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 201–300 of 1,001
Pothole Properties Measurement through Visual 2D Recognition and 3D Reconstruction
Jog, G. M., Koch, C., Golparvar‐Fard, M., & Brilakis, I. (2012) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784412343.0070 · Cited by 127
Thermal Facial Analysis for Deception Detection
Rajoub, B. A., & Zwiggelaar, R. (2014) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2014.2317309 · Cited by 118
“The non-deterministic aspect of the used tracker [34] means it will not necessarily track the same path along the video sequence.”
BackgroundMethodRobust tracking via weakly supervised ranking SVM
Bai, Y., & Tang, M. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247884 · Cited by 104
“[25] incrementally learned a low-dimensional subspace representation of the object frame by frame, efficiently adapting to appearance changes.”
BackgroundMethodOnline Object Tracking with Proposal Selection
Hua, Y., Alahari, K., & Schmid, C. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.354 · Cited by 104
“Object representation has evolved from classical colour histograms [10] to models learned from generative [30, 35, 42] or discriminative [3, 9, 19, 23] approaches.”
BackgroundCannons, K. J. (2008) · Cited by 124
An Experimental Survey on Correlation Filter-based TrackingPreprint
Chen, Z., Hong, Z., & Tao, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.05520 · Cited by 135
Real-Time Probabilistic Covariance Tracking With Efficient Model Update
Wu, Y., Cheng, J., Wang, J., Lu, H., Wang, J., Ling, H., Blasch, E., & Bai, L. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2182521 · Cited by 106
“In [34], Ross et al. proposed a generalized visual tracking framework based on the incremental image-as-vector subspace learning methods with a sample mean update.”
MethodOn-Line Anomaly Detection With High Accuracy
Xie, K., Li, X., Wang, X., Cao, J., Xie, G., Wen, J., Zhang, D., & Qin, Z. (2018) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2018.2819507 · Cited by 106
“Taking Ut+1 for example, instead of directly calculating the eigenvalue decomposition of Y t+1 to find Ut+1, we can apply the incremental SVD algorithms [27], [28] to calculate Ut+1 by operating on Ut and tk/ (t + k) Xt − Xt+1 with Ut obtained from the eigenvalue decomposition of Y t .”
MethodObject Tracking by Oversampling Local Features
Pernici, F., & Bimbo, A. D. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.250 · Cited by 111
Video Event Detection: From Subvolume Localization to Spatiotemporal Path Search
Tran, D., Yuan, J., & Forsyth, D. A. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.137 · Cited by 104
“ILTracking [43] works only at the beginning, then loses the tracks when occlusions occur.”
BackgroundStochastic Gradient Descent and Its Variants in Machine Learning
Netrapalli, P. (2019) · Journal of the Indian Institute of Science · doi:10.1007/s41745-019-0098-4 · Cited by 133
“(cid:31) In several settings either due to the sequential nature of data generation or due to the large ambient dimension d , storing all the samples x 1 , . . . , x n or the full empirical covariance matrix might not be feasible 31, 60, 67 .”
BackgroundCNNTracker: Online discriminative object tracking via deep convolutional neural network
Chen, Y., Yang, X., Zhong, B., Pan, S., Chen, D., & Zhang, H. (2015) · Applied Soft Computing · doi:10.1016/j.asoc.2015.06.048 · Cited by 108
Pan, Z. Y., Liu, S., Sangaiah, A. K., & Muhammad, K. (2018) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2018.06.012 · Cited by 105
Robust visual tracking with structured sparse representation appearance model
Bai, T., & Li, Y. (2011) · Pattern Recognition · doi:10.1016/j.patcog.2011.12.004 · Cited by 104
“Additionally, we also tested the prototype sparse representation based ‘1 tracker [9], IVT tracker [6] and Mean Shift (MS) [37] for”
BackgroundMethodResultInfluentialPatch detection for pavement assessment
Radopoulou, S. C., & Brilakis, I. (2015) · Automation in Construction · doi:10.1016/j.autcon.2015.03.010 · Cited by 101
“After a patch is detected, it is passed to a kernel tracker that tracks it in subsequent video frames [63].”
BackgroundVisual Tracking via Weighted Local Cosine Similarity
Wang, D., Lu, H., & Bo, C. (2014) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2360924 · Cited by 101
“In Table IV, we report the tracking results of trackers based on particle filter (including the MTT [21], APGL1 [16], IVT [6], LSST [34], ASLAS [32], and the proposed WLCS trackers), in which the average values and standard deviations obtained by five trials are illustrated.”
BackgroundMethodInfluentialDiscriminative Object Tracking via Sparse Representation and Online Dictionary Learning
Xie, Y., Zhang, W., Li, C., Lin, S., Qu, Y., & Zhang, Y. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2013.2259230 · Cited by 104
Liu, Y., Jing, X., Nie, J., Gao, H., Liu, J., & Jiang, G. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2863604 · Cited by 125
“For example, the method in [12] builds a subspace model using online PCA.”
MethodCaridakis, G., Karpouzis, K., Drosopoulos, A., & Kollias, S. (2005) · Encyclopedia of Statistical Sciences · doi:10.1002/0471667196.ess1930.pub2 · Cited by 101
Robust visual tracking via co-trained Kernelized correlation filters
Zhang, L., & Suganthan, P. N. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.04.004 · Cited by 101
Robust Structural Sparse Tracking
Zhang, T., Xu, C., & Yang, M. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2797082 · Cited by 106
“(IVT) [29], distribution field tracking (DFT) [63], fragments-based (Frag) [28], multiple experts using entropy minimization (MEEM) [64], and local-global tracking (LGT) [65] schemes.”
InfluentialSelf-citationWang, Q., Fang, J., & Yuan, Y. (2014) · Neurocomputing · doi:10.1016/j.neucom.2013.10.021 · Cited by 105
“Though there are data sets publicly available for tracking research [8,20,21], they only have the traditional RGB channels.”
BackgroundInverse Sparse Tracker With a Locally Weighted Distance Metric
Wang, D., Lu, H., Xiao, Z., & Yang, M. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2427518 · Cited by 98
“This work was supported in part by the China Post-Doctoral Science Foundation under Grant 2014M551085, in part by the Natural Science Foundation of China under Grant 61472060, in part by the Fundamental Research Funds for the Central Universities under Grant DUT13RC(3)105 and Grant DUT14YQ101, in…”
MethodSelf-citationTracking Objects From Satellite Videos: A Velocity Feature Based Correlation Filter
Shao, J., Du, B., Wu, C., & Zhang, L. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2916953 · Cited by 104
“Some representative methods are Meanshift [15], principal component analysis [16], [17], dictionary learning [18], and sparse coding [19].”
MethodSingle and Multiple Object Tracking Using a Multi-Feature Joint Sparse Representation
Hu, W., Li, W., Zhang, X., & Maybank, S. J. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2353628 · Cited by 97
“We compared our multi-object tracking algorithm with the incremental subspace algorithm [4] to show the necessity of occlusion handling.”
InfluentialAdeel, A., Gogate, M., & Hussain, A. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.08.008 · Cited by 96
“Finally, the object tracker [30] is used to track the lip regions across the sequence of frames.”
MethodAdaptive dimensionality reduction for neural network-based online principal component analysis
Migenda, N., Möller, R., & Schenck, W. (2021) · PLoS ONE · doi:10.1371/journal.pone.0248896 · Cited by 109
“In addition, at each data point presentation, a model with a dimensionality increased by one is estimated [8], and a forgetting factor may be used [26, 27] to either keep or discard past observations.”
BackgroundMethodBlurred 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 97
“For seven of these trackers, VTD tracker [13], GKT tracker [26], L1 tracker [19], IVT tracker [25], MIL tracker [1], ICTL tracker [29], OAB tracker [9], we use the publicly available code or the code from the original authors.”
BackgroundMethodInfluentialRobust Estimation of Similarity Transformation for Visual Object Tracking
Li, Y., Zhu, J., Hoi, S. C. H., Song, W., Wang, Z., & Liu, H. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018666 · Cited by 97
Adaptive Region Proposal With Channel Regularization for Robust Object Tracking
Lu, X., Ma, C., Ni, B., & Yang, X. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2944654 · Cited by 96
“DSST [68], SAMF [10], KCF [8] and traditional trackers: Struck [9], MCT [74], IVT [75], OGT [76], MIL [77], CT [78] and NCC [79].”
MethodTowards an Autonomous Vision-Based Unmanned Aerial System against Wildlife Poachers
Olivares-Méndez, M. A., Fu, C., Ludivig, P., Bissyandé, T. F., Kannan, S., Zurad, M., Annaiyan, A., Voos, H., & Campoy, P. (2015) · Sensors · doi:10.3390/s151229861 · Cited by 98
“[67] have done works similar to those in [64], although [66] did not consider the changing of the subspace mean when new data arrive, while the forgetting factor is not integrated in [67], which generates a higher computational cost during the tracking process.”
MethodOnce for All: A Two-Flow Convolutional Neural Network for Visual Tracking
Chen, K., & Tao, W. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2757061 · Cited by 94
Zhang, S., Wang, C., Chan, S. C., Wei, X., & Ho, C. S. (2014) · IEEE Sensors Journal · doi:10.1109/jsen.2014.2382174 · Cited by 102
“For example, subspacebased methods, such as IVT and AST, offer very good performance on Bobot_juice and Bobot_cup datasets, but not in others.”
BackgroundMethodA Biologically Inspired Appearance Model for Robust Visual Tracking
Zhang, S., Lan, X., Yao, H., Zhou, H., Tao, D., & Li, X. (2016) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2586194 · Cited by 94
Montuoro, A., Waldstein, S. M., Gerendas, B. S., Schmidt-Erfurth, U. M., & Bogunović, H. (2017) · Biomedical Optics Express · doi:10.1364/boe.8.001874 · Cited by 97
Literature Survey on Multi-Camera System and Its Application
Olagoke, A. S., Ibrahim, H., & Teoh, S. S. (2020) · IEEE Access · doi:10.1109/access.2020.3024568 · Cited by 107
“…(TLD) [230], resonant tunneling device (RTD) [231], Multiple Instance Learning (MIL) [232], incremental visual tracker (IVT) [233], Beyond semi-supervised (BeSemiT) [234], L1 tracker (L1T) [229], visual tracking decomposition (VTD), semi-supervised tracker (SemiT) [235],…”
BackgroundEuler Principal Component Analysis
Liwicki, S., Tzimiropoulos, G., Zafeiriou, S. P., & Pantić, M. (2012) · International Journal of Computer Vision · doi:10.1007/s11263-012-0558-z · Cited by 96
“We base the update method for the incremental Euler-PCA on standard incremental PCA (Ross et al. 2008; Levy and Lindenbaum 2000), as Euler-PCA is formulated as linear PCA in a non-linear subspace defined by an explicit mapping.”
BackgroundMethodInfluentialVisual 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 96
“In the first two sequences, NMF-Tracker is comparable to best-performed tracker IVT [34] as shown in Table I, but the number of particles employed in our tracker is 80% less than that used in IVT.”
BackgroundMethodInfluentialAhmed, I., Din, S., Jeon, G., Piccialli, F., & Fortino, G. (2021) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2020.1003453 · Cited by 103
“Researchers designed sophisticated feature based methods such as color histograms [47], attributes [48]–[50], traditional handcrafted features including histogram of oriented gradient (HOG) [14], [51], local binary patterns (LBP) [13], Haar-like features [12], [52], scale invariant feature transforms (SFIT) [15], and…”
MethodEnsemble-Based Tracking: Aggregating Crowdsourced Structured Time Series Data
Wang, N., & Yeung, D. (2014) · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · Cited by 104
One-class classifiers with incremental learning and forgetting for data streams with concept drift
Krawczyk, B., & Woźniak, M. (2015) · Soft Computing · doi:10.1007/s00500-014-1492-5 · Cited by 92
“We propose to extend the WOCSVM concept by adding an incremental learning principle to it (Ross et al. 2008).”
MethodInfluentialContext Aware Active Learning of Activity Recognition Models
Hasan, M., & Roy-Chowdhury, A. K. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.516 · Cited by 91
“The parameters of the Gaussians can be updated using the method in [29], wheres the co-occurance frequency matrices can be updated as follows, Fij = Fij + sum([(L = i).”
MethodSupporting Analysis of Dimensionality Reduction Results with Contrastive Learning
Fujiwara, T., Kwon, O.-H., & Ma, K. (2019) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2019.2934251 · Cited by 105
“For PCA, incremental algorithms [55, 60, 73] have been developed to solve this issue.”
MethodA discriminative key pose sequence model for recognizing human interactions
Vahdat, A., Gao, B., Ranjbar, M., & Mori, G. (2011) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2011.6130458 · Cited by 89
“We select a pair of detections with the minimum horizontal distance out of the three highest scoring detections, then run a tracker [12] to find trajectories of two individuals interacting with each other in the subsequent frames.”
MethodTransferring Visual Prior for Online Object Tracking
Wang, Q., Chen, F., Yang, J., Xu, W., & Yang, M. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2190085 · Cited by 94
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
“It is, however, well-known that the set of affine transformations is not a vector space, but rather a curved space possessing the structure of a Lie group (the affine group).”
BackgroundMethodSimilarity Fusion for Visual Tracking
Zhou, Y. C., Bai, X., Liu, W., & Latecki, L. J. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-015-0879-9 · Cited by 88
“We update the sample mean and eigenvectors incrementally following (Ross et al. 2008).”
BackgroundMethodInfluentialScribble Tracker: A Matting-Based Approach for Robust Tracking
Fan, J., Shen, X., & Wu, Y. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.257 · Cited by 88
“In the perspective of model design and update in tracking, early works tended to construct the model by describing the target itself [11], [7], [36], [23], while recently the adoption of context information has become very popular [43], [10], [32], [1], [14], [28], [44], [48], [34], [47].”
BackgroundIncremental Learning of 3D-DCT Compact Representations for Robust Visual Tracking
Li, X., Dick, A., Shen, C., van den Hengel, A., & Wang, H. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.166 · Cited by 88
A Survey on Compressed Sensing in Vehicular Infotainment Systems
Guo, J., Song, B., He, Y., Yu, F. R., & Sookhak, M. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2705027 · Cited by 89
“An effective appearance model is extremely important for the success of a tracking algorithm [66]–[69].”
BackgroundRobust Visual Tracking Using Oblique Random Forests
Zhang, L., Varadarajan, J., Suganthan, P. N., Ahuja, N., & Moulin, P. (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.2017.617 · Cited by 97
“Our tracking algorithm is formulated within a particle filtering framework [39].”
MethodA seam tracking system based on a laser vision sensor
Zou, Y., Chen, X., Gong, G., & Li, J. (2018) · Measurement · doi:10.1016/j.measurement.2018.06.020 · Cited by 88
Probabilistic Tracking of Affine-Invariant Anisotropic Regions
Giannarou, S., Visentini-Scarzanella, M., & Yang, G. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.81 · Cited by 95
“Index Terms—Salient feature extraction, feature point tracking, image-guided navigation Ç”
BackgroundGarcía, G. C., Ruiz, I. L., & Gómez‐Nieto, M. Á. (2016) · Sensors · doi:10.3390/s16111968 · Cited by 102
“In order to analyse and process large volumes of data over several years, various matching-learning techniques have been proposed, such as clustering [214], random sampling [215], data condensation [216], divide and conquer [217], and incremental learning [218].”
BackgroundAn Industrial Internet Application for Real-Time Fault Diagnosis in Industrial Motors
Langarica, S., Ruffelmacher, C., & Núñez, F. (2019) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2019.2913628 · Cited by 91
“…of data has to be managed, called incremental PCA (IPCA), builds a low-rank approximation for the input data using an amount of memory that is independent of the number of input data samples and is extremely efficient when the data set to be decomposed is too large to fit in memory, as shown in [25].”
MethodHigh resolution multispectral video capture with a hybrid camera system
Cao, X., Tong, X., Dai, Q., & Lin, S. C.-F. (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.2011.5995418 · Cited by 84
“Tracking with a state-of-the-art algorithm [16] fails when the object moves over the blue background.”
BackgroundRobust Online Visual Tracking with a Single Convolutional Neural Network
Li, H., Li, Y., & Porikli, F. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16814-2_13 · Cited by 84
“In particular, the temporal sampling plays a more important role and the robust structural Some tracking examples In Figure 7 we show the tracking results of our CNN tracker comparing with three state-of-the-art trackers (SCM, Struck and ASLA) and three classical tracking methods (IVT, MIL, CPF), on 9 video sequences.”
Dynamic Manifold Warping for view invariant action recognition
Gong, D., & Medioni, G. G. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126290 · Cited by 83
“Currently, we use the IVT Tracker [15], an online updated appearance model is used to model the objects dynamic variation.”
MethodVisualization-based nucleate boiling heat flux quantification using machine learning
Hobold, G. M., & da Silva, A. K. (2019) · International Journal of Heat and Mass Transfer · doi:10.1016/j.ijheatmasstransfer.2018.12.170 · Cited by 94
3D textureless object detection and tracking: An edge-based approach
Choi, C., & Christensen, H. I. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386065 · Cited by 83
Highly Nonrigid Object Tracking via Patch-Based Dynamic Appearance Modeling
Kwon, J., & Lee, K. M. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.32 · Cited by 83
Gao, J., Zhang, T., Yang, X., & Xu, C. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2656628 · Cited by 88
“Typically, generative methods include subspace based trackers [7], low-rank and sparse representation based trackers [3], [5], [28], [29], [30], [31], kernel-based trackers [6], covariance based trackers [9], visual tracking decomposition [11], and so on.”
Real-time visual tracking by deep reinforced decision making
Choi, J., Kwon, J., & Lee, K. M. (2018) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2018.05.009 · Cited by 95
“h the target object region from the surrounding background region. Generative approaches for visual tracking often utilize sparse representation [46,45,25] or linear subspace for incremental learning [20,32]. Using these criteria, they try to find the target region where it can be described by the model. The model is c…”
BackgroundExploring the Effects of Blur and Deblurring to Visual Object Tracking
Guo, Q., Feng, W., Gao, R., Liu, Y., & Wang, S. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3045630 · Cited by 86
“…proposed benchmark and categorize them into 4 classes according to representations they used: trackers using intensity-based features, 2 i.e ., IVT [67], CT [70], CSK [68], STC [69] and MBT [10], trackers based on HoG features, i.e ., BT [71], KCF [72], SAMF [73], SRDCF [74], fDSST [75], BACF [33]…”
BackgroundMethodA Robust Tracking System for Low Frame Rate Video
Zhang, X., Hu, W., Xie, N., Bao, H., & Maybank, S. J. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0819-8 · Cited by 81
“the color histogram based representation, 4×4 block color histogram based representation, the subspace based representation (Ross et al. 2008), and the region covariance based representation (Hu et al.”
MethodRobust Visual Tracking via Basis Matching
Zhang, S., Lan, X., Qi, Y., & Yuen, P. C. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2539860 · Cited by 81
“The second group includes some popular trackers including the fragment-based tracker (Frag) [45], the incremental visual tracker (IVT) [42], the”
BackgroundInfluentialA Saliency Prior Context Model for Real-Time Object Tracking
Ma, C., Miao, Z., Zhang, X.-P. S., & Li, M. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2694219 · Cited by 83
“The trackers we use for comparison are: ASLA [14], CT [2], CPF [28], CSK [3], CXT [9], DFT [7], IVT [8], L1APG [6], ORIA [29], SMS [30], TLD [31] and Struck [1], as well as the STC tracker [11].”
MethodInfluentialA Kinect-Based Real-Time Compressive Tracking Prototype System for Amphibious Spherical Robots
Pan, S., Shi, L., & Guo, S. (2015) · Sensors · doi:10.3390/s150408232 · Cited by 79
Is my new tracker really better than yours?
Zajc, L. Č., Kristan, M., & Leonardis, A. (2014) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2014.6836055 · Cited by 81
“This is still a popular measure [30, 3, 1, 23] and it measures the difference between the target’s predicted center from the tracker and the ground-truth center.”
BackgroundMethodDesigning Progressive and Interactive Analytics Processes for High-Dimensional Data Analysis
Turkay, Ç., Kaya, E., Balcisoy, S. S., & Hauser, H. (2016) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2016.2598470 · Cited by 79
“Online PCA: Online PCA algorithms make use of an incremental updating of the singular value decomposition (SVD) of the data matrix [32]1.”
Regional deep learning model for visual tracking
Wu, G., Lu, W., Gao, G., Zhao, C., & Liu, J. (2016) · Neurocomputing · doi:10.1016/j.neucom.2015.10.064 · Cited by 78
Robust Multitask Multiview Tracking in Videos
Mei, X., Hong, Z., Prokhorov, D. V., & Tao, D. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2399233 · Cited by 81
“The trackers appearing in the legend are Struck [22], FBT [71], VTS [64], TLD [33], L1O [43], NCC [72], MIL [21], L1T [3], and IVT [32]. multitask setting.”
BackgroundMethodInfluentialRobust Visual Tracking via Least Soft-Threshold Squares
Wang, D., Lu, H., & Yang, M. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2462012 · Cited by 78
Self-citationRelative Errors for Deterministic Low-Rank Matrix Approximations
Ghashami, M., & Phillips, J. M. (2013) · ACM-SIAM Symposium on Discrete Algorithms (SODA) · doi:10.1137/1.9781611973402.53 · Cited by 77
“We now generalize the relative error type bounds for Misra-Gies (in Section 2.1) to the Frequent Directions algorithm (in Section 2.2).”
MethodInfluentialLearning Compact Binary Codes for Visual Tracking
Li, X., Shen, C., Dick, A. R., & van den Hengel, A. (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.2013.313 · Cited by 83
“These trackers are referred to as ORF (online random forest tracker [25]), CT (compressive tracker [33]), Struck (structured learning tracker [11]), Frag (Fragment-based tracker [1]), MIT (multiple instance tracker [2]), OAB (online AdaBoost tracker [9] that is implemented with the same configuration as OAB1 in [2]),…”
BackgroundMethodDeep Metric Learning for Visual Tracking
Hu, J., Lu, J., & Tan, Y. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2477936 · Cited by 80
“Generative trackers [1]–[3], [5], [7], [10], [29], [30] learn an appearance model to represent the target object and search the best candidate that has the maximal similarity score with the templates.”
BackgroundMethodInfluentialContinual Object Detection: A review of definitions, strategies, and challenges
Menezes, A. G., de Moura, G., Alves, C., & de Carvalho, A. C. P. L. F. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.01.041 · Cited by 104
Visual Tracking of Construction Jobsite Workforce and Equipment with Particle Filtering
Zhu, Z., Ren, X., & Chen, D. (2016) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000573 · Cited by 77
Hu, K., Ye, J., Fan, E., Shen, S., Huang, L., & Pi, J. (2017) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-152381 · Cited by 76
“An inappropriate size of the bounding box is estimated by the IVT tracker, and it also fails soon (as seen in Fig.”
MethodInfluentialSmall Target Tracking in Satellite Videos Using Background Compensation
Wang, Y., Wang, T., Zhang, G., Cheng, Q., & Wu, J. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2978512 · Cited by 81
“Furthermore, incremental learning for robust visual tracking (IVT) involves learning an incremental subspace model, enabling robust tracking when the appearance of the target changes [7].”
BackgroundA Superior Tracking Approach: Building a Strong Tracker through Fusion
Bailer, C., Pagani, A., & Stricker, D. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10584-0_12 · Cited by 84
“505) can already be outperformed with the 15 worst algorithms that all have a performance below the average (best is IVT [24] with success score 0.”
BackgroundMethodInfluentialAudio Assisted Robust Visual Tracking With Adaptive Particle Filtering
Kılıç, V., Barnard, M., Wang, W., & Kittler, J. (2014) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2014.2377515 · Cited by 80
“The method of video-only tracking [4], [5] is generally reliable and accurate when the targets are in the camera field of view, but limitations are introduced when the targets are occluded by other speakers, when they disappear from the camera field of view, or the appearance of the targets or illumination is changed…”
MethodIterative deep learning for image set based face and object recognition
Shah, S. A. A., Bennamoun, M., & Boussaïd, F. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.10.004 · Cited by 75
“For YouTube Celebrities dataset, [46] was used, due to its high performance, to track the face region across every video sequence.”
MethodBounding Multiple Gaussians Uncertainty with Application to Object Tracking
Zhang, B., Perina, A., Li, Z., Murino, V., Liu, J., & Ji, R. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-016-0880-y · Cited by 76
An occlusion-aware particle filter tracker to handle complex and persistent occlusions
Meshgi, K., Maeda, S., Oba, S., Skibbe, H., Li, Y., & Ishii, S. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.05.011 · Cited by 84
Output Constraint Transfer for Kernelized Correlation Filter in Tracking
Zhang, B., Li, Z., Cao, X., Ye, Q., Chen, C., Shen, L., Perina, A., & Jill, R. (2017) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2016.2629509 · Cited by 75
Incremental Spatiotemporal Learning for Online Modeling of Distributed Parameter Systems
Wang, Z., & Li, H. (2018) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2018.2810447 · Cited by 75
“Various methods have been suggested for incremental learning regarding various problems in different areas, including unsupervised learning [14], supervised learning [15], reinforcement learning [16], machine vision [17], evolutionary algorithms [18], and human–robot interaction [19].”
MethodRobust Visual Detection–Learning–Tracking Framework for Autonomous Aerial Refueling of UAVs
Yin, Y., Wang, X., Xu, D., Liu, F., Wang, Y., & Wu, W. (2016) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2015.2509318 · Cited by 77
Occlusion and Motion Reasoning for Long-Term Tracking
Yang, H., Alahari, K., & Schmid, C. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10599-4_12 · Cited by 84
“Examples of object representations include colour histograms [11] as well as appearance representations learned with generative [26,29,33,41] and discriminative [2,10,20,46] models.”
Non-sparse linear representations for visual tracking with online reservoir metric learning
Li, X., Shen, C., Shi, Q., Dick, A., & van den Hengel, A. (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.2012.6247872 · Cited by 75
“These trackers are referred to as FragT (Fragment-based tracker [28]), MILT (multiple instance boosting-based tracker [29]), VTD (visual tracking decomposition [3]), OAB (online AdaBoost [30]), IPCA (incremental PCA [1]), L1T (`1 minimization tracker [2]), and DMLT (discriminative metric learning tracker [15]).”
MethodIncremental Reinforcement Learning With Prioritized Sweeping for Dynamic Environments
Wang, Z., Chen, C., Li, H.-X., Dong, D., & Tarn, T.-J. (2019) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2019.2899365 · Cited by 73
“Well-performed instances include incremental principal component analysis (IPCA) for robust visual tracking [28] and face recognition [29], population-based incremental learning for dynamic optimization problems [30], incremental learning for evolutionary-algorithms-based classification [31], and human–robot interacti…”
BackgroundMethodAdaptive computer vision-based 2D tracking of workers in complex environments
Konstantinou, E., Lasenby, J., & Brilakis, I. (2019) · Automation in Construction · doi:10.1016/j.autcon.2019.01.018 · Cited by 73
Pang, Y., & Ling, H. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.346 · Cited by 77
“Rank aggregation PageRank-like Elo’s rating Glicko’s rating rank name name score name score name score 1 Struck [27] Struck [27] 0.1069 Struck [27] 1.05 ± 0.22 Struck [27] 1.00 ± 0.00 2 MTT [77] MIL [5] 0.0880 ColorPF [55] 3.81 ± 2.10 MIL [5] 2.00 ± 0.00 3 ColorPF [55] ColorPF [55] 0.0822 MIL [5] 4.43 ± 2.02 VTD [37]…”
BackgroundInfluentialWani, A. A. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3025 · Cited by 93
“Balsubramani, Dasgupta & Freund (2013) , Ross et al. (2008) Multilinear PCA ( O ð n Q Extends PCA to tensor data via mode-wise decomposition.”
Adaptive kernel principal component analysis
Ding, M., Tian, Z., & Xu, H. (2009) · Signal Processing · doi:10.1016/j.sigpro.2009.11.001 · Cited by 72
Lip-Reading Driven Deep Learning Approach for Speech Enhancement
Adeel, A., Gogate, M., Hussain, A., & Whitmer, W. M. (2019) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2019.2917039 · Cited by 85
“Finally, the object tracker [39] is used to track lip regions across the sequence of frames.”
MethodLim, K. M., Tan, A. W. C., Lee, C. P., & Tan, S. C. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7263-7 · Cited by 73
“Particle filter is another popular filtering method which has been extensively applied in visual tracking tasks [51, 64, 73, 75].”
MethodVisual Tracking Under Motion Blur
Ma, B., Huang, L., Shen, J., Shao, L., Yang, M., & Porikli, F. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2615812 · Cited by 78
Self-citationOn pedestrian detection and tracking in infrared videos
Wang, J., Chen, D., Chen, H., & Yang, J. (2011) · Pattern Recognition Letters · doi:10.1016/j.patrec.2011.12.011 · Cited by 72
“These experiments include a comparison of our method and three other trackers: two of them are particle filter trackers using single cue of intensity and edge respectively, the third is the IVT (Incremental Visual Tracking) tracker (Ross David et al., 2008) which using intensity cue.”
MethodActive Contour-Based Visual Tracking by Integrating Colors, Shapes, and Motions
Hu, W., Zhou, X. S., Li, W., Luo, W., Zhang, X., & Maybank, S. J. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2236340 · Cited by 78
“The global motion is represented by a six dimensional affine vector m t = ( x t , y t , θ t , s t , α t , β t ) [37] where x t , y t , θ t , s t , α t , β t denote x , y translation, rotation angle, scale, aspect ratio, and skew direction at frame t .”
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.