Incremental Learning for Robust Visual Tracking
The DOI matches its Crossref record; 41 of the 43 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“However, if the target is occluded, the peak in the response map will be smoother, and the relative value of APCE becomes larger [7].”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [7]
In the citing paper
“It has been shown practically that if the target apparently appears in the detection scope, there will be a sharper peak in the response map, and the value of APCE will be smaller.”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [7]
In the citing paper
“This problem is solved by squaring the response map and then finding the confidence of the squared response map [7].”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [7]
In the citing paper
“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.”
From Object Tracking Benchmark (2015) · cites this paper as [47]
In the citing paper
“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.”
From Object Tracking Benchmark (2015) · cites this paper as [47]
Citations
Cites
Golub, G. (2012) · doi:10.56021/9781421407944 · Cited by 34,505
Advances in neural information processing systems 7
(1996) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(96)90463-0 · Cited by 14,281
(1981) · Cited by 11,963
Goodall, C. (1988) · Technometrics · doi:10.1080/00401706.1988.10488412 · Cited by 8,675
Jolliffe, I. T. (1986) · Springer Series in Statistics · doi:10.1007/978-1-4757-1904-8 · Cited by 8,273
Cootes, T. F., Edwards, G. J., & Taylor, C. J. (2001) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.927467 · Cited by 5,409
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 · cited 6×
“2003) (shown in highlighted ellipse) and the Mean Shift (Comaniciu et al. 2003) (depicted by a green dashed box) on four video sequences”
BackgroundMethodInfluentialProbabilistic Principal Component Analysis
Tipping, M. E., & Bishop, C. M. (1999) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/1467-9868.00196 · Cited by 3,679 · cited 2×
“Since our goal is to use a representation to describe the “thing” that we are tracking, we model image observations using a probabilistic interpretation of principal component analysis (Tipping and Bishop 1999).”
MethodReal-time tracking of non-rigid objects using mean shift
Comaniciu, D., Ramesh, V., & Meer, P. (2002) · Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662) · doi:10.1109/cvpr.2000.854761 · Cited by 2,906 · cited 1×
“Examples abound, ranging from representation methods based on view-based appearance models, [6], contours [17], parametric templates of geometry and illumination [13], integration of shape and color [4], mixture models [5], 3D models [21], exemplars [34], foreground/background models [16] templates with updating [26];…”
Advances in Neural Information Processing Systems 18
Murray, I., Mackay, D., Zoubin Ghahramani, A., & Skilling, J. (2006) · Cited by 1,927
Cited by
Items 601–700 of 1,001
Fast and Robust Object Tracking via Probability Continuous Outlier Model
Wang, D., Lu, H., & Bo, C. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2478399 · Cited by 29
“In the OSPT method, the tracked object is represented by a series of sparse prototypes (i.e., PCA basis vectors and trivial templates).”
BackgroundMethodInfluentialKhan, Z. H., & Gu, I. Y. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tsmcb.2013.2237900 · Cited by 29
“For subspace-based online learning, [2] proposes a method that performs incremental subspace tracking and learning, where the mean vector and eigen bases are updated without storing the covariances or previous objects.”
BackgroundMethodVisual Tracking via Constrained Incremental Non-negative Matrix Factorization
Zhang, H., Hu, S., Zhang, X., & Luo, L. (2015) · IEEE Signal Processing Letters · doi:10.1109/lsp.2015.2404856 · Cited by 29
“To demonstrate the improved performance of our tracker, by using eight challenging image sequences, we compare the tracking results of our method with other seven algorithms, including IVT [5], APGL1 [22], MIL [23], L1 [3], TLD [24], VTD [25] and OSPT [16].”
BackgroundMethodInfluentialTRIC-track: Tracking by Regression with Incrementally Learned Cascades
Wang, X., Valstar, M., Martínez, B., Khan, M. H., & Pridmore, T. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.493 · Cited by 30
“We use incremental learning [17] as our regressor update method.”
MethodYoon, J. H., Yang, M., & Yoon, K. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2473862 · Cited by 29
“, pðztjxt;mtÞ in (1)) is based on the incremental subspace model [27] for its computational efficiency over ‘1 sparse coding.”
BackgroundMethodInfluentialSelf-citationTemporal Restricted Visual Tracking Via Reverse-Low-Rank Sparse Learning
Yang, Y., Hu, W., Xie, Y., Zhang, W., & Zhang, T. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2519532 · Cited by 33
“[5] represented each target candidate via a”
InfluentialObject tracking based on online representative sample selection via non-negative least square
Ou, W., Yuan, D., Liu, Q., & Cao, Y. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4672-3 · Cited by 31
Incremental Tensor-Based Completion Method for Detection of Stationary Foreground Objects
Kajo, I., Kamel, N., & Ruichek, Y. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2841825 · Cited by 29
Incremental Ensemble Gaussian Processes
Lu, Q., Karanikolas, G. V., & Giannakis, G. B. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3157197 · Cited by 38
Haik, W., Maday, Y., & Chamoin, L. (2023) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2022.115868 · Cited by 29
Crowd Density Estimation and Mapping Method Based on Surveillance Video and GIS
Zhang, X., Sun, Y., Li, Q., Li, X., & Shi, X. (2023) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi12020056 · Cited by 33
Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models
Haas, R., Huberman-Spiegelglas, I., Mulayoff, R., Graßhof, S., Brandt, S. S., & Michaeli, T. (2024) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg59268.2024.10581912 · Cited by 72
“We use Incremental PCA [30] in order to calculate PCA on more samples than would otherwise fit in memory.”
MethodOn-Line Random Naive Bayes for Tracking
Godec, M., Leistner, C., Saffari, A., & Bischof, H. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.865 · Cited by 30
“edu/ ̃dross/ivt/ [17] 4http://vision.”
Kloihofer, W., & Kampel, M. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.866 · Cited by 29
“[11]1, since they show a single object and one is recorded with a non-stationary camera.”
BackgroundTracking by Third-Order Tensor Representation
Wang, Q., Chen, F., & Xu, W. (2010) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2010.2056366 · Cited by 29
Robust multi-image based blind face hallucination
Jin, Y., & Bouganis, C.-S. (2015) · 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.2015.7299162 · Cited by 28
“Note that this image prior can also be interpreted in two terms [21]: Euclidean distance to the PCA subspace and Mahalanobis distance within the PCA subspace.”
Robust hand tracking via novel multi-cue integration
Zhang, X., Li, W., Ye, X., & Maybank, S. J. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.01.002 · Cited by 29
A survey of datasets for visual tracking
Dubuisson, S., & Gonzales, C. (2015) · Machine Vision and Applications · doi:10.1007/s00138-015-0713-y · Cited by 29
“The Ross dataset [44] Fig.”
BackgroundConvolutional neural net bagging for online visual tracking
Li, H., Li, Y., & Porikli, F. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.07.002 · Cited by 29
“Among the competitors, TPGR [5] and KCF [30] are the most recently state-of-the-art visual trackers; TLD [31], VTD [32], CXT [33], ASLA [34], Struck [3], SCM [35] are the top-6 methods as reported in the benchmark; CPF [15], IVT [36] and MIL [4] are classical tracking methods which are used as baselines.”
MethodCo-difference based object tracking algorithm for infrared videos
Demir, H. S., & Çetin, A. E. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532394 · Cited by 28
“EXPERIMENTS We compared the proposed co-difference based tracking algorithm with various state-of-the-art trackers: COV [5], TBOOST [2], MILTrack [8], ODFS [9], FCT [10], STRUCK [11], L1APG [12], MOSSE [13], CRC [14] and IVT [15].”
MethodSIFT flow for abrupt motion tracking via adaptive samples selection with sparse representation
Zhang, H., Wang, Y., Luo, L., Lu, X., & Zhang, M. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.04.024 · Cited by 28
Robust Visual Tracking via Hierarchical Particle Filter and Ensemble Deep Features
Li, S., Zhao, S., Cheng, B. H., Zhao, E., & Chen, J. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2889457 · Cited by 29
“The latter performs by treating the object appearance as the generative process and estimating the most similar patch, including principal component analysis [8], dictionary learning [23], sparse coding [24] and et al .”
BackgroundMethodFu, C.-H., Huang, Z.-Y., Li, Y., Duan, R., & Lu, P. (2019) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros40897.2019.8967674 · Cited by 23
“HCF [9], BACF [5], KCF [7], StapleCA [18], Staple [19], Struck [20], ASLA [21], CSK [22], IVT [23], PTAV [24], TLD [25], MUSTER [26], MCCT [27], MCCT-H [27], DCF [7], STRCF [28], SRDCF [6], MEEM [29], SAMF”
BackgroundTarget Tracking Using a Mean-Shift Occlusion Aware Particle Filter
Bhat, P. G., Subudhi, B. N., Veerakumar, T., Caterina, G. D., & Soraghan, J. J. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3054815 · Cited by 29
“The proposed method is compared with fourteen state-of-the-art tracking algorithms: DSST [25], TLD [11], ECO [15], STRUCK [13], KCF [17], IVT [26], STAPLE [12], SiamFC [16], MDNet [27], SRDCF [14], SAMF [28], SiamRPN [29], DNT [30] and TADT [31].”
MethodAdversarially Robust One-class Novelty Detection
Lo, S.-Y., Oza, P., & Patel, V. M. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3189638 · Cited by 55
“Specifically, PLS learns the incrementallytrained [24] cascade principal components in the latent space.”
BackgroundSurvey of single‐target visual tracking methods based on online learning
Liu, Q., Zhao, X., & Hou, Z. (2014) · IET Computer Vision · doi:10.1049/iet-cvi.2013.0134 · Cited by 31
Robust infrared target tracking based on particle filter with embedded saliency detection
Wang, F., Zhen, Y., Zhong, B., & Ji, R. (2015) · Information Sciences · doi:10.1016/j.ins.2014.12.022 · Cited by 28
“In the eigen space model, the image observation is formulated by using a probabilistic interpretation [40] of principal component analysis [24].”
MethodInfluentialTowards Occlusion Handling: Object Tracking With Background Estimation
Zhao, S., Zhang, S., & Zhang, L. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2727138 · Cited by 28
“The generative models represent the target directly with fragments (Frag), subspace (IVT), sparse dictionary (L1 and MTT), or complex cells (CCT).”
Robust object tracking using a sparse coadjutant observation model
Zhao, J., Zhang, W., & Cao, F. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6132-0 · Cited by 29
“Some online update schemes have been proposed, such as template update [23], and incremental subspace learning [11, 25, 29].”
InfluentialAdaptive fusion of particle filtering and spatio-temporal motion energy for human tracking
Zhou, H., Fei, M., Sadka, A. H., Zhang, Y., & Li, X. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.05.006 · Cited by 28
“Size and appearance descriptors can be dramatically affected in the presence of view line and illumination changes [11].”
BackgroundMethodInfluentialSpeeded Up Low-Rank Online Metric Learning for Object Tracking
Cong, Y., Fan, B., Liu, J., Luo, J., & Yu, H. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2355692 · Cited by 27
“Frag, IVT, MIL, L1 trackers all drift, PN loses the object at about #40 frame and retracks the object again; VTD, ONNDL, SCM, OML and ours track the object accurately, where ONNDL outperforms all other methods and SCM and our method get the same mean overlap score.”
InfluentialLinear time Principal Component Pursuit and its extensions using ℓ1 filtering
Liu, R., Lin, Z., Su, Z., & Gao, J. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.03.046 · Cited by 27
“In the following, we compare the proposed tracking framework with six state-of-the-art visual tracking algorithms, i.e., Incremental Visual Tracking (IVT) [28], Multiple Instance Learning (MIL) [29], Visual Tracking by Sampling (VTS) [30], Tracking-LearningDetection (TLD) [31], L1 Minimization (L1) [32,33] and Sparse…”
BackgroundMethodInfluentialAdaptive Appearance Model and Condensation Algorithm for Robust Face Tracking
Lui, Y. M., Beveridge, J. R., & Whitley, L. D. (2010) · IEEE Transactions on Systems Man and Cybernetics - Part A Systems and Humans · doi:10.1109/tsmca.2010.2041655 · Cited by 27
Extended compressed tracking via random projection based on MSERs and online LS-SVM learning
Gao, Y., Shan, X. J., Hu, Z., Wang, D., Li, Y., & Tian, X.-H. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.02.012 · Cited by 29
Image set classification by symmetric positive semi-definite matrices
Faraki, M., Harandi, M. T., & Porikli, F. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477621 · Cited by 27
“[31].”
Robust Tracking and Redetection: Collaboratively Modeling the Target and Its Context
Liu, C., Liu, P., Zhao, W., & Tang, X. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2760633 · Cited by 27
“8 STC [37] CT [27] IVT [19] L1APG [38] LOT [18] ASLA [39] DSST [31] OS(%) 31.”
BackgroundMethodDeep Location-Specific Tracking
Yang, L., Liu, R., Zhang, D. D., & Zhang, L. (2017) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3123266.3123381 · Cited by 28
“Many methods have been proposed for the visual tracking problem, such as multiple instance learning [2], subspace learning [32, 36, 43], ensemble learning [1, 16, 47], compressive coding [48], etc.”
BackgroundMethodRobust Object Tracking Algorithm for Autonomous Vehicles in Complex Scenes
Cao, J., Song, C., Song, S., Xiao, F., Zhang, X., Liu, Z., & Ang, M. H. (2021) · Remote Sensing · doi:10.3390/rs13163234 · Cited by 29
“[9] proposed a robust incremental learning algorithm for object tracking.”
BackgroundGesture Control for Consumer Electronics
Shan, C. (2010) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-84996-507-1_5 · Cited by 27
“Ross et al. [ 68 ] represented the target in a low-dimensional subspace which is adaptively updated using the tracking results.”
MethodCo-Learned Multi-View Spectral Clustering for Face Recognition Based on Image Sets
Huang, L., Lu, J., & Tan, Y. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2319817 · Cited by 27
“Due to the low quality of this Database, we apply a tracking algorithm [26] to crop face regions across frames of each video.”
MethodEnhancement of Construction Equipment Detection in Video Frames by Combining with Tracking
Park, M.-W., & Brilakis, I. (2012) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784412343.0053 · Cited by 27
“’s comparative study (2011), a kernel-based method (Ross et al., 2008) is used for tracking.”
MethodVisual Tracker Using Sequential Bayesian Learning: Discriminative, Generative, and Hybrid
Lei, Y., Ding, X., & Wang, S. (2008) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2008.928226 · Cited by 27
“1) WSL tracker [5]; 2) incremental subspace learning (ISL) tracker [2]; 3) mean-shift tracker [6].”
BackgroundMethodRobust Target Tracking by Online Random Forests and Superpixels
Wang, W., Wang, C., Liu, S., Zhang, T., & Cao, X. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2684759 · Cited by 27
“lenge DSST [48], and incremental learning tracking method IVT [19].”
BackgroundMethodInfluentialSpatial Neighborhood-Constrained Linear Coding for Visual Object Tracking
Liu, H., Yuan, M., Sun, F., & Zhang, J. (2013) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2013.2247613 · Cited by 26
Visual Tracking via Locally Structured Gaussian Process Regression
Sui, Y., & Zhang, L. (2015) · IEEE Signal Processing Letters · doi:10.1109/lsp.2015.2402313 · Cited by 28
“Subspace representation [4]–[6] assumes that the temporally obtained targets reside in a low-dimensional subspace, and the principal components analysis method is used to evaluate the representation.”
MethodReverse Training: An Efficient Approach for Image Set Classification
Hayat, M., Bennamoun, M., & An, S. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10599-4_50 · Cited by 29
“[21] to track the face region in the subsequent frames.”
BackgroundMethodWan, M., Xiao-bo, Y., Zhang, X., Xu, Y., Gu, G., & Chen, Q. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3051183 · Cited by 30
Channel Graph Regularized Correlation Filters for Visual Object Tracking
Jain, M., Tyagi, A., Subramanyam, A. V., Denman, S., Sridharan, S., & Fookes, C. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3063144 · Cited by 27
Robust Principal Component Thermography for Defect Detection in Composites
Ebrahimi, S., Fleuret, J. R., Klein, M. T., Théroux, L.-D., Georges, M. P., Ibarra‐Castanedo, C., & Maldague, X. (2021) · Sensors · doi:10.3390/s21082682 · Cited by 26
“In each iteration after solving Ak+1 and Ek+1, the low-rank matrix L is updated by Incremental-PCA [53].”
MethodTracking video objects with feature points based particle filtering
Gao, T., Li, G., Lian, S., & Zhang, J. (2011) · Multimedia Tools and Applications · doi:10.1007/s11042-010-0676-y · Cited by 28
“Ross [31, 32] proposed a method that incrementally learns and adapts a low dimensional eigenspace representation to reflect appearance changes of the object.”
MethodSparse representations of image gradient orientations for visual recognition and tracking
Tzimiropoulos, G., Zafeiriou, S. P., & Pantić, M. (2011) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2011.5981809 · Cited by 27
“As usual, quantitative performance evaluation is based on the RMS errors between the true and the estimated locations of these seven points [13].”
MethodImproved Practical Matrix Sketching with Guarantees
Desai, A., Ghashami, M., & Phillips, J. M. (2016) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2016.2539943 · Cited by 26
“Index Terms—Low-rank matrix approximation, Streaming algroithm, Frequent Directions F”
BackgroundWu, K. J., Gregory, T. S., Moore, J., Hooper, B., Lewis, D., & Tse, Z. T. H. (2016) · IET Radar Sonar & Navigation · doi:10.1049/iet-rsn.2016.0232 · Cited by 26
Object Tracking Using Multiple Features and Adaptive Model Updating
Hu, Q., Guo, Y., Lin, Z., An, W., & Cheng, H. (2017) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2017.2729378 · Cited by 28
“Some representative generative trackers include incremental visual tracker (IVT) [15], frag-track (Frag) [16], and circulant sparse tracker (CST) [17].”
BackgroundRobust object tracking with crow search optimized multi-cue particle filter
Walia, G. S., Kumar, A., Saxena, A., Sharma, K., & Singh, K. (2019) · Pattern Analysis and Applications · doi:10.1007/s10044-019-00847-7 · Cited by 27
Feature Particles Tracking for Moving Objects
Gao, T., Wang, P., Wang, C., & Yao, Z. (2012) · Journal of Multimedia · doi:10.4304/jmm.7.6.408-414 · Cited by 25
“detection, background subtraction and inter-frame differencing [5] [6].”
BackgroundRobust visual tracking using discriminative sparse collaborative map
Zhou, Z., Zhang, W., & Zhao, J. (2019) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-019-01011-7 · Cited by 26
Object tracking using learned feature manifolds
Guo, Y., Chen, Y., Tang, F., Li, A., Luo, W., & Liu, M. (2013) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2013.09.007 · Cited by 25
Graph-Regularized Structured Support Vector Machine for Object Tracking
Zhang, S., Sui, Y., Zhao, S., & Zhang, L. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2513659 · Cited by 27
Online Sparse Matrix Gaussian Process Regression and Vision Applications
Ranganathan, A., & Yang, M. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88682-2_36 · Cited by 25
“Two publicly available datasets from [19], namely the Fish and Sylvester datasets are used to evaluate these algorithms.”
MethodSelf-citationVisual tracking with semi-supervised online weighted multiple instance learning
Wang, Z., Yoon, S., Xie, S. J., Lu, Y. F., & Park, D. S. (2015) · The Visual Computer · doi:10.1007/s00371-015-1067-1 · Cited by 25
“Eight state-of-the-art trackers, which included MIL [18], WMIL [19], ODFS [27], RTCT [28], IVT [29], DFT [30], LIAPG [31], MTT [32] were compared with the proposed Semi-WMIL tracker for these video sequences.”
MethodAdaptive pedestrian tracking via patch-based features and spatial–temporal similarity measurement
Shen, X., Sui, X., Pan, K., & Tao, Y. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.11.017 · Cited by 25
Efficient Frequent Directions Algorithm for Sparse Matrices
Ghashami, M., Liberty, E., & Phillips, J. M. (2016) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2939672.2939800 · Cited by 25
“Examples of these methods include di↵erent version of iterative SVD [19, 21, 23, 5, 33].”
MethodImproving retail efficiency through sensing technologies: A survey
Quintana, M. I., Menéndez, J. M., Álvarez, F., & López, J. P. (2016) · Pattern Recognition Letters · doi:10.1016/j.patrec.2016.05.027 · Cited by 31
Real-Time Adaptive Histogram Min-Max Bucket (HMMB) Model for Background Subtraction
Roy, S. M., & Ghosh, A. K. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2669362 · Cited by 25
“The algorithm used an incremental singular value decomposition (SVD) [34] method to discover the dominant projection subspaces of a 3rd-order tensor and adaptively updated the sample mean and an eigenbasis when new frames arrive.”
MethodRobust object tracking via multi-cue fusion
Hu, M., Liu, Z., Zhang, J., & Zhang, G. (2017) · Signal Processing · doi:10.1016/j.sigpro.2017.04.008 · Cited by 28
Khan, S., Xu, G., Chan, R., & Yan, H. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.08.039 · Cited by 27
A robust visual tracking method via local feature extraction and saliency detection
Wang, Y., Wei, X., Ding, L., Tang, X., & Zhang, H. (2019) · The Visual Computer · doi:10.1007/s00371-019-01646-1 · Cited by 25
“They are Struck [33], SCM [54], TLD [55], VTD [56], VTS [57], CXT [58], CSK [16], ASLA [59], DFT [60], LSK [61], CPF [62], LOT [63], IVT [12], KMS [64], L1 [3], MTT [5], MIL [7], L1APG [4], OAB [65], SemiT [66], Frag [67], ORIA [68], BSBT [69] and SMS [70].”
BackgroundMethodOnline Object Tracking, Learning and Parsing with And-Or Graphs
Wu, T., Lu, Y., & Zhu, S. C. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2644963 · Cited by 29
“i) Appearance modeling of the whole object, such as incremental learning [29], kernel-based [30], particle filtering [15], sparse coding [31] and 3D-DCT representation [32]; More recently, Convolutional neural networks are utilized in improving tracking performance [5], [6], [33], which are usually pre-trained on some…”
MethodEfficient object tracking using hierarchical convolutional features model and correlation filters
Abbass, M. Y., Kwon, K.-C., Kim, N., Abdelwahab, S. A., El-Samie, F. E. A., & Khalaf, A. A. M. (2021) · The Visual Computer · doi:10.1007/s00371-020-01833-5 · Cited by 24
Adeel, A. (2020) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2020.00015 · Cited by 30
“Finally, the object tracker (Ross et al., 2008) is used to track the lip regions across the sequence of frames. visual extraction procedure produced a set of corner points for each frame, where lip regions are then extracted by cropping the raw image.”
MethodRobust 2D Principal Component Analysis: A Structured Sparsity Regularized Approach
Sun, Y., Tao, X., Li, Y., & Lü, J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2419075 · Cited by 25
Learning structured visual dictionary for object tracking
Yang, F., Lu, H., & Yang, M. (2013) · Image and Vision Computing · doi:10.1016/j.imavis.2013.09.008 · Cited by 25
“At time t, we draw L candidate statesXt={xt}i=1 L where xt=(cxt, cyt, st , θt) around the tracked object at time t−1 using random walks with factorized Gaussians in a way similar to [38].”
MethodSelf-citationObject Tracking With Joint Optimization of Representation and Classification
Wang, Q., Chen, F., Xu, W., & Yang, M. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2339571 · Cited by 26
“The challenging factors of the sequences for comparison are listed in Table I, and the compared trackers include: the Lucas–Kanade tracker (KLT) [3], incremental visual tracking (IVT) [6], fragments-based tracker (FGT) [8], semisupervised tracker (SST) [23], MIL tracking [20], 1 tracking (L1T) [11], visual tracking de…”
BackgroundMethodSelf-citationA novel joint tracker based on occlusion detection
Li, X., He, Z., You, X., & Chen, C. L. P. (2014) · Knowledge-Based Systems · doi:10.1016/j.knosys.2014.08.019 · Cited by 24
“The incremental method proposed in [2] is used on the tracking results, which can adapt to the appearance change and maintain the constant feature of the target.”
BackgroundMethodInfluentialAutomatic Bootstrapping and Tracking of Object Contours
Chiverton, J., Xie, X.-H., & Mirmehdi, M. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2167343 · Cited by 26
“The authors compared their work with that in [18], which was described as robust because of the use of an incremental PCA approach for (online) learning the appearance of the tracked object.”
MethodVisual Tracking via Temporally Smooth Sparse Coding
Liu, T., Wang, G., Wang, L., & Chan, K. L. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2365363 · Cited by 26
“Besides the mentioned sparse coding based L1 trackers, we also test the speed of IVT, which is the baseline of most particle filter based tracking methods.”
BackgroundMethodInfluentialRobust object tracking based on local region sparse appearance model
Han, G., Wang, X., Liu, J., Sun, N., & Wang, C. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.07.122 · Cited by 24
“8, we can see that tracking drift occurs in the STC, IVT, Frag, MTT and LSK algorithms, since their update mechanisms do not consider partial occlusion.”
MethodInfluentialEmpowering Simple Binary Classifiers for Image Set Based Face Recognition
Hayat, M., Khan, S. H., & Bennamoun, M. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-017-1000-3 · Cited by 26
“We, therefore, use tracking (Ross et al. 2008) to extract faces.”
MethodOnline hash tracking with spatio-temporal saliency auxiliary
Fang, J., Xu, H., Wang, Q., & Wu, T. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.03.006 · Cited by 24
High-performance UAVs visual tracking based on siamese network
Yang, S., Chen, H., Xu, F., Li, Y., & Yuan, J. (2021) · The Visual Computer · doi:10.1007/s00371-021-02271-7 · Cited by 26
Forward–Backward Mean-Shift for Visual Tracking With Local-Background-Weighted Histogram
Wang, L., Yan, H., Wu, H., & Pan, C. (2013) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2013.2263281 · Cited by 24
“Robustness can be enhanced with the use of subspace models of appearance [15], [31].”
BackgroundAli, A., Jalil, A., Ahmed, J., Iftikhar, M. A., & Hussain, M. (2014) · Signal Image and Video Processing · doi:10.1007/s11760-014-0612-0 · Cited by 24
“, incremental visual tracking (IVT) [79], λ1 tracker [80], PN learning [81], visual tracking decomposition (VTD) [70], MIL tracker [66], FragTrack [60], local sparse appearance model (LSAM) [69], PROST [67], and EENC tracker [27,30].”
Varfolomieiev, A. Y., & Lysenko, O. M. (2013) · Journal of Real-Time Image Processing · doi:10.1007/s11554-013-0354-1 · Cited by 24
“Compared to other state-of-the-art frameworks [1, 2, 3, 7, 11, 12, 16] the improved median flow tracker shows acceptable and even better reliability, and considerably higher operation speed.”
BackgroundMethodRobust Visual Tracking Using Flexible Structured Sparse Representation
Bai, T., & Li, Y. (2013) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2013.2272089 · Cited by 24
“The learned Eigen templates provide a richer description than the raw templates because they span an optimal subspace that has the smallest reconstruction error with not only the current nut also the past appearance information.”
BackgroundImproving Pothole Recognition through Vision Tracking for Automated Pavement Assessment
Koch, C., & Brilakis, I. (2011) · Cambridge University Engineering Department Publications Database · Cited by 24
Robust tracking via monocular active vision for an intelligent teaching system
Wang, R., Dong, H., Han, T. X., & Mei, L. (2016) · The Visual Computer · doi:10.1007/s00371-015-1206-8 · Cited by 24
“To better account for appearance changes, subspace-based models have been proposed [10,11].”
BackgroundMethodECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning
Kim, B., Yu, J., & Hwang, S. J. (2024) · 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/cvpr52733.2024.00322 · Cited by 48
“It is critical in real-world applications where new classes emerge unpredictably, such as in robotics [39] and surveillance [38].”
BackgroundVisual Tracking via Sparse and Local Linear Coding
Wang, G., Qin, X., Zhong, F., Liu, Y., Li, H., Peng, Q., & Yang, M. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2445291 · Cited by 23
“The affine state describing the parameters of an object is typically denoted by t = (xt , yt , ηt , st , βt , θt ), which comprises the x and y translations, rotation angle, scale, aspect ratio, and skew direction at time t , respectively.”
BackgroundMethodSelf-citationVisual Tracking by Sampling Tree-Structured Graphical Models
Hong, S., & Han, B. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10590-1_1 · Cited by 25
“Most of them are online trackers, which include MIL [8], LSK [25], CSK [26], DFT [27], IVT [6], MTT [7], VTD [28], VTS [29], FRAG [30], L1APG [2], CXT [31], ASLA [32], SCM [4], Struck [33], TLD [9] and WLMC [10], while OTLE [12] and OMA [1] are offline trackers.”
BackgroundReview on Kernel based Target Tracking for Autonomous Driving
Wang, Y., Yue, J., Dong, Y., & Hu, Z. (2016) · Journal of Information Processing · doi:10.2197/ipsjjip.24.49 · Cited by 24
“Moreover, the multiple subspace temples in IPCA and DIKT also strengthen the stability of trackers.”
BackgroundMethodInfluentialRobust Visual Tracking Using Exemplar-Based Detectors
Gao, C., Chen, F., Yu, J.-G., Huang, R., & Sang, N. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2513700 · Cited by 25
“multiple-instance learning tracker (MIL) [4], Struck [6], the online boosting tracker (OAB) [7], the incremental visual tracking method (IVT) [21], the visual tracking decomposition algorithm (VTD) [24], and the fragment tracker (Frag) [40].”
MethodBeyond Standard Benchmarks: Parameterizing Performance Evaluation in Visual Object Tracking
Zajc, L. Č., Lukežič, A., Leonardis, A., & Kristan, M. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.360 · Cited by 25
“Both benchmarks rank Struck as top performing and IVT as worst performing.”
BackgroundInfluentialVisual object tracking with online sample selection via lasso regularization
Liu, Q., Ma, X., Ou, W., & Zhou, Q. (2017) · Signal Image and Video Processing · doi:10.1007/s11760-016-1035-x · Cited by 23
“Several approaches have been proposed in the past years, which can be classified into generative methods [15,19,23,24] and discriminative methods [3,6,10,13,16,18,31].”
BackgroundOnline Feature Selection for Visual Tracking
Roffo, G., & Melzi, S. (2016) · British Machine Vision Conference (BMVC) · doi:10.5244/c.30.120 · Cited by 27
Evolving Head Tracking Routines With Brain Programming
Olague, G., Hernandez, D. E., Clemente, E., & Chan-Ley, M. (2018) · IEEE Access · doi:10.1109/access.2018.2831633 · Cited by 23
“Also, several tracking algorithms have been proposed through the idea of incremental learning based on updating appearance models [55] and on-line sparse principal component analysis [31].”
MethodApplication of deep learning to large scale riverine flow velocity estimation
Forghani, M., Qian, Y., Lee, J. H., Farthing, M. W., Hesser, T., Kitanidis, P. K., & Darve, E. (2021) · Stochastic Environmental Research and Risk Assessment · doi:10.1007/s00477-021-01988-0 · Cited by 28
Feature Aggregation Networks Based on Dual Attention Capsules for Visual Object Tracking
Cao, Y., Ji, H., Zhang, W., & Shirani, S. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3063001 · Cited by 25
Zadobrischi, E., & Dimian, M. (2021) · Remote Sensing · doi:10.3390/rs13071234 · Cited by 23
“These adjustments demonstrate that there is the capacity for consistent improvements in the section dedicated to position, lighting, and area [81,82].”
BackgroundA KCF-Based Incremental Target Tracking Method With Constant Update Speed
Zhao, F., Hui, K., Wang, T., Zhang, Z., & Chen, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3080308 · Cited by 24
“To address the above model drifting problem, the methods in [25], [26] focus on improving the model updating process.”
Method
Metadata
- Authors
- Ross, D. A., Lim, J., Lin, R.-S., & Yang, M.-H.
- Affiliations
- University of Toronto (CA)
- Honda Research Institute, USA (US)
- Motorola (United States) (US)
- Corresponding author
- Ross, David A.
- Venue
- International Journal of Computer Vision
- Published
- 2007-08-17
- Volume
- 77
- Issue
- 1-3
- Pages
- 125-141
- ISSN
- 0920-5691 (ISSN-L)
- 1573-1405
- OpenAlex
- W2139047213
- Cited by
- 3,061
- References
- 43
- Citations by year
- 2026: 25 · 2025: 47 · 2024: 53 · 2023: 51 · 2022: 83 · 2021: 126 · 2020: 148 · 2019: 244 · 2018: 279 · 2017: 324 · 2016: 340 · 2015: 359 · 2014: 331 · 2013: 214 · 2012: 161
- FWCI
- 66.90
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- International Journal of Computer Vision (publishedVersion)
- Funders
- Honda Research Institute, USA
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- visual object tracking, incremental learning, principal component analysis, appearance modeling, forgetting factor, illumination variation, robust tracking
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.