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 901–1,000 of 1,001
Multi-manifold metric learning for face recognition based on image sets
Huang, L., Lu, J., & Tan, Y. (2014) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2014.08.006 · Cited by 16
“To overcome this problem, we apply an incremental visual tracking algorithm [49] to track faces in each frame of the Youtube Celebrities database, as mentioned in [48].”
MethodThe VOT2013 challenge: overview and additional results
Kristan, M., Pflugfelder, R. P., Leonardis, A., Matas, J., Porikli, F., Zajc, L. Č., Nebehay, G., Fernández, G. J., & Vojíř, T. (2014) · ANU Open Research (Australian National University) · Cited by 16
An Efficient Tracking System by Orthogonalized Templates
Yang, X., Wang, M., Zhang, L., Sun, F., Hong, R., & Qi, M. (2016) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2016.2515559 · Cited by 16
“In [29], the residual term e is assumed to be Gaussian distributed with a small variance.”
BackgroundMethodInfluentialDiscriminative Hash Tracking With Group Sparsity
Du, D., Zhang, L., Lu, H., Mei, X., & Li, X. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2457618 · Cited by 16
“The ten trackers are the FRAG tacker [47], IVT tracker [26],”
BackgroundVisual Tracking by Sampling in Part Space
Huang, L., Ma, B., Shen, J., He, H., Shao, L., & Porikli, F. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2745204 · Cited by 17
Context-based occlusion detection for robust visual tracking
Niu, X., & Qiao, Y. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296964 · Cited by 18
“We choose KCF [2], Struck [12], SCM [13], TLD [14], CSK [15], IVT [16] and MIL [17] for comparison.”
MethodLearning target-aware correlation filters for visual tracking
Li, D., Wen, G., Kuai, Y., Xiao, J., & Porikli, F. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.11.036 · Cited by 16
Memory Mechanisms for Discriminative Visual Tracking Algorithms With Deep Neural Networks
Wang, L., Zhang, L., Wang, J., & Zhang, Y. (2019) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2019.2900506 · Cited by 16
“Generative methods assume that the target object can be described by some generative process, and typically search many candidates to minimize reconstruction errors [3]–[7].”
MethodParallelization of the Honeybee Search Algorithm for Object Tracking
Perez-Cham, O. E., Puente, C., Soubervielle‐Montalvo, C., Gustavo Olague, A., Aguirre-Salado, C. A., & Núñez-Varela, A. S. (2020) · Applied Sciences · doi:10.3390/app10062122 · Cited by 16
“The other trackers that are displayed are: Struck (STR) [45], Foreground-Background Tracker (FBT) [46], Tracking Learning and Detection (TLD) [47], Tracking by Sampling Trackers (TST) [48], Lucas-Kanade Tracker (LKT) [49], Kalman Appearance Tracker (KAT) [50], Fragments-based Robust Tracking (FRT) [51], Mean Shift Tra…”
Grassmannian learning mutual subspace method for image set recognition
de Souza, L. S., Sogi, N., Gatto, B. B., Kobayashi, T., & Fukui, K. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.10.040 · Cited by 19
Robust Visual Tracking with SIFT Features and Fragments Based on Particle Swarm Optimization
Cheng, X., Li, N., Zhang, S., & Wu, Z. (2013) · Circuits Systems and Signal Processing · doi:10.1007/s00034-013-9713-1 · Cited by 17
“Mean shift [5, 8, 9], Particle filter [2, 21], Condensation [16], Subspace-based tracking method [23], FragTrack [1, 10] and Visual tracking decomposition [18].”
MethodInfluentialRobust Tracking via Locally Structured Representation
Sui, Y., & Zhang, L. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-016-0881-x · Cited by 17
“A robust representation always has some structures, e.g., subspace (Ross et al. 2007; Kwon and Lee 2010; Wang and Lu 2012), sparsity (Mei and Ling 2009; Liu et al. 2010; Mei et al. 2011), and compactness (Li et al. 2013).”
BackgroundInfluentialUnderstanding Tracking Methodology of Kernelized Correlation Filter
Yadav, S., & Payandeh, S. (2018) · IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) · doi:10.1109/iemcon.2018.8614990 · Cited by 19
A Visual Analytics Framework for Reviewing Streaming Performance Data
Kesavan, S. P., Fujiwara, T., Li, J. K., Ross, C. J., Mubarak, M., Carothers, C. D., Ross, R. B., & Ma, K. (2020) · IEEE Pacific Visualization Symposium · doi:10.1109/pacificvis48177.2020.9280 · Cited by 16
“The Procrustes transformation tries to find the best overlap between two sets of positions (i.e., the previous and updated PCA results in our case) by using a combination of translation, uniform scaling, rotation, and reflection.”
BackgroundMethodInfluentialNoise-Aware Framework for Robust Visual Tracking
Li, S., Zhao, S., Cheng, B. H., & Chen, J. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2996245 · Cited by 18
Occluded object tracking using object-background prototypes and particle filter
Mondal, A. (2021) · Applied Intelligence · doi:10.1007/s10489-020-02047-x · Cited by 17
Zaheer, R., Hanif, M. K., Sarwar, M. U., & Talib, R. (2025) · IEEE Access · doi:10.1109/access.2025.3551741 · Cited by 20
Model-Based Tracking at 300Hz Using Raw Time-of-Flight Observations
Stühmer, J., Nowozin, S., Fitzgibbon, A. W., Szeliski, R., Perry, T., Acharya, S., Cremers, D., & Shotton, J. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.408 · Cited by 15
“General purpose tracking approaches address these challenges through adaptive non-parametric methods, as in mean-shift tracking [4], and by online learning of a flexible object representation [22].”
BackgroundRobust Object Tracking via Large Margin and Scale-Adaptive Correlation Filter
Li, J., Zhou, X., Chan, S., & Chen, S. (2017) · IEEE Access · doi:10.1109/access.2017.2778740 · Cited by 16
“The generative methods (IVT [5], VTD [6], L1-norm tracker [4], [7], [8]) model tracking task as minimizing reconstruction error based on some given target templates, and then search for the most similar patches as tracking result.”
MethodRen, C., & Xu, Y. H. (2020) · IET Generation Transmission & Distribution · doi:10.1049/iet-gtd.2019.1371 · Cited by 15
“To address the real-time DSA model updating problem, this study proposes an incremental broad learning method for accuracy maintenance and improvement of the data-driven DSA models [30–32].”
MethodIntransitive Atmosphere Dynamics Leading to Persistent Hot–Dry or Cold–Wet European Summers
Weiland, R. S., van der Wiel, K., Selten, F., & Coumou, D. (2021) · Journal of Climate · doi:10.1175/jcli-d-20-0943.1 · Cited by 15
Augmented bilinear network for incremental multi-stock time-series classification
Shabani, M., Tran, D. T., Kanniainen, J., & Iosifidis, A. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109604 · Cited by 21
Correlation filter based visual trackers for person pursuit using a low-cost Quadrotor
Haag, K., Dotenco, S., & Gallwitz, F. (2015) · International Conference on Innovations for Community Services (I4CS) · doi:10.1109/i4cs.2015.7294481 · Cited by 19
Visual Object Tracking Based on Backward Model Validation
Yuan, Y., Emmanuel, S., Fang, Y., & Lin, W. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2319632 · Cited by 15
“In order to address the problems from appearance variations during tracking, online appearance model based algorithms have been investigated by several early studies [1], [2], [3].”
BackgroundMethodResultInfluentialDiscriminative multi-task objects tracking with active feature selection and drift correction
Fan, B., Cong, Y., & Du, Y. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.06.015 · Cited by 15
“However, IVT is less effective in handling heavy occlusion or non-rigid distortion.”
BackgroundMethodInfluentialMinimum Uncertainty Gap for Robust Visual Tracking
Kwon, J., & Lee, K. 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.2013.305 · Cited by 15
“Using the sequences, the proposed method (MUG) was analyzed and compared with 6 state-of-the-art tracking methods, MC [16, 28], IVT [29], FRAGT [1], MIL [2], VTS [19], and MTT [37].”
MethodA comparison of tracking algorithm performance for objects in wide area imagery
Philip, R. C., Ram, S., Gao, X., & Rodríguez, J. J. (2014) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai.2014.6806041 · Cited by 15
“The SOT [11] and IVT [10] trackers are comparable in performance across all scenarios, with both failing to handle occlusion satisfactorily.”
BackgroundMethodMulti-feature Hashing Tracking
Ma, C., Liu, C., Peng, F., & Liu, J. (2015) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.09.019 · Cited by 16
Singular spectrum-based matrix completion for time series recovery and prediction
Tsagkatakis, G., Beferull‐Lozano, B., & Tsakalides, P. (2016) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-016-0360-0 · Cited by 15
Selective Sampling Importance Resampling Particle Filter Tracking With Multibag Subspace Restoration
Jenkins, M. D., Barrie, P., Buggy, T., & Morison, G. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2631660 · Cited by 15
“temporally as in algorithms such as IVT [16] and KCF [23] we use two bags of appearance models.”
BackgroundMethodInfluentialPatch-based visual tracking with online representative sample selection
Ou, W., Yuan, D., Li, D., Liu, B., Xia, D., & Zeng, W. (2017) · Journal of Electronic Imaging · doi:10.1117/1.jei.26.3.033006 · Cited by 15
Deep Learning and Preference Learning for Object Tracking: A Combined Approach
Pang, S., del Coz, J. J., Yu, Z., Luaces, O., & Díez, J. (2017) · Neural Processing Letters · doi:10.1007/s11063-017-9720-5 · Cited by 15
“As we can see, DPL2 performs quite well for both 1 2 3 4 5 6 7 8 9 101112131415 DPL SCM Struck ASLA TLD CXT CSK VTS VTD LSK IVT L1APG MTT MIL CT CD 2 1 2 3 4 5 6 7 8 9 101112131415 DPL SCM Struck VTS CXT TLD ASLA CSK VTD LSK IVT L1APG MTT MIL CT CD 2 Fig.”
MethodOnline discriminative dictionary learning for robust object tracking
Zhou, T., Liu, F., Bhaskar, H., Yang, J., Zhang, H., & Cai, P. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.10.019 · Cited by 15
Visual tracking via salient feature extraction and sparse collaborative model
Liu, Y. M., Feng, Y., Zhong, C., Tao, Y., Dai, B., & Yin, M. (2018) · AEU - International Journal of Electronics and Communications · doi:10.1016/j.aeue.2018.02.019 · Cited by 18
Discriminative tracking via supervised tensor learning
Xu, G., Khan, S., Zhu, H., Han, L., Ng, M. K., & Yan, H. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.05.108 · Cited by 16
Occlusion-Aware Correlation Particle Filter Target Tracking Based on RGBD Data
Zhai, Y., Song, P., Mou, Z., Chen, X.-X., & Liu, X. (2018) · IEEE Access · doi:10.1109/access.2018.2869766 · Cited by 19
Yang, X., Zhu, R., Wang, J., & Li, Z. (2019) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2019.01.020 · Cited by 15
SIFT-Based Visual Tracking using Optical Flow and Belief Propagation Algorithm
Biswas, B., Ghosh, S. K., Hore, M., & Ghosh, A. (2020) · The Computer Journal · doi:10.1093/comjnl/bxz155 · Cited by 16
A Bottom-Up and Top-Down Integration Framework for Online Object Tracking
Li, M., Peng, L., Wu, T., & Peng, Z. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.2978623 · Cited by 15
“In [54], Ross et al. have presented to learn a low dimensional subspace representation of the target objects with incremental learning, in which the new target observations are updated in the appearance model while preserving most of the previous knowledge.”
BackgroundMethodPyramid-based Scatterplots Sampling for Progressive and Streaming Data Visualization
Chen, X., Zhang, J., Fu, C., Fekete, J., & Wang, Y. (2021) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2021.3114880 · Cited by 15
“Citation information: DOI 10.1109/TVCG.2021.3114880, IEEE Transactions on Visualization and Computer Graphics incremental PCA [38] for visualizing streaming multidimensional data.”
BackgroundInfluentialComputer vision based object recognition principles in education
Lámer, J., Cymbalak, D., & Jakab, F. (2013) · International Conference on Emerging eLearning Technologies and Applications (ICETA) · doi:10.1109/iceta.2013.6674439 · Cited by 18
Privacy preserving video surveillance using pedestrian tracking mechanism
Zhang, P., Thomas, T., Emmanuel, S., & Kankanhalli, M. (2010) · ACM Workshop on Multimedia in Forensics, Security and Intelligence (MiFor) · doi:10.1145/1877972.1877983 · Cited by 15
“Then as in [12], the probability of a sample drawn from the subspace is estimated as:”
BackgroundImproved Practical Matrix Sketching with Guarantees
Ghashami, M., Desai, A., & Phillips, J. M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-44777-2_39 · Cited by 15
Part-Based Co-Difference Object Tracking Algorithm for Infrared Videos
Demir, H. S., & Adil, Ö. F. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451294 · Cited by 17
Karimah, S. N., & Hasegawa, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-78114-9_19 · Cited by 18
Robust Frequent Directions with Application in Online LearningPreprint
Luo, L., Chen, C., Zhang, Z., Li, W.-J., & Zhang, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.05067 · Cited by 15
Taalimi, A., Qi, H., & Khorsandi, R. (2015) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2015.7301775 · Cited by 14
“We compare our method with state-ofthe-art sparse-based trackers: MTT [22], L1T [13], ODDL [19] and with other non-sparse state-of-the-art methods: IVT [15], Frag [1], MIL [2], plus two feature-fusion based trackers COV [5] and OAB [4].”
MethodObject-tracking based on particle filter using particle swarm optimization with density estimation
Xia, G., & Ludwig, S. A. (2016) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2016.7744317 · Cited by 14
Robust visual tracking using dynamic feature weighting based on multiple dictionary learning
Liu, R., Lan, X., Yuen, P. C., & Feng, G. (2016) · European Signal Processing Conference (EUSIPCO) · doi:10.1109/eusipco.2016.7760632 · Cited by 14
A four dukkha state-space model for hand tracking
Lim, K. M., Tan, A. W. C., & Tan, S. C. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.06.012 · Cited by 14
Scene-Aware Adaptive Updating for Visual Tracking via Correlation Filters
Li, F., Zhang, S., & Qiao, X. (2017) · Sensors · doi:10.3390/s17112626 · Cited by 14
“The IVT algorithm in [5] represents the candidate samples by the mean and feature vectors in the lower dimensional feature space.”
MethodQian, C., Zhuang, Y., & Xu, Z. (2014) · Neurocomputing · doi:10.1016/j.neucom.2013.12.025 · Cited by 14
Global Coupled Learning and Local Consistencies Ensuring for sparse-based tracking
Yang, Y., Xie, Y., Zhang, W., Hu, W., & Tan, Y. (2015) · Neurocomputing · doi:10.1016/j.neucom.2014.12.060 · Cited by 14
“However, K can also be a flexible variable controlled by a predefined threshold τ0, i.e., K can be the number of particles whose global scores are over τ0 ð0oτ0o1Þ. trackers are compared with GLT algorithm on the benchmark video sequences; they are OAB [41], FragTrack [43], IVT [40], L1T [10], NNT [45], MIL [44], ODLS…”
BackgroundMethodInfluentialNotice of Removal: Patchwise Joint Sparse Tracking With Occlusion Detection
Zarezade, A., Rabiee, H. R., Soltani-Farani, A., & Khajenezhad, A. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2346029 · Cited by 14
“Ross et al. exploit eigenbasis update algorithms and proposed an incremental learning method [38] which updates eigenbases of the object subspace using incremental SVD with a forgetting factor.”
MethodCollaborative Tracking for Multiple Objects in the Presence of Inter-Occlusions
Xiao, J., & Oussalah, M. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2406193 · Cited by 19
“These features can be utilized in two distinct schemes: holistic approach [8-9] where a single appearance model for the whole target is employed, and a subspace-based approach [10-11], where different parts of the target are associated distinct appearance models.”
BackgroundIncremental robust local dictionary learning for visual tracking
Bai, S., Liu, R., Su, Z., Zhang, C., & Jin, W. (2014) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2014.6890262 · Cited by 14
“g [4, 8]) have been applied to visual tracking which are designed based on dimensionality reduction.”
MethodInfluentialLinear time offline tracking and lower envelope algorithms
Gu, S., Zheng, Y., & Tomasi, C. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126451 · Cited by 15
“We test our linear time offline tracking algorithm on 8 video sequences from multiple data sets [8, 29, 1, 5, 30] in the literature and compare it to the following state-of-art online tracking methods: FragTracker [1], Multiple Instance Learning [5], PROST [30] and Nearest Neighbor [18].”
MethodIncremental \(N\) -Mode SVD for Large-Scale Multilinear Generative Models
Lee, M., & Choi, C. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2346012 · Cited by 14
“The update of U′ and ′ can be accomplished using the scatter matrix D̃D̃T [18].”
BackgroundMethodInfluentialAdaptive Visual Tracking with Minimum Uncertainty Gap Estimation
Kwon, J., & Lee, K. M. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2537330 · Cited by 14
“To obtain the tracking results of IVT, MIL, FRAGT, VTS, MTT, TLD, STRUCK and ASLA, we used the software provided by the authors.”
MethodInfluentialUsing Discriminative Motion Context for Online Visual Object Tracking
Duffner, S., & García, C. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2504739 · Cited by 14
“Many recent works [16], [2], [4], [5], [3], [6], [9], [10], [11], [12] propose a tracking-by-detection framework, where a discriminative detector is trained with object and background image samples.”
Visual Tracking via Joint Discriminative Appearance Learning
Sun, C., Li, F., Lu, H., & Hua, G. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2595265 · Cited by 14
“Most Bayesian tracking algorithms [2], [17], [19], [26] exploit the particle filter (PF) to inference the posterior state of the target object.”
BackgroundObject tracking using color-feature guided network generalization and tailored feature fusion
Wang, J., Zhu, H., Yu, S., & Fan, C. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.02.001 · Cited by 14
Vision-based surveillance system for monitoring traffic conditions
Park, M.-W., Kim, J. I., Lee, Y.-J., Park, J., & Suh, W. (2017) · Multimedia tools and applications · doi:10.1007/s11042-017-4521-4 · Cited by 14
Robust RGBD Tracking via Weighted Convolution Operators
Liu, W., Tang, X., & Zhao, C. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2964019 · Cited by 19
Sui, Y., Wang, G., Tang, Y., & Zhang, L. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46484-8_12 · Cited by 15
“[1] utilized incremental subspace learning method to represent the target and locate the target in terms of representation accuracy.”
MethodIncremental CP Tensor Decomposition by Alternating Minimization Method
Zeng, C., & Ng, M. K. (2021) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/20m1319097 · Cited by 16
Fast and reliable incremental dimensionality reduction for streaming data
Neves, T. T. D. A. T., Martins, R. M., Coimbra, D. B., Kucher, K., Kerren, A., & Paulovich, F. V. (2021) · Computers & Graphics · doi:10.1016/j.cag.2021.08.009 · Cited by 15
A Visual Analytics Approach for Hardware System Monitoring with Streaming Functional Data Analysis
Shilpika, Fujiwara, T., Sakamoto, N., Nonaka, J., & Ma, K.-L. (2022) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3165348 · Cited by 17
Investigation of Surrogate Modeling Options with High-Dimensional Input and Output
Guo, Y., Mahadevan, S., Matsumoto, S., Taba, S., & Watanabe, D. (2023) · AIAA Journal · doi:10.2514/1.j061901 · Cited by 20
Roldán-Gómez, J., del Rincón, J. M., Boubeta-Puig, J., & Martínez, J. L. (2023) · Wireless Networks · doi:10.1007/s11276-022-03219-y · Cited by 16
“To implement our proposal we use incremental PCA [31].”
Test Time Adaptation with Regularized Loss for Weakly Supervised Salient Object Detection
Veksler, O. (2023) · 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/cvpr52729.2023.00711 · Cited by 22
Human automatic detection and tracking for outdoor video
Ciarelli, P. M., Salles, E. O. T., & de Oliveira, E. S. (2011) · Integrated Computer-Aided Engineering · doi:10.3233/ica-2011-0383 · Cited by 14
“On the other hand, in [32] it is proposed a tracking method with incremental learning based on principal component analysis for representation of appearance target and particle fi lters to estimate the position of target in each frame.”
InfluentialAn Incremental Tensor Factorization Approach for Web Service Recommendation
Zhang, W., Sun, H., Liu, X., Xiaohui, & Guo (2014) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2014.176 · Cited by 14
“The algorithm in [10] extends the classic incremental SVD by computing the subspace of a dynamic matrix with the mean updating which removes the assumption that the mean of the previous data is equal to the mean of the new data.”
MethodReal-time tracking-with-detection for coping with viewpoint change
Oron, S., Bar-Hillel, A., & Avidan, S. (2015) · Machine Vision and Applications · doi:10.1007/s00138-015-0676-z · Cited by 14
“ple templates and sparse representations to represent target appearance [5,21,33,44].”
BackgroundKhan, Z. H., & Gu, I. Y. (2014) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2014.03.013 · Cited by 15
“Tracker T3 uses subspace-learning-based tracking [3].”
BackgroundMethodInfluentialZoom-SVD: Fast and Memory Efficient Method for Extracting Key Patterns in an Arbitrary Time Range
Jang, J.-G., Choi, D., Jung, J., & Kang, U. (2018) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3269206.3271682 · Cited by 20
“Incremental SVD is used to analyze patterns in time series data [35], and several efficient methods for incremental SVD were proposed [2, 32].”
MethodApplication of gcForest to visual tracking using UAV image sequences
Liu, F., & Anzhe, 杨. Y. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07864-y · Cited by 15
“7), ECO [8], ECO_hc, DSiam [15], ASLA [22], CSK [18], DSST [9], IVT [37], KCF [19], MEEM [46], MUSTER [20], SAMF [28], SRDCF [11], Struck [16], TLD [24].”
BackgroundQuantitative and Qualitative Comparison of 2D and 3D Projection Techniques for High-Dimensional Data
Tian, Z., Zhai, X., van Steenpaal, G., Yu, L., Dimara, E., Espadoto, M., & Telea, A. C. (2021) · Information · doi:10.3390/info12060239 · Cited by 14
“AE [66] nonlinear samples global O(iNw) yes no Keras DM [67] nonlinear samples local O(N3) no yes Tapkee FA [68] linear samples global O(n3) yes yes scikit-learn F-ICA [69] linear samples global O(n3) yes yes scikit-learn G-RP [32] nonlinear samples global O(Nn3) yes no scikit-learn H-LLE [70] nonlinear samples local…”
Keeping Context In Mind: Automating Mobile App Access Control with User Interface Inspection
Fu, H., Zheng, Z., Zhu, S.-C., & Mohapatra, P. (2017) · IEEE Conference on Computer Communications · doi:10.1109/infocom.2019.8737510 · Cited by 13
“Compared to non-updatable classifiers, all these methods can iteratively incorporate new user feedback to update their knowledge and do not assume the availability of a sufficiently large training set before the learning process can start [21].”
MethodRobust visual tracking by metric learning with weighted histogram representations
Wang, J., Wang, H., & Yan, Y. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.11.050 · Cited by 13
“Ross et al. [3] used a low-dimensional subspace model to represent an object, which is robust to illumination and pose changes.”
BackgroundTwo dimensional hashing for visual tracking
Ma, C., & Liu, C. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.01.003 · Cited by 15
“The most representative literature based on this method is IVT [21,22].”
BackgroundMethodVisual object tracking via coefficients constrained exclusive group LASSO
Ma, X., Liu, Q., Ou, W., & Zhou, Q. (2018) · Machine Vision and Applications · doi:10.1007/s00138-018-0930-2 · Cited by 13
“[46] extend this idea by integrating the incremental principal component analysis (IPCA) and particle filtering [26].”
Gao, F., Yang, B., Chen, C., Guan, X., & Tang, Y. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3315955 · Cited by 14
“Hence, inspired by [51], [52], and [53], we adopt the incremental principal component analysis (IPCA) method to determine and amend the principal directions.”
MethodMemory Prompt for Spatiotemporal Transformer Visual Object Tracking
Xu, T., Wu, X., Zhu, X., & Kittler, J. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3353698 · Cited by 16
Xu, C., & Schuster, E. (2012) · Asia-Pacific Journal of Chemical Engineering · doi:10.1002/apj.1679 · Cited by 13
Wang, J., You, X., Wu, W., Guillen, M. R., Cabrerizo, M., Sullivan, J. E., Donner, E. J., Björnson, B., Gaillard, W. D., & Adjouadi, M. (2013) · Human Brain Mapping · doi:10.1002/hbm.22265 · Cited by 13
Online unsupervised feature learning for visual tracking
Liu, F., Shen, C., Reid, I. D., & van den Hengel, A. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.04.008 · Cited by 13
“Examples that fall into this category are incremental subspace learning [10], sparse representation based tracking [1, 8, 11–13], distribution fields representation based tracking [14], etc .”
BackgroundMethodRobust Simultaneous Registration and Segmentation with Sparse Error Reconstruction
Ghosh, P., & Manjunath, B. S. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.103 · Cited by 13
Qin, L., Snoussi, H., & Abdallah, F. (2014) · Sensors · doi:10.3390/s140609380 · Cited by 19
“The first sequence is the “David-outdoor” sequence from [22], where the target undergoes partial occlusion, total occlusion, pose change and non-rigid deformation.”
BackgroundEfficient and Robust Learning for Sustainable and Reacquisition-Enabled Hand Tracking
Aziz, M. A. A., Niu, J., Zhao, X., & Li, X. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2418275 · Cited by 13
Graph Embedding Based Semi-supervised Discriminative Tracker
Gao, J. G., Xing, J., Hu, W., & Zhang, X. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.25 · Cited by 13
“To show the superiority of GSDT over other competing trackers, we perform experiments using SLAM[9], IVT[18], VTD[11], VTS[12], MIL[2] and SSOBT[8] on eight videos.”
MethodInfluentialOnline similarity learning for visual tracking
Yi, S., Jiang, N., Feng, B., Wang, X., & Liu, W. (2016) · Information Sciences · doi:10.1016/j.ins.2016.05.019 · Cited by 14
Object tracking using a convolutional network and a structured output SVM
Li, J., Zhou, X., Chan, S., & Chen, S. (2017) · Computational Visual Media · doi:10.1007/s41095-017-0087-3 · Cited by 15
“Various generative target appearance modeling algorithms have been proposed using sparse representation [13, 14], density estimation [15, 16], and incremental subspace learning [17].”
Global-patch-hybrid template-based arbitrary object tracking with integral channel features
Parate, M. R., Satpute, V. R., & Bhurchandi, K. M. (2017) · Applied Intelligence · doi:10.1007/s10489-017-0974-4 · Cited by 13
“The TLD, PTT, IVT and Frag trackers performed better for smaller scale factors (e.g., 0.8).”
BackgroundMethodInfluentialRobust multi‐feature visual tracking via multi‐task kernel‐based sparse learning
Kang, B., Zhu, W., & Liang, D. (2017) · IET Image Processing · doi:10.1049/iet-ipr.2016.1062 · Cited by 13
Robust Visual Tracking via Smooth Manifold Kernel Sparse Learning
Liu, G. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2844685 · Cited by 13
“In [16], the IVT tracker attempted to learn an adaptive, low-dimensional subspace for appearance modeling.”
MethodConstrained mutual convex cone method for image set based recognition
Sogi, N., Zhu, R., Xue, J., & Fukui, K. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108190 · Cited by 13
Review of recent advances in visual tracking techniques
M, J. R. S., & Augasta, M. G. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10848-6 · Cited by 17
“Ross et al., [53] have described the tracking methods that incrementally learn a low-dimensional subspace representation and efficiently adapting online to changes in the appearance of the target.”
BackgroundUnsupervised Diffeomorphic Surface Registration and Non-linear Modelling
Croquet, B., Christiaens, D., Weinberg, S. M., Bronstein, M. M., Vandermeulen, D., & Claes, P. D. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87202-1_12 · Cited by 18
“As baseline we used iterative optimisation to find the training set SVFs followed by incremental PCA [24] on the velocity fields (incremental PCA has better memory scaling than traditional PCA), this is referred to as tangent-PCA (t-PCA).”
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
Gao, J. G., Lu, Y., Qi, X., Kou, Y., Li, B., Li, L., Yu, S., & Hu, W. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3156977 · Cited by 14
“Online learning has been an important part of visual tracking for about ten years since the classic IVT tracker [37] was first proposed in 2008.”
Background
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.