · Cited by 632 · see citing works
“The parameters of GFSDCF were learned on OTB-2015 [47] dataset.”
MethodWang, Q., Teng, Z., Xing, J., Gao, J., Hu, W., & Maybank, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00510 · Cited by 604 · see citing works
“By extensively training large deep networks on large datasets offline and aggressively learning the target sequence online, those trackers have obtained record-breaking results on all recent benchmarks [51, 52] and challenges [15, 16, 28].”
BackgroundMethodInfluentialLarge Margin Object Tracking with Circulant Feature Maps
Wang, M., Liu, Y., & Huang, Z. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.510 · Cited by 665 · see citing works
“until end of video sequence. features based version LMCF and deep CNNs based version DeepLMCF to validate the performance of the proposed method. We implement experiment on the OTB-13 [29] and OTB15 [30] benchmark datasets. All these sequences are annotated with 11 attributes which cover various challenging factors, i…”
BackgroundMethodInfluentialVITAL: VIsual Tracking via Adversarial Learning
Song, Y., Ma, C., Wu, X., Gong, L., Bao, L., Zuo, W., Shen, C., Lau, R. W. H., & Yang, M. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00937 · Cited by 595 · see citing works
“Since the OTB-2015 dataset contains more videos with large scale changes and low resolution, our VITAL tracker does not perform as well as ECO in overlap success.”
MethodInfluentialSelf-citationRGB-T object tracking: Benchmark and baseline
Li, C., Liang, X., Lu, Y., Zhao, N., & Tang, J. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.106977 · Cited by 596 · see citing works
“There are 5 widely used metrics for tracking performance evaluation [18, 20], i.”
MethodAction-Decision Networks for Visual Tracking with Deep Reinforcement Learning
Yun, S., Choi, J., Yoo, Y., Yun, K., & Choi, J. Y. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.148 · Cited by 547 · see citing works
“To verify the effectiveness of the components of ADNet, we conducted four variants of ADNet and evaluated them using OTB-100.”
BackgroundMethodInfluentialCREST: Convolutional Residual Learning for Visual Tracking
Song, Y., Ma, C., Gong, L., Zhang, J., Lau, R. W. H., & Yang, M. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.279 · Cited by 572 · see citing works
“We conduct quantitative and qualitative evaluations on the benchmark datasets including OTB-2013 [45], OTB2015 [46] and VOT-2016 [24].”
BackgroundMethodInfluentialSelf-citationDeep visual tracking: Review and experimental comparison
Li, P., Wang, D., Wang, L., & Lu, H. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.11.007 · Cited by 517 · see citing works
Need for Speed: A Benchmark for Higher Frame Rate Object Tracking
Galoogahi, H. K., Fagg, A., Huang, C., Ramanan, D., & Lucey, S. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.128 · Cited by 542 · see citing works
“However, most of these algorithms - and the datasets they have been evaluated upon [38, 37, 23] - have been aimed at the canonical approximate frame rate of 30 Frames Per Second (FPS).”
BackgroundInfluentialUnveiling the Power of Deep Tracking
Bhat, G., Johnander, J., Danelljan, M., Khan, F. S., & Felsberg, M. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01216-8_30 · Cited by 514 · see citing works
“In fact, trackers based on handcrafted features [1,2,3,4] still provide competitive results, even outperforming many deep trackers on standard benchmarks [5,6].”
BackgroundMethodInfluentialGuo, D., Shao, Y., Cui, Y., Wang, Z., Zhang, L., & Shen, C. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00942 · Cited by 537 · see citing works
“It is also challenging in terms of zero-class-overlap between the pro-0 Figure 7 – Evaluation with each single attribute on OTB-100 [32] in terms of success. vided training subset and testing subset.”
The Seventh Visual Object Tracking VOT2019 Challenge Results
Kristan, M., Matas, J., Leonardis, A., Felsberg, M., Pflugfelder, R. P., Kämäräinen, J., Zajc, L. Č., Drbohlav, O., Lukežič, A., Berg, A., et al. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00276 · Cited by 465 · see citing works
“To compete for the winner of VOT2019 challenge, learning on specific datasets (OTB, VOT, ALOV, UAV123, NUS-PRO, TempleColor and RGBT234) was prohibited.”
BackgroundMethodInfluentialMulti-cue Correlation Filters for Robust Visual Tracking
Wang, N., Zhou, W., Tian, Q. C., Hong, R., Wang, M., & Li, H. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00509 · Cited by 492 · see citing works
“On the OTB-2015 [48] dataset, our proposed MCCT tracker achieves the best results on OP and DP with scores of 86.”
BackgroundMethodInfluentialSiamese Cascaded Region Proposal Networks for Real-Time Visual Tracking
Fan, H., & Ling, H. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00814 · Cited by 477 · see citing works
The Visual Object Tracking VOT2017 Challenge Results
Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., Zajc, L. Č., Vojír, T., Häger, G., Lukežič, A., Eldesokey, A., et al. (2017) · 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw.2017.230 · Cited by 319 · see citing works
“Most tracking datasets [77, 39, 60, 40, 45] have partially followed the trend in computer vision of increasing the number of sequences.”
BackgroundMethodInfluentialSelf-citationVisual Tracking via Adaptive Spatially-Regularized Correlation Filters
Dai, K., Wang, D., Lu, H., Sun, C., & Li, J. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00480 · Cited by 448 · see citing works
“In this section, we demonstrate the effectiveness of our tracker on the OTB2015 [35], TC128 [27] VOT2016 [19], VOT2017 [20] and LaSOT [14] datasets.”
BackgroundMethodLi, X., Ma, C., Wu, B., He, Z., & Yang, M. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00146 · Cited by 481 · see citing works
“%) on the OTB-2013 and OTB-2015 datasets.”
MethodInfluentialSelf-citationMulti-task Correlation Particle Filter for Robust Object Tracking
Zhang, T., Xu, C., & Yang, M. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.512 · Cited by 433 · see citing works
“Our method is evaluated on three benchmark datasets: OTB-2013 [36], OTB-2015 [37], and Temple Color [22].”
MethodInfluentialSelf-citationLearning the Model Update for Siamese Trackers
Zhang, L., Gonzalez-Garcia, A., Weijer, J. V. D., Danelljan, M., & Khan, F. S. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00411 · Cited by 475 · see citing works
“t and the background. Among the tracking-by-detection approaches, discriminative correlation filter based trackers [19,48,11,7] have recently shown excellent performance on several tracking benchmarks [42,43,24,22]. These trackers learn a correlation filter from example patches of the target appearance to discriminate b…”
MethodTransforming Model Prediction for Tracking
Mayer, C., Danelljan, M., Bhat, G., Paul, M., Paudel, D. P., Yu, F., & Gool, L. V. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00853 · Cited by 460 · see citing works
Xu, T., Feng, Z.-H., Wu, X.-J., & Kittler, J. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2919201 · Cited by 411 · see citing works
“Recently, considering the joint circular structure of sliding candidates, Discriminative Correlation Filter (DCF) based tracking methods [7], [8] have achieved outstanding performance in many challenging benchmarks and competitions [5], [9], [10].”
BackgroundMethodInfluentialWang, N., Song, Y., Ma, C., Zhou, W., Liu, W., & Li, H. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00140 · Cited by 443 · see citing works
“Comparison results with fully-supervised baseline (left) and state-of-the-art (right) trackers on the OTB-2015 benchmark [57].”
BackgroundMethodInfluentialDanelljan, M., Hager, G., Khan, F. S., & Felsberg, M. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.159 · Cited by 440 · see citing works
“To evaluate our approach, we perform comprehensive experiments on three benchmark datasets: OTB-2015 [27], VOT-2015 [17] and Temple-Color [20].”
BackgroundMethodInfluentialDeep Learning for Visual Tracking: A Comprehensive Survey
Marvasti-Zadeh, S. M., Cheng, L., Ghanei-Yakhdan, H., & Shohreh Kasaei, B. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3046478 · Cited by 417 · see citing works
“[48], OTB2015 [186], TC128 [187], UAV123 [188], NUS-PRO [189], NfS [190], DTB [191], TrackingNet [192], OxUvA [193], BUAA-PRO [194], GOT10k [195], and LaSOT [196] are com-”
BackgroundMethodInfluentialVisual Object Tracking for Unmanned Aerial Vehicles: A Benchmark and New Motion Models
Li, S., & Yeung, D. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11205 · Cited by 414 · see citing works
“Recently, the benchmark has been extended (Wu, Lim, and Yang 2015).”
BackgroundOnline Multi-Object Tracking with Dual Matching Attention Networks
Zhu, J., Yang, H., Liu, N., Kim, M., Zhang, W., & Yang, M.-H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_23 · Cited by 377 · see citing works
“The ECO tracker achieves the state-of-the-art performance on visual tracking benchmarks [25,52,38,33] and its fast variant ECO-HC based on hand-crafted features (HOG [11] and Color Names [49]) operates at 60 frames per second (FPS) on a single CPU, which is suitable for the online MOT task.”
MethodSelf-citationLearning Target Candidate Association to Keep Track of What Not to Track
Mayer, C., Danelljan, M., Paudel, D. P., & Gool, L. V. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01319 · Cited by 392 · see citing works
“Comparison with state-of-the-art on the OTB-100 [45], NFS [24] and UAV123 [37] datasets in terms of AUC score.”
BackgroundMethodDiscriminative Correlation Filter Tracker with Channel and Spatial Reliability
Lukežič, A., Vojíř, T., Zajc, L. Č., Matas, J., & Kristan, M. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-017-1061-3 · Cited by 484 · see citing works
“The OTB100 [44] benchmark contains results of 29 trackers evaluated on 100 sequences by a no-reset evaluation protocol.”
BackgroundMethodInfluentialLearning Dynamic Memory Networks for Object Tracking
Yang, T., & Chan, A. B. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01240-3_10 · Cited by 382 · see citing works
“Figure 5 (right) shows success plots on OTB-2015 using different numbers of memory slots.”
BackgroundMethodInfluentialKnow Your Surroundings: Exploiting Scene Information for Object Tracking
Bhat, G., Danelljan, M., Gool, L. V., & Timofte, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58592-1_13 · Cited by 414 · see citing works
“We evaluate our proposed tracking architecture on five tracking benchmarks: VOT2018 [29], GOT-10k [23], TrackingNet [36], OTB-100 [45], and NFS [14].”
BackgroundMethodInfluentialLaSOT: A High-quality Large-scale Single Object Tracking Benchmark
Fan, H., Bai, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Harshit, Huang, M., Liu, J., et al. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01387-y · Cited by 360 · see citing works
STMTrack: Template-free Visual Tracking with Space-time Memory Networks
Fu, Z., Liu, Q., Fu, Z., & Wang, Y. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01356 · Cited by 399 · see citing works
AiATrack: Attention in Attention for Transformer Visual Tracking
Gao, S., Zhou, C., Ma, C., Wang, X., & Yuan, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20047-2_9 · Cited by 396 · see citing works
AI Benchmark: Running Deep Neural Networks on Android Smartphones
Ignatov, A., Timofte, R., Chou, W., Wang, K., Wu, M., Hartley, T., & Van Gool, L. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-11021-5_19 · Cited by 347 · see citing works
“One notable group of such tasks is concerned with computer vision problems like image classification [1, 2, 3], image enhancement [4, 5, 6] and super-resolution [7, 8, 9], optical character recognition [10], object tracking [11, 12], visual scene understanding [13, 14], face detection and recognition [15, 16], gaze tr…”
BackgroundGao, J., Zhang, T., & Xu, C. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00478 · Cited by 343 · see citing works
“It has various applications such as intelligent video surveillance, humancomputer interaction, robotics, and autonomous driving, to name a few [71, 33, 13, 24, 74, 42, 17].”
BackgroundMethodInfluentialInteractive deep learning method for segmenting moving objects
Wang, Y., Luo, Z., & Jodoin, P. (2016) · Pattern Recognition Letters · doi:10.1016/j.patrec.2016.09.014 · Cited by 327 · see citing works
Understanding and Diagnosing Visual Tracking Systems
Wang, N., Shi, J., Yeung, D., & Jia, J. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.355 · Cited by 369 · see citing works
“For a comprehensive survey, readers are referred to [28, 40].”
BackgroundZhang, K., Liu, X., Xu, J., Yuan, J., Cai, W., Chen, T., Wang, K., Gao, Y., Nie, S., Xu, X., et al. (2021) · Nature Biomedical Engineering · doi:10.1038/s41551-021-00745-6 · Cited by 324 · see citing works
GradNet: Gradient-Guided Network for Visual Object Tracking
Li, P., Chen, B., Ouyang, W., Wang, D., Yang, X., & Lu, H. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00626 · Cited by 348 · see citing works
“We refer the reader to [38] for more detailed information.”
BackgroundInfluentialAttentional Correlation Filter Network for Adaptive Visual Tracking
Choi, J., Chang, H. J., Yun, S., Fischer, T., Demiris, Y., & Choi, J. Y. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.513 · Cited by 319 · see citing works
“ACFN showed the best performance within the self-comparison, and the state-of-the-art performance amongst real-time trackers in TPAMI2015 [39] and VOT2014 [22] dataset.”
BackgroundMethodInfluentialParallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking
Fan, H., & Ling, H. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.585 · Cited by 330 · see citing works
“Following the protocol in [39, 40], we report the results in one-pass evaluation (OPE) using distance precision rate (DPR) and overlap success rate (OSR) as shown in Fig.”
BackgroundMethodInfluentialJung, I., Son, J., Baek, M., & Han, B. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01225-0_6 · Cited by 297 · see citing works
“5 illustrates the precision and success plots on TempleColor dataset [30], which is containing 128 color videos while most of sequences are overlapped with OTB2015 dataset [28].”
MethodInfluentialEnd-to-End Flow Correlation Tracking with Spatial-Temporal Attention
Zhu, Z. D., Wu, W., Zou, W., & Yan, J. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00064 · Cited by 321 · see citing works
“Analyses results include OTB2013 [8], OTB2015[4] VOT2015 [5]and VOT2016[7].”
BackgroundResultInfluentialNenavath, H., & Jatoth, R. K. (2017) · Applied Soft Computing · doi:10.1016/j.asoc.2017.09.039 · Cited by 312 · see citing works
The First Facial Landmark Tracking in-the-Wild Challenge: Benchmark and Results
Shen, J., Zafeiriou, S. P., Chrysos, G. G., Kossaifi, J., Tzimiropoulos, G., & Pantić, M. (2015) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2015.132 · Cited by 289 · see citing works
“This is mainly attributed to the fact that face tracking is modelled as a face detection or as a general object tracking problem [43, 23, 61, 24].”
BackgroundOverview and methods of correlation filter algorithms in object tracking
Liu, S., Liu, D., Srivastava, G., Połap, D., & Woźniak, M. (2021) · Complex & Intelligent Systems · doi:10.1007/s40747-020-00161-4 · Cited by 305 · see citing works
“100 video sequences are contained in extended version OTB2015 [11] which is extended from the OTB2013 (50 videos).”
BackgroundVision-Based Anti-UAV Detection and Tracking
Zhao, J. W., Zhang, J., Li, D., & Wang, D. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3177627 · Cited by 330 · see citing works
“, COCO [37], ILSVRC [38], LaSOT [39], OTB [40]), the most notable characteristic of the proposed dataset for UAV detection and tracking is that the proportion of small objects is larger.”
BackgroundModeling and Propagating CNNs in a Tree Structure for Visual TrackingPreprint
Nam, H., Baek, M., & Han, B. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.07242 · Cited by 280 · see citing works
“It is interesting that MUSTer is not as competitive as in the OTB [37, 36] while TCNN is outstanding in both OTB and VOT2015 datasets consistently compared to other trackers.”
BackgroundMethodInfluentialHigh-Performance Long-Term Tracking With Meta-Updater
Dai, K., Zhang, Y., Wang, D., Li, J., Lu, H., & Yang, X. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00633 · Cited by 310 · see citing works
“Each video in this dataset lasts for average 2.4 minutes, which is much longer than other commonly used short-term datasets (such as OTB2015 [46]).”
BackgroundInfluentialSelf-Supervised Deep Correlation Tracking
Yuan, D., Chang, X., Huang, P.-Y., Liu, Q., & He, Z. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3037518 · Cited by 288 · see citing works
“In order to verify the proposed self-SDCT tracker, we made some experimental comparisons between our tracker and some state-of-the-art trackers on standard benchmark datasets including OTB-100 [19], UAVDT [20], TColor-128 [21], and UAV-123 [22].”
MethodInfluentialStructured Siamese Network for Real-Time Visual Tracking
Zhang, Y., Wang, L., Qi, J., Wang, D., Feng, M., & Lu, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01240-3_22 · Cited by 272 · see citing works
“Ours ACFN LCT SCT MEEM CFNet-conv2 SiameseFC Staple KCF DSST speed/fps 45 15 27 40 10 75 58 80 172 24 0 5 10 15 20 25 30 35 40 45 50 Location error threshold 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 P re ci si o n Precision plots of OPE StructSiam [0.880] ACFN [0.860] LCT [0.848] SCT [0.839] MEEM [0.830] SiamFC [0.809]…”
MethodInfluentialTowards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
Wang, X., Shu, X., Zhang, Z., Jiang, B., Wang, Y., Tian, Y., & Wu, F. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01355 · Cited by 302 · see citing works
“GTI [78] combine SiamRPN++ and visual grounding module, and achieves 0.73 | 0.58, 0.47 | 0.47 on OTB-Lang and LaSOT dataset.”
InfluentialGlobalTrack: A Simple and Strong Baseline for Long-Term Tracking
Huang, L., Zhao, X., & Huang, K. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6758 · Cited by 279 · see citing works
“Over the past decades, significant progress has been made in this area (Wu, Lim, and Yang 2015; Valmadre et al. 2018; Huang, Zhao, and Huang 2018).”
BackgroundVisible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline
Zhang, P., Zhao, J. W., Wang, D., Lu, H., & Ruan, X. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00868 · Cited by 308 · see citing works
“However, existing visual and RGB-T datasets [20, 26, 40] label attributes at the sequencelevel, which involves various challenges into single sequence in a coarse manner.”
BackgroundDCFNet: Discriminant Correlation Filters Network for Visual TrackingPreprint
Wang, Q., Gao, J. G., Xing, J., Zhang, M., & Hu, W. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.04057 · Cited by 305 · see citing works
“One common setting for this problem is to initialize the object of interest in the first frame with a bounding box and the aim is to estimate the trajectory of the object in subsequent frames [1, 2, 3].”
BackgroundMethodInfluentialWeighted Sparse Representation Regularized Graph Learning for RGB-T Object Tracking
Li, C., Zhao, N., Lu, Y., Zhu, C., & Tang, J. (2017) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3123266.3123289 · Cited by 283 · see citing works
“As in other benchmarks [43, 44], we set the threshold to 20 pixels to obtain the representative PR. Note that GTOT sets the threshold to 5 pixels as most of its tracked targets are small.”
BackgroundMethodObject Tracking via Dual Linear Structured SVM and Explicit Feature Map
Ning, J., Yang, J., Jiang, S., Lei Zhang, A., & Yang, M. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.462 · Cited by 250 · see citing works
“We evaluate the DLSSVM and Scale-DLSSVM trackers against the state-of-the-art methods on the TB50 [31] and TB100 [32] datasets, where the results of 29 trackers are reported.”
BackgroundMethodInfluentialSelf-citationThe Eighth Visual Object Tracking VOT2020 Challenge Results
Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R. P., Kämäräinen, J., Danelljan, M., Zajc, L. Č., Lukežič, A., Drbohlav, O., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-68238-5_39 · Cited by 262 · see citing works
SANet: Structure-Aware Network for Visual Tracking
Fan, H., & Ling, H. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.275 · Cited by 263 · see citing works
“Comparison of the proposed tracker with the state-ofthe-art deep learning-based method (MDNet in [34]) in challenging situations of similar background on sequences Coupon and Box [49].”
BackgroundMethodInfluentialSpatially supervised recurrent convolutional neural networks for visual object tracking
Ning, G., Zhang, Z., Huang, C., Ren, X., Wang, H., Cai, C., & He, Z. (2017) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2017.8050867 · Cited by 276 · see citing works
“Specifically, we compare our results with the top 9 trackers that achieved the best performance evaluated by the benchmark [9].”
ResultLearn to Match: Automatic Matching Network Design for Visual Tracking
Zhang, Z., Liu, Y., Wang, X., Li, B., & Hu, W. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01309 · Cited by 269 · see citing works
“The effectiveness of the proposed framework is verified on OTB100 [40], LaSOT [10], GOT10K [14], TrackingNet [27] and TNL2K [39].”
BackgroundMethodInfluentialTowards a Better Understanding of Transfer Learning for Medical Imaging: A Case Study
Alzubaidi, L., Fadhel, M. A., Al-Shamma, O., Zhang, J., Santamaría, J., Duan, Y., & R. Oleiwi, S. (2020) · Applied Sciences · doi:10.3390/app10134523 · Cited by 258 · see citing works
“It is used as a primary task in di ff erent application areas including event detection [32], scene understanding [33], and object tracking [34].”
Deep Regression Tracking with Shrinkage Loss
Lu, X., Ma, C., Ni, B., Yang, X., Reid, I. D., & Yang, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01264-9_22 · Cited by 251 · see citing works
“Figure 11 compares the convergence speed and the required training iterations using different losses on the OTB-2015 dataset [9].”
BackgroundMethodInfluentialSelf-citation
- Authors
- Wu, Y., Lim, J., & Yang, M.-H.
- Affiliations
- Nanjing University of Information Science and Technology (CN)
- Hanyang University (KR)
- University of California, Merced (US)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2015-09-01
- Volume
- 37
- Issue
- 9
- Pages
- 1834-1848
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- OpenAlex
- W2158592639
- Semantic Scholar
- c4c45661501c16064eead6e5d37dcb80d41c7a78
- Cited by
- 3,371
- References
- 118
- Citations by year
- 2026: 102 · 2025: 174 · 2024: 209 · 2023: 295 · 2022: 323 · 2021: 442 · 2020: 483 · 2019: 539 · 2018: 429 · 2017: 235 · 2016: 116 · 2015: 24
- FWCI
- 230.94
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- The Royal Society of Chemistry’s Journals, Books and Databases (The Royal Society of Chemistry) (submittedVersion)
- Funders
- NSFC (61005027, 61370036)
- ICT R&D programs of MSIP/IITP (10047078, 14-824-09-006)
- National Science Foundation (1149783)
- IIS (1152576)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- object tracking, benchmark dataset, tracking algorithm evaluation, online tracking, performance evaluation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-08.
Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-08.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
