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 301–400 of 1,001
Robust Visual Tracking Revisited: From Correlation Filter to Template Matching
Liu, F., Gong, C., Huang, X., Zhou, T., Yang, J., & Tao, D. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2813161 · Cited by 72
“Subspace analysis utilizes PCA subspace [12], Riemannian manifold on a tangent space [13], and other linear/nonlinear subspaces to model the relationship of object appearances.”
BackgroundMethodRetracted: Multiscale fast correlation filtering tracking algorithm based on a feature fusion model
Chen, Y., Wang, J., Liu, S., Chen, X., Xiong, J., Xie, J., & Yang, K. (2019) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5533 · Cited by 72
RetractedExtended Lucas-Kanade Tracking
Oron, S., Bar-Hille, A., & Avidan, S. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10602-1_10 · Cited by 77
“Early methods performing template matching [19,21,20,7] later evolved and inspired the use of multiple templates and sparse representations to represent target appearance [30,5,14,24], and for known target classes a more complex use of structure can be made [27].”
MethodAn experimental comparison of online object-tracking algorithms
Wang, Q., Chen, F., Xu, W., & Yang, M. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.895965 · Cited by 72
Self-citationA Deep Learning Approach to Detecting Engagement of Online Learners
Dewan, M. A. A., Lin, F. O., Wen, D., Murshed, M., & Uddin, M. Z. (2018) · IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) · doi:10.1109/smartworld.2018.00318 · Cited by 81
“The forgetting factor and the batch size to update the face models in IVT are set to 0.99 and 5, respectively.”
MethodInfluentialAn Incremental Dimensionality Reduction Method for Visualizing Streaming Multidimensional Data
Fujiwara, T., Chou, J., Shilpika, Xu, P., Ren, L., & Ma, K. (2019) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2019.2934433 · Cited by 69
“For example, methods like incremental PCA [45, 49, 68], incremental Isomap [36], and incremental local linear embedding (LLE) [34] are categorized as such.”
BackgroundMethodInfluentialOnline Spatio-temporal Structural Context Learning for Visual Tracking
Wen, L., Cai, Z., Lei, Z., Yi, D., & Li, S. Z. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33765-9_51 · Cited by 76
“To better represent the target features, some methods [1,2,8,9,10] model the appearance of the target in a generative way.”
MethodAnuragi, A., Sisodia, D. S., & Pachori, R. B. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10711-8 · Cited by 79
Visual Object Tracking Based on Local Steering Kernels and Color Histograms
Zoidi, O., Tefas, A., & Pitas, I. (2012) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2012.2226527 · Cited by 68
“Other approaches employ a hierarchical framework based on bounded irregular pyramids [24] and an incremental eigenbasis learning framework [25].”
MethodA feature covariance matrix with serial particle filter for isolated sign language recognition
Lim, K. M., Tan, A. W. C., & Tan, S. C. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.01.047 · Cited by 68
Online Object Tracking, Learning, and Parsing with And-Or Graphs
Lu, Y., Wu, T., & Zhu, S.-C. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.443 · Cited by 66
“Most popular methods can be divided into four streams: (1) Appearance modeling of object itself as a whole, such as the incremental learning [29], kernel-based [8], particle filtering [17], Figure 2.”
MethodCan We Track Targets From Space? A Hybrid Kernel Correlation Filter Tracker for Satellite Video
Shao, J., Du, B., Wu, C., & Zhang, L. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2922648 · Cited by 71
Online Distance Metric Learning for Object Tracking
Tsagkatakis, G., & Savakis, A. E. (2011) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2011.2133970 · Cited by 66
Robust joint discriminative feature learning for visual tracking
Lan, X., Zhang, S., & Yuen, P. C. (2016) · International Joint Conference on Artificial Intelligence · Cited by 66
Practical galaxy morphology tools from deep supervised representation learning
Walmsley, M., Scaife, A. M. M., Lintott, C. J., Lochner, M., Etsebeth, V., Géron, T., Dickinson, H. J., Fortson, L., Kruk, S., Masters, K. L., et al. (2022) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stac525 · Cited by 111
Towards continuous monitoring of pulse rate in neonatal intensive care unit with a webcam
Mestha, L. K., Kyal, S., Xu, B., Lewis, L., & Kumar, V. (2014) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2014.6944455 · Cited by 66
Classification of the MNIST data set with quantum slow feature analysis
Kerenidis, I., & Luongo, A. (2020) · Physical Review A · doi:10.1103/physreva.101.062327 · Cited by 89
Learning Non-linear Reconstruction Models for Image Set Classification
Hayat, M., Bennamoun, M., & An, S. (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.2014.246 · Cited by 74
“We used [21] to track the face region across every video sequence given the location of the face window in the first frame (provided with the dataset).”
BackgroundMethodKart, U., Kämäräinen, J., & Matas, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11009-3_8 · Cited by 71
Joint Classification and Regression for Visual Tracking with Fully Convolutional Siamese Networks
Cui, Y., Guo, D., Shao, Y., Wang, Z., Shen, C., Zhang, L., & Chen, S. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-021-01559-4 · Cited by 75
“Visual tracking, in particular single object tracking (Ross et al., 2008; Huang et al., 2016; Lukežiˇc et al., 2018; Ma et al., 2018b; Sui et al., 2019), has received considerable attention in the computer vision community due to its wide applications such as intelligent video analysis,…”
BackgroundEnhanced robust spatial feature selection and correlation filter learning for UAV tracking
Wen, J., Chu, H., Lai, Z., Xu, T., & Shen, L. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.01.003 · Cited by 64
Robust Object Tracking with Online Multi-lifespan Dictionary Learning
Xing, J., Gao, J. G., Li, B., Hu, W., & Yan, S. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.88 · Cited by 64
“with six state-of-the-art algorithms, the fragment tracker (Frag) [1], the incremental visual tracking (IVT) algorithm [22], the multi-instance learning (MIL) tracker [4], the visual tracking decomposition (VTD) method [14], the latest 1-tracker ( 1) [5] and its multi-task tracking (MTT) version [27].”
InfluentialLearning to Track Objects from Unlabeled Videos
Zheng, J., Ma, C., Peng, H., & Yang, X. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01329 · Cited by 82
A Contemporary and Comprehensive Survey on Streaming Tensor Decomposition
Thanh, L. T., Abed‐Meraim, K., Trung, N. L., & Hafiane, A. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3230874 · Cited by 77
“in [100] on the mode-n unfolding matrix X ðnÞ t 1⁄4 1⁄2XðnÞ t 1;Y t in (32).”
Multi-Correlation Filters With Triangle-Structure Constraints for Object Tracking
Ruan, W., Chen, J., Wu, Y., Wang, J., Liang, C., Hu, R., & Jiang, J. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2872897 · Cited by 66
“Comparison of state-of-the-art trackers: We conduct comparisons with 15 existing state-of-the-art trackers, namely, (i) convolutional neural network based tracker (CNT [55]); (ii) CF trackers (Staple [24], KCF [26], DSST [27], STC [48], and CSK [49]); (iii) part-based trackers (RPT [37], SCM [16], and IVT [18]); (iv)…”
BackgroundInfluentialTopic Modeling with Contextualized Word Representation ClustersPreprint
Thompson, L., & Mimno, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12626 · Cited by 121
“Figure 3 shows that reduced PCA features produce improved internal coherence and little significant change in external coherence, but reduced SRP features are worse in both metrics, especially for BERT.”
MethodInfluentialUnmanned Aerial Vehicle Video-Based Target Tracking Algorithm Using Sparse Representation
Wan, M., Gu, G., Qian, W., Ren, K., Maldague, X., & Chen, Q. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2930656 · Cited by 62
“IVT L1 PCOM CT MTT WMIL ODFS STC CNT Ours T/s 0.161 0.164 0.012 0.101 0.159 0.100 0.052 0.066 3.030 1.538 Fr/fps 6.21 6.09 83.33 9.90 6.28 10.00 19.23 15.15 0.33 0.65 1) Time Complexity The most time-consuming part of our algorithm is the iterations implemented in Algorithm 1.”
MethodInfluentialRobust Object Tracking Based on Temporal and Spatial Deep Networks
Teng, Z., Xing, J., Wang, Q., Lang, C., Feng, S., & Jin, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.130 · Cited by 64
“Conventional methods design the tracking observation model using different representations, some of the most typical ones include the subspace representation [46], the sparse representation [24, 40, 63], the structured representation [20, 27], and the correlation filter based representation [22, 61].”
BackgroundMethodLi, K., He, F., Yu, H., & Chen, X. (2019) · Frontiers of Computer Science · doi:10.1007/s11704-018-6442-4 · Cited by 63
Lifelong Incremental Reinforcement Learning With Online Bayesian Inference
Wang, Z., Chen, C., & Dong, D. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3055499 · Cited by 75
Wang-Landau Monte Carlo-Based Tracking Methods for Abrupt Motions
Kwon, J., & Lee, K. M. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.161 · Cited by 63
“The method is then extended to obtain good performance in terms of scalability, even on a high-dimensional state space.”
MethodNew perspectives in face correlation research: a tutorial
Wang, Q., Alfalou, A., & Brosseau, C. (2017) · Advances in Optics and Photonics · doi:10.1364/aop.9.000001 · Cited by 63
Discriminative Tracking Using Tensor Pooling
Ma, B., Huang, L., Shen, J., & Shao, L. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2477879 · Cited by 64
“Since the subspace learning [10], [17], [18] methods could capture compact and informative appearance of an object and can be easily extended to online learning algorithms, which are suitable for tracking tasks, in this paper, we propose to address the tracking problem within an online tensor subspace learning framewo…”
BackgroundMethodInfluentialRobust tensor subspace learning for anomaly detection
Li, J., Guan, H., Wen, J. A., & Gao, X. (2011) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-011-0017-0 · Cited by 61
“Illumination changes and camera shaking are regarded as extrinsic appearance variation, whereas intrinsic changes are resulted from object motion and pose variation in the scene [5].”
BackgroundState-Aware Anti-Drift Object Tracking
Han, Y., Deng, C., Zhao, B., & Tao, D. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2905984 · Cited by 66
“Most existing trackers adopt either the generative [12], [13] or the discriminative [14]–[16] approaches.”
BackgroundEngagement Detection in e-Learning Environments using Convolutional Neural Networks
Murshed, M., Dewan, M. A. A., Lin, F. O., & Wen, D. (2019) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc/picom/cbdcom/cyberscitech.2019.00028 · Cited by 64
“A particle filter-based tracker (IVT [40]) is used to follow the motion of faces, where the number of particles, x and y-translations, rotation, scaling, aspect ratio, and skew direction changes are set to 9, 9, 0.”
MethodConstructing Adaptive Complex Cells for Robust Visual Tracking
Chen, D., Yuan, Z., Wu, Y., Zhang, G., & Zheng, N. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.142 · Cited by 66
“They usually build robust object representations using particular features including superpixels [28], integral histograms [1, 8], local descriptors[9], subspace representation [22] and sparse representation [17, 20], etc.”
BackgroundAD-VAT+: An Asymmetric Dueling Mechanism for Learning and Understanding Visual Active Tracking
Zhong, F., Sun, P., Luo, W., Yan, T., & Wang, Y. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2952590 · Cited by 82
“, [1], [2], [3], [4], [5], [6] aims to solely propose a 2D bounding box of the target frame by frame, and does not actively take into consideration the camera-control.”
BackgroundSobral, A. C., Baker, C. G., Bouwmans, T., & Zahzah, E.-H. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11758-4_11 · Cited by 60
“Subsequently various approaches [16, 5, 21, 23, 2] have been proposed to update the SVD more efficiently and supporting new operations.”
BackgroundRepresentation learning with deep extreme learning machines for efficient image set classification
Uzair, M., Faisal Shafait, B., Ghanem, B., & Mian, A. S. (2016) · Neural Computing and Applications · doi:10.1007/s00521-016-2758-x · Cited by 60
“To detect faces in YouTube Celebrities, we track a face in each video sequence with the algorithm in [36] due to its high accuracy.”
MethodEfficient Online Subspace Learning With an Indefinite Kernel for Visual Tracking and Recognition
Liwicki, S., Zafeiriou, S. P., Tzimiropoulos, G., & Pantić, M. (2012) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2012.2208654 · Cited by 64
“We evaluate the performance of all methods on nine very popular video sequences, V i , i = 1 , . . . , 9 (subsets of which are used in [6], [34], and [45]–[47]).”
BackgroundMethodInfluentialFormal Models of the Network Co-occurrence Underlying Mental Operations
Bzdok, D., Varoquaux, G. P., Grisel, O., Eickenberg, M., Poupon, C., & Thirion, B. (2016) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1004994 · Cited by 62
“An implementation of incremental PCA [84] performed batch-by-batch decomposition for low-rank approximation with efficient memory usage (batch size = 100 activity maps, whitening).”
MethodDeep learning to frame objects for visual target tracking
Pang, S., del Coz, J. J., Yu, Z., Luaces, O., & Díez, J. (2017) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2017.08.010 · Cited by 64
Exploratory analysis of hyperspectral FTIR data obtained from environmental microplastics samples
Wander, L., Vianello, A., Vollertsen, J., Westad, F., Braun, U., & Paul, A. (2020) · Analytical Methods · doi:10.1039/c9ay02483b · Cited by 70
Dual Linear Regression Based Classification for Face Cluster Recognition
Chen, L. (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.2014.342 · Cited by 59
“Tracking) [18] tool to track and extract faces frame by frame using the information of the cropped face in the first frame available via the dataset website 5.”
MethodRobust Visual Tracking Based on Convolutional Features with Illumination and Occlusion Handing
Li, K., He, F., & Yu, H. (2018) · Journal of Computer Science and Technology · doi:10.1007/s11390-017-1764-5 · Cited by 60
“IVT[14] incrementally learns a low dimensional PCA subspace representation, which can effectively model smooth pose variation.”
BackgroundInfluentialPrivacy-Preserving Distributed IDS Using Incremental Learning for IoT Health Systems
Tabassum, A., Erbad, A., Mohamed, A. M. S., & Guizani, M. (2021) · IEEE Access · doi:10.1109/access.2021.3051530 · Cited by 70
“Recently researchers have shown much interest in incremental learning algorithms [22], also referred to as Transfer Learning [23], Online Learning [24], and Federated Learning [25] to adapt to the complex real environments.”
BackgroundVisual Tracking via Adaptive Tracker Selection with Multiple Features
Yoon, J. H., Kim, D. Y., & Yoon, K. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33765-9_3 · Cited by 67
“Tracker references : We update each tracker reference by using the incremental PCA [3].”
BackgroundMethodInfluentialDynamic subspace-based coordinated multicamera tracking
Ayazoğlu, M., Li, B., Dicle, C., Sznaier, M., & Camps, O. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126531 · Cited by 59
“Both trackers estimate the Fundamental matrix from 8 point correspondences (selected by hand), perform background subtraction using a mixture of Gaussians model [25] as a preprocessing step and use the adaptive template matching particle filter tracker IVT [24] to locate the target in the 2D images.”
MethodFace Recognition in Low Quality Images: A SurveyPreprint
Li, P., Prieto, L., Mery, D., & Flynn, P. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.11519 · Cited by 78
“the GLF feature for tracking, faces from 20 ×20 to 200 ×200 could be successfully tracked on their videos captured outdoors. They also evaluated their tracker on Dudek previously used by Ross et al. [94] and the Boston University head tracking database [57]. In 2013, Khan et al. [53] and Mostafa et al. [75] conducted…”
MethodCascaded Continuous Regression for Real-Time Incremental Face Tracking
Sánchez, E., Martínez, B., Tzimiropoulos, G., & Valstar, M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46484-8_39 · Cited by 64
Research on Cattle Behavior Recognition and Multi-Object Tracking Algorithm Based on YOLO-BoT
Tong, L., Fang, J., Wang, X., & Zhao, Y. (2024) · Animals · doi:10.3390/ani14202993 · Cited by 59
Xiao, Z., Lu, H., & Wang, D. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2291355 · Cited by 58
“Object tracking via online subspace learning [20]–[24] has attracted much attention in recent years.”
BackgroundMethodInfluentialAn ensemble of deep neural networks for object tracking
Zhou, X., Xie, L., Zhang, P., & Zhang, Y. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025169 · Cited by 65
“8(8.6) 9.3(40.5) 17.0(115.0) 17.8(18.9) 27.5(86.0) 34.9(88.7) 42.7(10.5) 0.6(363.8) DLT [23] 84.1(7.0) 59.8(28.4) 21.1(144.1) 95.2(3.0) 100(2.6) 33.3(104.8) 82.0(6.6) 2.3(388.1) IVT [5] 597-OPR 82-OPR 118-OCC SUCCESS 199-SV 118-OPR SUCCESS 5-DEF MIL [3] 717-IV 70-FM 119-OCC 98-OPR 199-SV 100-DEF SUCCESS 5-DEF MTT [31]…”
InfluentialA Geometric Particle Filter for Template-Based Visual Tracking
Kwon, J., Lee, H. S., Park, F. C., & Lee, K. M. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.170 · Cited by 58
“However, previous template-based visual tracking algorithms employing particle filtering [64], [32], [46], [31], [33], [4] are all confined to affine motion tracking , i.e. , template-based visual tracking with affine transformations.”
MethodPersistent Aerial Tracking system for UAVs
Mueller, M. F., Sharma, G., Smith, N., & Ghanem, B. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759253 · Cited by 63
“The active UAV continues tracking until the new UAV is positioned correctly to ensure that the most current template is transfered and the target is in view even if it has moved during the handover operation.”
BackgroundMethodMODE-TASK: large-scale protein motion tools
Ross, C. J., Nizami, B., Glenister, M., Amamuddy, O. S., Atılgan, A. R., Atılgan, C., & Bishop, Ö. T. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty427 · Cited by 58
Xu, T., Feng, Z., Wu, X., & Kittler, J. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2945068 · Cited by 64
“The visual tracking community, following the development of mathematical theories and modelling techniques in recent decades, has reported an impressive spectrum of achievements, ranging from template matching [1], statistical learning theory [2], particle filter [3], subspace learning [4], discriminative correlation…”
BackgroundMethodLiu, Z., Zhang, W., & Zhao, P. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.01.045 · Cited by 59
Robust infrared vehicle tracking across target pose change using L1 regularization
Ling, H., Bai, L., Blasch, E., & Mei, X. (2010) · International Conference on Information Fusion (FUSION) · doi:10.1109/icif.2010.5711902 · Cited by 74
Biometric recognition in surveillance scenarios: a survey
Neves, J. C., Narducci, F., Barra, S., & Proença, H. P. M. C. (2016) · Artificial Intelligence Review · doi:10.1007/s10462-016-9474-x · Cited by 62
“In general, particle filters or sequential Monte Carlo methods are preferred in Bayesian tracking (Ross et al. 2008; Wu et al. 2011a; Zhang et al. 2012; Kwon and Lee 2010; Xiao et al. 2013), since they can handle any kind of noise and do not require the motion model to be linear.”
Robust Visual Tracking via Multiple Kernel Boosting With Affinity Constraints
Yang, F., Lu, H., & Yang, M. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2276145 · Cited by 58
Self-citationGeneralized Pooling for Robust Object Tracking
Ma, B., Hu, H., Shen, J., Liu, Y., & Shao, L. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2588329 · Cited by 58
“Ross et al. [31] and Ho et al. [32] flattened the intensity of the target region into a 1http://github.com/shenjianbing/poolingtrack high-dimensional vector directly.”
BackgroundAdaptive appearance model tracking for still-to-video face recognition
Dewan, M. A. A., Granger, É., Marcialis, G. L., Sabourin, R., & Roli, F. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.08.002 · Cited by 56
“The update and management of template galleries with faces captured during operations may improve intra-class variability of gallery-face-models and the FR performance, though these adaptive methods may corrupt the gallery-face-model if incorrectly updated [7,9].”
BackgroundMATRIOSKA: A Multi-level Approach to Fast Tracking by Learning
Maresca, M. E., & Petrosino, A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41184-7_43 · Cited by 59
Real-time and robust object tracking in video via low-rank coherency analysis in feature space
Chen, C., Li, S., Qin, H., & Hao, A. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.01.025 · Cited by 56
“And then, they [18] further proposed an occlusion-handling method by coupling additional noise templates (which is local) with a batch of PCA based individual phototypes (which is global) [15].”
MethodAcquisition of High Spatial and Spectral Resolution Video with a Hybrid Camera System
Ma, C., Cao, X., Tong, X., Dai, Q., & Lin, S. C.-F. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0690-4 · Cited by 56
“Tracking with a state-of-the-art algorithm (Ross et al. 2008) fails when the object moves over the blue background.”
BackgroundTracking by Sampling and IntegratingMultiple Trackers
Kwon, J., & Lee, K. M. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.213 · Cited by 59
“VISUAL object tracking is a well-known problem in thecomputer vision community.”
BackgroundMethodRobust Visual Tracking via Exclusive Context Modeling
Zhang, T., Ghanem, B., Liu, S., Xu, C., & Ahuja, N. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2393307 · Cited by 55
“In the L1 tracker [1], a tracking candidate is represented as a sparse linear combination of object templates and trivial templates.”
MethodMulti-Feature Fusion in Particle Filter Framework for Visual Tracking
Bhat, P. G., Subudhi, B. N., Veerakumar, T., Laxmi, V., & Gaur, M. S. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2954331 · Cited by 56
“Out of the 30 algorithms considered for comparison, the particle filter context is used for tracking by six algorithms: IVT, SSIR, SSIRMSR, PFOH, L1 and Co-T.”
BackgroundInfluentialTracking Using Multilevel Quantizations
Hong, Z., Wang, C., Mei, X., Prokhorov, D. V., & Tao, D. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10599-4_11 · Cited by 59
“Many trackers are built to exploit high-level visual information using holistic appearance models [5,19,41,46].”
BackgroundMethodInfluentialWang, D., & Lu, H. (2012) · Signal Processing · doi:10.1016/j.sigpro.2012.07.015 · Cited by 55
“5(a) and (b), our IOPNMF tracker achieves similar performance to the IPCA tracker (IVT [33], a state-of-the-art method).”
BackgroundMethodResultInfluentialYe, M., Giannarou, S., Meining, A. G., & Yang, G. (2015) · Medical Image Analysis · doi:10.1016/j.media.2015.10.003 · Cited by 70
“We can also observe that most approaches (IVT, OAB, MIL, Struck, etc.) presented very low F-measures for all of the GI sequences.”
BackgroundMethodInfluentialA novel visual tracking method using bat algorithm
Gao, M., Shen, J., Yin, L., Liu, W., Zou, G., Li, H., & Fu, G. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.11.072 · Cited by 57
Visual object tracking—classical and contemporary approaches
Ali, A., Jalil, A., Niu, J., Zhao, X., Rathore, S., Ahmed, J., & Iftikhar, M. A. (2015) · Frontiers of Computer Science · doi:10.1007/s11704-015-4246-3 · Cited by 67
“il1) 2 Incremental visual tracker [207] √ √ √ cs.”
Metric Learning Based Structural Appearance Model for Robust Visual Tracking
Wu, Y., Ma, B., Yang, M., Zhang, J., & Jia, Y. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2291283 · Cited by 53
“The CT, Frag, IVT, DFML, and 1 trackers get lost in tracking the object after drastic illumination changes, whereas VTD and SCM algorithms perform slightly better.”
MethodInfluentialSelf-citationSparse Coding From a Bayesian Perspective
Lu, X., Wang, Y., & Yuan, Y. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2245914 · Cited by 53
“Tracking results of the sequence birch_seq_mb by our method, the 1 penalty based method [13], the IVT method [38], and the OMIST method [39], respectively (from top to down).”
MethodOnboard Robust Visual Tracking for UAVs Using a Reliable Global-Local Object Model
Fu, C., Duan, R., Kırcalı, D., & Kayacan, E. (2016) · Sensors · doi:10.3390/s16091406 · Cited by 54
“Visual tracking algorithms based on incremental subspace learning [31] and hierarchical methods are developed in [28,32] to track a 2D or 3D object for UAVs.”
MethodPerformance of an insect-inspired target tracker in natural conditions
Bagheri, Z. M., Wiederman, S. D., Cazzolato, B. S., Grainger, S., & O’Carroll, D. C. (2017) · Bioinspiration & Biomimetics · doi:10.1088/1748-3190/aa5b48 · Cited by 54
Correlation Filter Learning Toward Peak Strength for Visual Tracking
Sui, Y., Wang, G., & Zhang, L. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2690860 · Cited by 58
“[16] introduced the incremental principal component analysis (PCA)”
BackgroundMethodZhu, X., Wu, X., Xu, T., Feng, Z., & Kittler, J. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2979480 · Cited by 60
“Early work included Kalman filtering [37], mean-shift [38] and incremental learning [39] methods.”
MethodTrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the WildPreprint
Müller, M., Bibi, A., Giancola, S., Alsubaihi, S., & Ghanem, B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.10794 · Cited by 160
“Last, we include some baseline trackers such as TLD [51], Struck [22], ASLA [19] and IVT [20] for reference.”
BackgroundMethodPoint-to-Set Distance Metric Learning on Deep Representations for Visual Tracking
Zhang, S., Qi, Y., Jiang, F., Lan, X., Yuen, P. C., & Zhou, H. (2017) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2766093 · Cited by 54
Structure-Aware Local Sparse Coding for Visual Tracking
Qi, Y., Qin, L., Zhang, J., Zhang, S., Huang, Q., & Yang, M. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2797482 · Cited by 52
Self-citationMian, A. S., Hu, Y., Hartley, R. I., & Owens, R. A. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2282996 · Cited by 52
“Our goal is to adaptively learn a better distance metric for each query set during matching such that the metric can better model the characteristics of the query set in the local context.”
BackgroundBIT: Biologically Inspired Tracker
Cai, B., Xu, X., Xing, X., Jia, K., Miao, J., & Tao, D. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2520358 · Cited by 56
“On the other hand, automated feature extraction is able to learn self-taught features [8] from input images, which can be either unsupervised such as principal component analysis (PCA) [9], or supervised such as linear discriminant analysis (LDA) [10].”
BackgroundMethodInfluentialGündoğdu, E., Koç, A., Solmaz, B., Hammoud, R. I., & Alatan, A. A. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.43 · Cited by 56
“Incremental visual tracking (IVT) [33], mean shift tracking [6] and visual tracking decomposition [24] are some prominent examples of robust and generative tracking methods.”
BackgroundP2T: Part-to-Target Tracking via Deep Regression Learning
Gao, J., Zhang, T., Yang, X., & Xu, C. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2813166 · Cited by 54
“In general, most current trackers adopt global appearance models to determine target location [4], [6], [7], [9], [10], [14], which may not perform well under significant appearance changes such as partial occlusion and deformation.”
MethodLi, Z., Zhang, J., Zhang, K., & Li, Z. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2839916 · Cited by 52
“Moreover, the PCA basis matrix U is incrementally updated by the incremental subspace learning method [19].”
BackgroundMethodInfluentialDynamically Modulated Mask Sparse Tracking
Chen, Z., You, X., Zhong, B., Li, J., & Tao, D. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2577718 · Cited by 55
“In specific, typical global information representations include vector-based raw pixel representation which used in IVT [6], optical flow representation which used in PROST [7], haar feature-based representation like MIL [8], CT [9], and Struck [10].”
MethodGündoğdu, E., Özkan, H., Demir, H. S., Ergezer, H., Akagündüz, E., & Pakin, S. K. (2015) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2015.7301290 · Cited by 59
“OTCBVS - Precision Comparison IR Visible TBOOST 10.88 5.31 STRUCK 8.45 3.77 L1APG 8.26 4.94 FCT 6.92 3.87 MOSSE 6.14 4.67 IVT 5.81 4.64 MIL 5.00 4.29 ODFS 4.19 4.20 CRC 4.32 5.68 ate a precise ground truth by annotating a bounding box for each person in the sequences.”
BackgroundMethodInfluentialOptimal spatio-temporal path discovery for video event detection
Tran, D., & Yuan, J. (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.2011.5995416 · Cited by 55
“[17] Incremental Learning Tracking* 30.”
BackgroundMethodInfluentialA new system for driver drowsiness and distraction detection
Sabet, M., Zoroofi, R. A., Sadeghniiat‐Haghighi, K., & Sabbaghian, M. (2012) · Iranian Conference on Electrical Engineering · doi:10.1109/iraniancee.2012.6292547 · Cited by 51
A Joint Framework for Athlete Tracking and Action Recognition in Sports Videos
Kong, L., Huang, D., Qin, J., & Wang, Y. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2893318 · Cited by 55
“boosting [26], and incremental subspace update [27].”
Machine learning based novelty detection using modal analysis
Ozdagli, A. I., & Koutsoukos, X. (2019) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12511 · Cited by 58
“Either, incremental PCA (Ross, Lim, Lin, & Yang, 2008), or AE should be used for a system with large sensor arrays.”
MethodTracking Using Motion Patterns for Very Crowded Scenes
Zhao, X., Gong, D., & Medioni, G. G. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33709-3_23 · Cited by 56
“Our single target tracking results are compared with IVT Tracker [6], P-N Tracker [7] and CTM [1].”
MethodResultSingle object tracking via robust combination of particle filter and sparse representation
Yi, S., He, Z., You, X., & Cheung, Y. (2014) · Signal Processing · doi:10.1016/j.sigpro.2014.09.020 · Cited by 53
“, the incremental learning visual tracking (IVT) method [8], the l1 tracker [12], the multiple instance learning (MIL) tracker [2], the visual tracking decomposition (VTD) method [6], the P-N learning (PN) tracker [3] and ASLSA.”
BackgroundMethodRobust MIL-Based Feature Template Learning for Object Tracking
Lan, X., Yuen, P. C., & Chellappa, R. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11220 · Cited by 50
“With limited amount of labeled tracking samples available in the first frame, additional examples of the tracked targets which are collected by the tracker itself should be utilized for model updating (e.g. (Ross et al. 2008), (Mei and Ling 2011), (Babenko, Yang, and Belongie 2011)).”
MethodInfluentialLi, K., He, F., Yu, H., & Chen, X. (2017) · Applied mathematics/Applied Mathematics. A Journal of Chinese Universities/Gao-xiao yingyong shuxue xuebao · doi:10.1007/s11766-017-3466-8 · Cited by 50
“IVT[43] assumes that the target is generated from a PCA subspace which is updated using SKL algorithm[26].”
MethodEfficient Visual Object Tracking with Online Nearest Neighbor Classifier
Gu, S., Zheng, Y., & Tomasi, C. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19315-6_21 · Cited by 56
“We test our new NN-based tracker on 8 video sequences from multiple data sets [30, 31, 5, 20, 21] and compare it to the state-of-art tracking methods: AdaBoost [18], Online Random Forests [26], Fragments [5], Multiple Instance Learning [20] and PROST [21].”
Method
Metadata
- Authors
- Ross, D. A., Lim, J., Lin, R.-S., & Yang, M.-H.
- Affiliations
- University of Toronto (CA)
- Honda Research Institute, USA (US)
- Motorola (United States) (US)
- Corresponding author
- Ross, David A.
- Venue
- International Journal of Computer Vision
- Published
- 2007-08-17
- Volume
- 77
- Issue
- 1-3
- Pages
- 125-141
- ISSN
- 0920-5691 (ISSN-L)
- 1573-1405
- OpenAlex
- W2139047213
- Cited by
- 3,061
- References
- 43
- Citations by year
- 2026: 25 · 2025: 47 · 2024: 53 · 2023: 51 · 2022: 83 · 2021: 126 · 2020: 148 · 2019: 244 · 2018: 279 · 2017: 324 · 2016: 340 · 2015: 359 · 2014: 331 · 2013: 214 · 2012: 161
- FWCI
- 66.90
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- International Journal of Computer Vision (publishedVersion)
- Funders
- Honda Research Institute, USA
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- visual object tracking, incremental learning, principal component analysis, appearance modeling, forgetting factor, illumination variation, robust tracking
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.