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 701–800 of 1,001
Sparse Camera Network for Visual Surveillance -- A Comprehensive SurveyPreprint
Song, M., Tao, D., & Maybank, S. J. (2013) · BIROn (Birkbeck, University of London) · doi:10.48550/arxiv.1302.0446 · Cited by 30
“Ross et al. [82] presented an incremental learning method to obtain a low-dimensional subspace representation of the target and efficiently adapt online to changes in the appearance of the target.”
MethodYang, T., Zhang, Y., Tong, X., Zhang, X., & Yu, R. (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.2011.5995417 · Cited by 23
Pixel-Wise Spatial Pyramid-Based Hybrid Tracking
Lu, H., Lu, S., Wang, D., Wang, S., & Leung, H. (2012) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2012.2201794 · Cited by 24
“Similar to [6], our tracking method meets Bayesian inference for visual tracking, which is a Markov model with hidden state variables.”
BackgroundMethodInfluentialRobust Object Tracking via Locality Sensitive Histograms
He, S., Lau, R. W. H., Yang, Q., Wang, J., & Yang, M. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2527300 · Cited by 23
“The incremental subspace visual tracker algorithm [27] represents target objects using a subspace model with incremental learning.”
MethodSelf-citationMultiple face tracking and recognition with identity-specific localized metric learning
Zhou, X., Jin, K., Chen, Q., Xu, M., & Shang, Y. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.09.022 · Cited by 23
Thermal Sensor-Based Multiple Object Tracking for Intelligent Livestock Breeding
Kim, W., Cho, Y. B., & Lee, S.-R. (2017) · IEEE Access · doi:10.1109/access.2017.2775040 · Cited by 25
“To resolve this problem, adaptive models, which evolve during the tracking process by utilizing the target region and its surroundings, have been introduced [21], [22].”
BackgroundAn Integrated Deep Learning Framework for Occluded Pedestrian Tracking
Chen, K., Song, X., Zhai, X., Zhang, B., Hou, B., & Wang, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2900296 · Cited by 26
“Typical generative algorithms include sparse coding [6], locally orderless tracking (LOT) [7], distribution fields for tracking (DFT) [8], and incremental visual tracking (IVT) [9].”
BackgroundDistractor-Aware Visual Tracking by Online Siamese Network
Zha, Y., Wu, M., Qiu, Z., Dong, S., Yang, F., & Zhang, P. (2019) · IEEE Access · doi:10.1109/access.2019.2927211 · Cited by 24
“The following works update the model with stable frames [29], the fixed learning rate [30], sum of template [31] or multi- templates of different lifespans [32].”
BackgroundA Hybrid Method for Tracking of Objects by UAVs
Sarıbaş, H., Uzun, B., Benlıgıray, B., Eker, O., & Çevıkalp, H. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00082 · Cited by 23
“Generative approaches use the location of the object in the previous frame to infer its location in the current frame [27, 33].”
BackgroundJoint Channel Reliability and Correlation Filters Learning for Visual Tracking
Du, F., Liu, P., Zhao, W., & Tang, X. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2909654 · Cited by 24
“Generative methods focus on learning the appearance of the target and searching for the most similar regions, and they are based on subspace learning [27], template matching [28], sparse representation [29], [30], etc.”
BackgroundZhou, Y. C., Yang, Y., Yi, M., Bai, X., Liu, W., & Latecki, L. J. (2014) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001414550015 · Cited by 26
Incremental learning of weighted tensor subspace for visual tracking
Wen, J. A., Li, X., Gao, X., & Tao, D. (2009) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2009.5346874 · Cited by 23
“…the limitation of the fixed appearance model, the Condensation [3], support vector machine [9], kernel-based tracking [10], active appearance mode [8], spatial-appearance model [19], online-updating sparse Bayesian classifier [20], are proposed to deal with the problem of the appearance shift.”
MethodA temporal sparse collaborative appearance model for visual tracking
Zhao, J., Chen, N., & Zhou, Z. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08630-1 · Cited by 24
Online Visual Tracking via Two View Sparse Representation
Wang, D., Lu, H., & Bo, C. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2322389 · Cited by 22
“Similar to [9], we use the affine motion model with six parameters to depict the object’s”
MethodInfluentialA co-training framework for visual tracking with multiple instance learning
Lu, H., Zhou, Q.-H., Wang, D., & Xiang, R. (2011) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2011.5771455 · Cited by 24
“Firstly, we apply IVT model [ 3 ] in the first frame.”
BackgroundMethodResultInfluentialLow Rank Approximation Lower Bounds in Row-Update Streams
Woodruff, D. P. (2014) · neural information processing systems · Cited by 22
Online Metric-Weighted Linear Representations for Robust Visual Tracking
Li, X., Shen, C., Dick, A., Zhang, Z. M., & Zhuang, Y. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2469276 · Cited by 22
A Tracking-Learning-Detection (TLD) method with local binary pattern improved
Jia, C., Wang, Z., Wu, X., Cai, B., Huang, Z., Wang, G., Zhang, T., & Tong, D. (2015) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2015.7419004 · Cited by 22
“The author compared TLD with many other trackers, such as Iterative Visual Tracking (IVT) [12], Online Discriminative Features (ODV) [13], Ensemble Tracking (ET) [14], Multiple Instance Learning (MIL) [15], and Co-trained Generative Discriminative tracking (CoGD) [16], Online Boosting (OB) [17], Online Random Forrest…”
MethodExploiting Spatial Structure from Parts for Adaptive Kernelized Correlation Filter Tracker
Yao, R., Xia, S., Shen, F., Zhou, Y. Z., & Niu, Q. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2545705 · Cited by 22
“We set the vertice of whole object (i.e., part 0) as the root of the tree, then the tree can be obtained by searching for construction a set of connections that would connect all the vertices and have minimum total weight.”
Multi-feature tracking via adaptive weights
Jiang, H., Li, J., Wang, D., & Lu, H. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.03.074 · Cited by 22
Contextual Bag-of-Words for Robust Visual Tracking
Zeng, F., Ji, Y., & Levine, M. D. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2778561 · Cited by 23
Wang, J., Liu, W., Xing, W., & Zhang, S. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.01.005 · Cited by 24
A geometry-driven car-following distance estimation algorithm robust to road slopes
Cao, Z. L., Yang, D., Jiang, K., Xu, S., Wang, S., Zhu, M., & Xiao, Z. (2019) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2019.03.009 · Cited by 25
Adaptive Compressive Tracking via Online Vector Boosting Feature Selection
Liu, Q., Yang, J., Zhang, K., & Wu, Y. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2606512 · Cited by 25
“[18] presented a tracking method that incrementally learns a low-dimensional subspace representation,”
MethodMao, Y., He, Z., Ma, Z., Tang, X., & Wang, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2932733 · Cited by 25
“the largest posterior probability region, as the object region prediction [1][2][3].”
BackgroundGarg, S., & Milford, M. J. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196827 · Cited by 22
“We use Incremental PCA [52], [53], [54] for this purpose to keep the transformation computationally tractable.”
MethodÇinar, U., Çetin-Atalay, R., & Çetin, Y. Y. (2023) · Journal of Imaging · doi:10.3390/jimaging9020025 · Cited by 22
“We have utilized the PCA algorithm presented in [38], an incremental technique to calculate the PCA of large datasets.”
MethodDescription-Discrimination Collaborative Tracking
Chen, D., Yuan, Z., Hua, G., Wu, Y., & Zheng, N. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10590-1_23 · Cited by 22
“The former directly models the object appearance [13,17,11,20], but easily drifts to similar distractors, the latter one distinguishes the target from the background [2,10,14], but is not robust enough as the background may change dramatically.”
BackgroundFeature competition and partial sparse shape modeling for cardiac image sequences segmentation
Qin, X., Tian, Y. T., & Yan, P. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.07.044 · Cited by 22
Learning deep features for multiple object tracking by using a multi-task learning strategy
Wang, L., Pham, N. T., Ng, T.-T., Wang, G., Chan, K. L., & Leman, K. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025168 · Cited by 22
“Model-free object tracking approaches can be divided into two categories: generative [8, 9, 10, 11, 12] and discriminative [13, 14, 15, 16, 17].”
BackgroundPyramid-Based Visual Tracking Using Sparsity Represented Mean Transform
Zhang, Z., & Wong, K. H. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.160 · Cited by 22
“We compare our method against 7 recent state-of-art visual tracking methods: ASLA tracker [11], Frag tracker [1], IVT tracker [16], L1APG tracker [4], MTT tracker [20], STRUCK tracker [9] and TLD tracker [12].”
MethodGame-theoretical occlusion handling for multi-target visual tracking
Zhou, X., Li, Y., & He, B. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.02.013 · Cited by 22
“It extends the single target visual tracking [1] [2] [3] [4] [5] to a situation where the number of targets is not known and is also varying with time.”
BackgroundVisual Tracking Using Sparsity Induced Similarity
Liu, H., & Sun, F. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.421 · Cited by 22
“It has been shown that for tracking scenario, constant subspace assumption is more reasonable than constant brightness or color assumptions[8].”
BackgroundPosterity Logging of Face Imagery for Video Surveillance
Bagdanov, A. D., Bimbo, A., Dini, F., Lisanti, G., & Masi, I. (2012) · IEEE Multimedia · doi:10.1109/mmul.2012.15 · Cited by 28
Adaptive low-rank subspace learning with online optimization for robust visual tracking
Liu, R., Wang, D., Han, Y., Fan, X. N., & Luo, Z. (2017) · Neural Networks · doi:10.1016/j.neunet.2017.02.002 · Cited by 23
Incremental term representation learning for social network analysis
Peng, H. M., Bao, M., Li, J., Bhuiyan, M. Z. A., Liu, Y., He, Y., & Yang, E. (2017) · Future Generation Computer Systems · doi:10.1016/j.future.2017.05.020 · Cited by 22
Visual Tracking via Subspace Learning: A Discriminative Approach
Sui, Y., Tang, Y., Zhang, L., & Wang, G. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-017-1049-z · Cited by 24
“Previous work (Ross et al. 2007; Kwon and Lee 2010; Wang et al. 2013a, b; Zhang et al. 2014a) constructs a subspace where only the previously obtained targets (i.”
BackgroundMethodResultInfluentialHasan, M. K., Sakib, N., Love, R. R., & Ahamed, S. I. (2017) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon.2017.8249004 · Cited by 24
Cui, Z., Cai, Y., Zheng, W., Xu, C., & Yang, J. J. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2886788 · Cited by 24
Eigengalaxies: describing galaxy morphology using principal components in image space
Uzeirbegovic, E., Geach, J. E., & Kaviraj, S. (2020) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staa2651 · Cited by 29
“Other large scale PCA methods include incremental PCA (Ross et al. 2008), which approximates PCA by processing data in batches commensurate with the available random access memory.”
MethodRanking to Learn and Learning to Rank: On the Role of Ranking in Pattern Recognition ApplicationsPreprint
Roffo, G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.05933 · Cited by 41
“Other trackers used for the comparison are the following: CSK [102], CPF [191], Struck [95], CXT [57], VTD [131], VTS [132], LSK [146], KMS [45], Frag [4], MIL [8], CT [271], TLD [119], IVT [219], DFT [229], ASLA [116], L1APG [10], ORIA [262], MTT [272], and LOT [179].”
MethodCollaborative object tracking model with local sparse representation
Xie, C., Tan, J., Chen, P., Zhang, J., & He, L. (2013) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2013.12.012 · Cited by 21
“The tracking videos [13,15,37], MATLAB codes, and data sets can be, respectively found from URLs [30–32].”
BackgroundMethodInfluentialObject tracking based on an online learning network with total error rate minimization
Jang, S.-I., Choi, K., Toh, K., Teoh, A. B. J., & Kim, J. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.07.020 · Cited by 21
“…August 2014 Keywords: Object tracking Particle filter Self-adaptation Random projection network Online learning a b s t r a c t This paper presents a visual object tracking system which is tolerant to external imaging factors such as illumination, scale, rotation, occlusion and background changes.”
BackgroundRobust Orientation and Appearance Adaptation for Wide-Area Large Format Video Object Tracking
Pelapur, R., Palaniappan, K., & Seetharaman, G. S. (2012) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2012.92 · Cited by 21
“…by using target observations [7, 8], fusing multiple sources of sensor information [9, 10], parts-based deformable templates [11, 12], as a learning problem using on-line boosting [13], or online multiple instance boosting [14], while earlier techniques used offline classifier training [15, 16].”
MethodOrderless Tracking through Model-Averaged Posterior Estimation
Hong, S., Kwak, S., & Han, B. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.285 · Cited by 24
“We compare our tracking algorithm with existing techniques in real videos with such challenges and illustrate its superior performance qualitatively and quantitatively.”
MethodMulti-Tracker Partition Fusion
Khalid, O., SanMiguel, J. C., & Cavallaro, A. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2542699 · Cited by 21
“We have implemented six TPF configurations: TPF3 (ST, AFT, and LOT), TPF4 (ST, AFT, LOT, and IVT), TPF5 (ST, AFT, LOT, IVT, and FCT), TPF6 (ST, AFT, LOT, IVT, FCT, and AMS), TPF7 (ST, AFT, LOT, IVT, FCT, AMS, and L1T), and TPF8 (ST, AFT, LOT, IVT, FCT, AMS, L1T, and LSST).”
MethodInfluentialLocality-Constrained Collaborative Model for Robust Visual Tracking
Zhou, T., Lu, Y., & Di, H. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2493498 · Cited by 21
“The IVT and 1 trackers drift first after several rotations (e.g., #83 and #124).”
BackgroundMethodInfluentialEfficient Tracking of Moving Target Based on an Improved Fast Differential Evolution Algorithm
Lin, L., & Zhu, M. (2018) · IEEE Access · doi:10.1109/access.2018.2793298 · Cited by 22
“[21] proposed an effective IVT Tracker, which can update the appearance model of the target dynamically.”
BackgroundDeep Spatial and Temporal Network for Robust Visual Object Tracking
Zhu, T., Xing, J., Wang, Q., Zhang, B., & Fan, J. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2942502 · Cited by 23
“among the sampled candidate regions to the given target, and they are usually built on sparse representation [23], density estimation [24], template matching [25], correlation filter [26], or subspace learning [27], etc.”
BackgroundRobust Structural Low-Rank Tracking
Javed, S., Mahmood, A., Dias, J. M. M., & Werghi, N. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2972102 · Cited by 23
“, proposed incremental low-dimensional subspace based on Principal Component Analysis (PCA) [23].”
MethodInfluentialStructure-aware keypoint tracking for partial occlusion handling
Bouachir, W., & Bilodeau, G.-A. (2014) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2014.6836011 · Cited by 21
“OAB SemiB Frag MIL L1 SAT Sequence P E P E P E P E P E P E David indoor [24] 34 45 46 37 8 73 61 23 41 42 100 10”
MethodInfluentialIntegrating tracking with fine object segmentation
Papoutsakis, K. E., & Argyros, A. (2013) · Image and Vision Computing · doi:10.1016/j.imavis.2013.07.008 · Cited by 21
“The method extends the idea of Hough Forests and couples the generalized Hough transform for object detection with the GrabCut [43] interactive segmentation method.”
MethodInfluentialObject tracking via non-Euclidean geometry: A Grassmann approach
Rowlands, S., Harandi, M. T., Lovell, B. C., & Sanderson, C. (2014) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2014.6836008 · Cited by 22
“On the Tiger 2 sequence, most trackers, including SCM, IVT and FragTrack, fail to track the object from the early frames onwards.”
InfluentialVisual object tracking with online weighted chaotic multiple instance learning
Abdechiri, M., Karim Faez, A., & Amindavar, H. R. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.03.032 · Cited by 21
“The models were introduced by using mixture generative appearance models [10] and kernel-based models [11], shape-driven kernel based models [12], subspace models [13], incremental visual tracking (IVT) [14], visual tracking decomposition (VTD) [15], L1T [16], multitask tracker (MTT) [17] and low rank sparse tracker (…”
MethodRobust Object Tracking by Nonlinear Learning
Ma, B., Hu, H., Shen, J., Zhang, Y., Shao, L., & Porikli, F. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2776124 · Cited by 21
“The performance of our tracker is compared with IVT [44], KCF2 [3], L1APG [13], MDNet [45], MIL [46], MatFlow [48], STC [50], TGPR [39], and Zhang (see [31, A.4]) reported in this benchmark.”
MethodA hybrid tracking framework based on kernel correlation filtering and particle filtering
Zhao, Z., Feng, P., Guo, J., Yuan, C., Wang, T., Liu, F., Zhao, Z., Cui, Z., & Wu, B. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.02.043 · Cited by 22
Comparative Evaluations of Selected Tracking-by-Detection Approaches
Mekonnen, A. A., & Lerasle, F. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2817609 · Cited by 24
“On the subject of appearance model, trackers can usually be classified in either of two groups: generative [36], [37] and discriminative methods [38], [39].”
BackgroundGesID: 3D Gesture Authentication Based on Depth Camera and One-Class Classification
Wang, X., & Tanaka, J. (2018) · Sensors · doi:10.3390/s18103265 · Cited by 24
“Incremental learning [13] is a human-like learning mechanism of machine learning, as it will acquire the new knowledge without forgetting prior knowledge.”
BackgroundXu, N., Xiao, G., Zhang, X., & Bavirisetti, D. P. (2018) · International Conference on Virtual Reality · doi:10.1145/3198910.3198918 · Cited by 21
“Most trackers including CT, IVT, etc., drift away because of continuous variation of target appearance under complex situations.”
BackgroundRobust visual tracking via nonlocal regularized multi-view sparse representation
Kang, B., Zhu, W., Liang, D., & Chen, M. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.11.005 · Cited by 22
“We compare the proposed tracking algorithm with 12 state-of-the-art methods: IVT[14], CT[11], 245”
BackgroundMethodPAC Interaction Inspection Using Real-Time Contact Point Tracking
Shen, Y., Liu, Z., & Zhang, G. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2884039 · Cited by 21
“For the evaluation of the proposed tracking algorithm’s efficiency, a total of nine state-of-art tracking methods and the proposed method were used to track the data sets in various situations: TLD [36], L1APG [37], ORIA [38], CSK [39], IVT [40], LOT [41], KMS [42], SCM [43], and DFT [44].”
MethodRubio, P., Chamoin, L., & Louf, F. (2019) · Comptes Rendus Mécanique · doi:10.1016/j.crme.2019.11.004 · Cited by 21
Visual Object Tracking Via Multi-Stream Deep Similarity Learning Networks
Li, K., Kong, Y., & Fu, Y. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2959249 · Cited by 21
“This strategy plays an important role in tracking methods like TLD [5], IVT [6] etc.”
BackgroundMethodDeep Learning Approaches for Automated Seizure Detection from Scalp Electroencephalograms
Golmohammadi, M., Shah, V., Obeid, I., & Picone, J. (2020) · Springer eBooks · doi:10.1007/978-3-030-36844-9_8 · Cited by 22
Feng, Y., Wang, T., Hu, B., Chen, Y., & Tan, J. (2020) · IEEE Access · doi:10.1109/access.2020.2988118 · Cited by 23
“In this way, it helps to solve the problem caused by dynamic data [41], [42].”
BackgroundRecursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
Gao, J. G., Hu, W., & Lu, Y. (2020) · 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/cvpr42600.2020.00741 · Cited by 25
“Online learning has been an important part of visual tracking for about ten years since the classic IVT tracker [31] was first proposed in 2008.”
BackgroundAdvances in Deep Learning Methods for Visual Tracking: Literature Review and Fundamentals
Zhang, X., Jiang, R.-H., Fan, C., Tong, T.-Y., Wang, T., & Huang, P. (2021) · Machine Intelligence Research · doi:10.1007/s11633-020-1274-8 · Cited by 25
Multi-local-task learning with global regularization for object tracking
Zhang, S., Sui, Y., Zhao, S., Yu, X., & Zhang, L. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.06.005 · Cited by 21
On-Line Multi-view Forests for Tracking
Leistner, C., Godec, M., Saffari, A., & Bischof, H. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15986-2_50 · Cited by 21
“The sequences Sylvester and David are taken from [31] and Face Occlusion 1 is taken from [32], respectively.”
BackgroundNon-negative Subspace Representation Learning Scheme for Correlation Filter Based Tracking
Xu, T., Wu, X., & Kittler, J. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8546146 · Cited by 24
Soft-assigned bag of features for object tracking
Ren, T., Qiu, Z., Liu, Y., Yu, T., & Bei, J. (2014) · Multimedia Systems · doi:10.1007/s00530-014-0384-y · Cited by 20
“The compared tracking methods includes robust fragment-based tracking (Frag) [38], incremental PCA tracking (IVT) [39], multiple instance learning (MIL) [40], visual tracking decomposition (VTD) [41], sparsity-based collaborative model tracking (SCM) [1], tracking learning detection (TLD) [42] and original BoF trackin…”
MethodInfluentialThe Applicability of Spatiotemporal Oriented Energy Features to Region Tracking
Cannons, K. J., & Wildes, R. P. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.233 · Cited by 21
“The overall horizontal structure of the car is captured by the energy in bins 1 and 4.”
BackgroundMulti-Stream Deep Similarity Learning Networks for Visual Tracking
Li, K., Kong, Y., & Fu, Y. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/301 · Cited by 21
“In [Ross et al., 2008], Eigen Images of the target are computed by incremental PCA over the target intensity-value template.”
MethodRobust Visual Tracking with Double Bounding Box Model
Kwon, J., Roh, J., Lee, K. M., & Gool, L. V. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10590-1_25 · Cited by 22
“The proposed method (DBB) was compared with 11 different state-of-the-art tracking methods [27,37]: ABCShift [36], MC [19], IVT [30], MIL [3], BHMC [22], BHT [26], HT [12], LGT [6], VTD [20], VTS [21], and TLD [18], where VTD and VTS are state-of-the-art trackers that use color information and BHMC, BHT, HT, and LGT a…”
MethodWang, Z., Chen, C., & Dong, D. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3160173 · Cited by 22
“Incremental learning has been widely investigated to cope with learning tasks with an ever-changing environment [28], in areas such as supervised learning [29], RL [23], [24], machine vision [30], human–robot interaction [31], and system”
BackgroundExploring Dimensionality Reduction Techniques in Multilingual Transformers
Huertas-García, Á., Martín, A. G., Huertas‐Tato, J., & Camacho, D. (2022) · Cognitive Computation · doi:10.1007/s12559-022-10066-8 · Cited by 33
“To manage this situation, an Incremental PCA approach [70] is applied, which simply fits the PCA in batches being independent of the number of input data samples, but still dependent on the input data features.”
MethodRSPT: Reconstruct Surroundings and Predict Trajectory for Generalizable Active Object Tracking
Zhong, F., Bi, X., Zhang, Y., Zhang, W., & Wang, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i3.25482 · Cited by 39
Venkatraman, A., Wilson, M. A., & Zapiain, D. M. D. O. (2025) · npj Computational Materials · doi:10.1038/s41524-024-01495-0 · Cited by 22
Decentralized Dimensionality Reduction for Distributed Tensor Data Across Sensor Networks
Liang, J., Yu, G., Chen, B., & Zhao, M. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2469100 · Cited by 20
Correlation-based incremental visual tracking
Kim, M. (2011) · Pattern Recognition · doi:10.1016/j.patcog.2011.08.026 · Cited by 20
Wang, H., Wang, X., Zheng, J., Deller, J. R., Peng, H., Zhu, L., Chen, W., Li, X., Liu, R., & Bao, H. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.06.019 · Cited by 20
Face Feature Weighted Fusion Based on Fuzzy Membership Degree for Video Face Recognition
Choi, J. Y., Plataniotis, K. N., & Ro, Y. M. (2012) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2012.2185693 · Cited by 20
“Note that {Im}Mm=1 is assumed to be obtained from a video sequence containing face regions by using face clustering [8] or face tracking techniques [9].”
BackgroundCovariance Tracking via Geometric Particle Filtering
Liu, Y., Li, G., & Shi, Z. (2010) · EURASIP Journal on Advances in Signal Processing · doi:10.1155/2010/583918 · Cited by 21
“Over the last 10 years, numerous approaches [3-10] have been proposed to address this problem.”
BackgroundMethodInfluentialOvertaking vehicle detection using a spatio-temporal CRF
Zhang, X., Jiang, P., & Wang, F. (2014) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2014.6856546 · Cited by 20
Thirteen Hard Cases in Visual Tracking
Chu, D. M., & Smeulders, A. W. M. (2010) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2010.85 · Cited by 20
“Using benchmark datasets [15, 4, 5, 2] with evaluation metrics [11, 6] provides common frameworks to compare trackers.”
Background2D or Not 2D: Bridging the Gap Between Tracking and Structure from Motion
Lebeda, K., Hadfield, S., & Bowden, R. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16817-3_42 · Cited by 20
“[2] extended particle filtering by introducing incremental learning of an object appearance subspace that allowed the model to adapt to changes.”
BackgroundLow-Complexity Multidimensional DCT Approximations for High-Order Tensor Data Decorrelation
Coutinho, V. A., Cintra, R. J., & Bayer, F. M. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2679442 · Cited by 22
“To demonstrate the effectiveness of the sought 3D DCT approximations, we aim at applying them to two major contexts: (i) interframe video coding [19,20,24,25,73,77,91,92,106–108] and (ii) visual tracking [81,103,109].”
MethodImproved object tracking via joint color-LPQ texture histogram based mean shift algorithm
Medouakh, S., Boumehraz, M., & Terki, N. (2017) · Signal Image and Video Processing · doi:10.1007/s11760-017-1196-2 · Cited by 20
“Recently, tracking algorithms can be generally categorized into two main categories: generative tracking [2,6–9] and discriminative tracking [10–15].”
BackgroundDepth Masked Discriminative Correlation Filter
Kart, U., Kämäräinen, J., Matas, J., Fan, L., & Cricri, F. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8546179 · Cited by 25
Using fuzzy least squares support vector machine with metric learning for object tracking
Zhang, S., Lu, W. B., Xing, W., & Zhang, L. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.07.012 · Cited by 20
CNN tracking based on data augmentation
Wang, Y., Wei, X., Tang, X., Shen, H., & Ding, L. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.105594 · Cited by 23
Real-time visual tracking via multi-cue based adaptive particle filter framework
Kumar, A., Walia, G. S., & Sharma, K. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08655-6 · Cited by 20
Tăuţan, A.-M., Rossi, A. C., de Francisco, R., & Ionescu, B. E. (2020) · Biomedizinische Technik/Biomedical Engineering · doi:10.1515/bmt-2020-0139 · Cited by 24
Robust Object Tracking Using Constellation Model with Superpixel
Wang, W., & Nevatia, R. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37431-9_15 · Cited by 20
“An incremental visual tracker(IVT) [8] with an online subspace al-gorithm has been proposed to model target appearance adaptively.”
MethodOnline learning-based robust visual tracking for autonomous landing of Unmanned Aerial Vehicles
Fu, C., Carrio, A., Olivares-Méndez, M. A., & Campoy, P. (2014) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2014.6842309 · Cited by 20
“Ross et al [19] and F.”
Context-Aware Query Selection for Active Learning in Event Recognition
Hasan, M., Paul, S., Mourikis, A. I., & Roy–Chowdhury, A. K. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2878696 · Cited by 27
“The parameters of the Gaussians can be updated using the method in [34], whereas the co-occurrence frequency matrices Fa and Fc can be updated as follows:”
MethodGao, Y., Zhan, Y., & Shen, D. G. (2014) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2013.2291495 · Cited by 19
“While these methods share some similarities with our framework in terms of incremental learning, there are three main differences between previous incremental learning approaches and our method: 1) instead of preserving all previously learned knowledge [32], ILSM selectively discards some learned population characteri…”
Adaptive Local Movement Modelling for Object Tracking
Zhang, B., Li, Z., Perina, A., Bue, A. D., & Murino, V. (2015) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2015.11 · Cited by 19
Initialization-Insensitive Visual Tracking through Voting with Salient Local Features
Yi, K. M., Jeong, H., Heo, B., Chang, H. J., & Choi, J. Y. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.362 · Cited by 19
“Sequences coke, tiger1, and tiger2 are from [4], sylvester is from [18], occFace and woman are from the [1], motocross1 and mtn.”
BackgroundLinear Regression and Adaptive Appearance Models for Fast Simultaneous Modelling and Tracking
Ellis, L., Dowson, N., Matas, J., & Bowden, R. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-010-0364-4 · Cited by 19
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.