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 501–600 of 1,001
Robust visual tracking using autoregressive hidden Markov Model
Park, D. W., Kwon, J., & Lee, K. M. (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.2012.6247898 · Cited by 42
“[16] utilize the incremental learning strategy to adaptively update subspaces that compose the target appearance.”
BackgroundMethodAdaptive NormalHedge for robust visual tracking
Zhang, S., Zhou, H., Yao, H., Zhang, Y., Wang, K., & Zhang, J. (2014) · Signal Processing · doi:10.1016/j.sigpro.2014.08.027 · Cited by 38
Robust Multi-Speaker Tracking via Dictionary Learning and Identity Modeling
Barnard, M., Koniusz, P., Wang, W., Kittler, J., Naqvi, S. M., & Chambers, J. A. (2014) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2014.2301977 · Cited by 37
Hierarchical Kalman-particle filter with adaptation to motion changes for object tracking
Yin, S., Na, J. H., Choi, J. Y., & Oh, S. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.02.010 · Cited by 41
“[9,10] proposed an incremental subspace learning method and Yang et al.”
MethodLie to Me: Deceit detection via online behavioral learning
Bhaskaran, N., Nwogu, I., Frank, M. G., & Govindaraju, V. (2011) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2011.5771407 · Cited by 38
“We implemented an extension of an incremental learning tracker [16], a probabilistic tracker based on incremental principal component analysis.”
MethodJeong, J., Yoon, T. S., & Park, J. B. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.02.043 · Cited by 40
Learning Deep Match Kernels for Image-Set Classification
Sun, H., Zhen, X., Zheng, Y., Yang, G., Yin, Y., & Li, S. (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.2017.661 · Cited by 41
“By following settings in previous work [25], we adopt the algorithm in [41] to detect the faces for each clip and resize to patches of the size 50× 50.”
MethodYu, L., Yang, T., & Chan, A. B. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2845371 · Cited by 38
“For more complex models, one solution is to use a particle filter [5], [6], [7], [8], [9], [10], [11], [12], [13], [14], [15], where the posterior is approximated as a set of weighted particles pðxtjy1:tÞ 1⁄4 P m vmdðxt x̂mÞ, where ðvm; x̂mÞ is the mth particle.”
BackgroundMethodRealtime tracking and grasping of a moving object from range video
Husain, F., Colome, A., Dellen, B., Alenya, G., & Torras, C. (2014) · 2014 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2014.6907234 · Cited by 38
“Previously, this assumption has been made in [22], [23], [24], [25] for color/grayscale images.”
BackgroundMethodInfluentialLinearization to Nonlinear Learning for Visual Tracking
Ma, B., Hu, H., Shen, J., Zhang, Y., & Porikli, F. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.500 · Cited by 36
“ASLA DSSM Struck IVT L1APG LOT SCM TLD VTD CSK ODDL WDL Ours DP 0.530 0.533 0.654 0.499 0.479 0.519 0.648 0.601 0.574 0.541 0.561 0.689 0.737 OP 0.433 0.414 0.472 0.357 0.377 0.366 0.498 0.434 0.415 0.396 0.410 0.493 0.508 Figure 4.”
MethodInfluentialRobust Object Tracking Based on Principal Component Analysis and Local Sparse Representation
Liu, H., Shutao Li, A., & Fang, L. (2015) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2015.2437636 · Cited by 36
“Since this method represents the object as a holistic target, the IVT method cannot well handle the partial occlusions.”
MethodInfluentialNam, H., Hong, S., & Han, B. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10602-1_8 · Cited by 38
“Many tracking algorithms have been investigating this problem and some promising solutions have been proposed such as template update [22,23,6], sparse representation [3,4,5], incremental subspace learning [9], multi-task learning [10], multiple instance learning [13], P-N learning [12], and”
BackgroundMethodReal-time multi-scale tracking based on compressive sensing
Yun-xia, W., Jia, N., & Jiping, S. (2014) · The Visual Computer · doi:10.1007/s00371-014-0942-5 · Cited by 37
“The IVT method [7] uses an online subspace model to adapt to appearance changes.”
MethodFast Learning of Spatially Regularized and Content Aware Correlation Filter for Visual Tracking
Han, R., Feng, W., & Wang, S. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2998978 · Cited by 38
“Many machine learning methods, e.g., support vector machines (SVM) [6], [7], subspace learning [8], online multi-instance boosting [9], sparse and compressive reconstruction [5], [10], correlation filter (CF) [11], [12], and convolutional neural network (CNN) [13], [14], have been developed to this…”
BackgroundKalman Filter for Spatial-Temporal Regularized Correlation Filters
Feng, S., Hu, K., Fan, E., Zhao, L., & Wu, C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3060164 · Cited by 37
“…framework, we compare our framework with 30 state-of-the-art trackers from the literature: CPF [37], KMS [38], SMS [39], Frag [40], OAB [41], IVT [42], SBT [43], MIL [44], BSBT [45], TLD [46], VTD [47], CXT [48], LSK [49], Struck [50], VTS [51], ASLA [52], DFT [53], L1APG [54], LOT [55], MTT…”
MethodVisual Tracking With Spatio-Temporal Dempster–Shafer Information Fusion
Li, X., Dick, A. R., Shen, C., Zhang, Z. M., van den Hengel, A., & Wang, H. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2253478 · Cited by 37
An RGB–D based image set classification for robust face recognition from Kinect data
Hayat, M., Bennamoun, M., & El-Sallam, A. A. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.07.027 · Cited by 35
“Figure 3: Few pre-processed RGB images using (a) our method, and (b) [35, 28].”
BackgroundMethodInfluentialSimultaneous Speech Detection With Spatial Features for Speaker Diarization
Zelenák, M., Segura, C., Luque, J., & Hernando, J. (2012) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2160167 · Cited by 35
“PCA was used for similar issues in diarization in [25].”
MethodInfluentialZhang, L., Lu, H., Du, D., & Liu, L. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2509244 · Cited by 36
“Large numbers of effective tracking approaches have been proposed in the literature.”
BackgroundMethodRobust Visual Tracking With Multitask Joint Dictionary Learning
Fan, H., & Xiang, J. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2515738 · Cited by 35
“In [4], the incremental visual tracking introduces an online approach for efficiently learning and updating a low-dimensional principal component analysis (PCA) subspace representation for the object.”
BackgroundMethodYao, R., Xia, S., Zhang, Z., & Zhang, Y. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2631727 · Cited by 38
“5 are the following: KCF [8], Struck [5], PT [7], STC [33], SPOT [26], IVT [3], MIL [4], OAB [11], Frag [23], VTD [56], ACT [32], TLD [6], L1APG [13], and ASLA [57].”
BackgroundMethodInfluentialVisual object tracking by correlation filters and online learning
Zhang, X., Xia, G.-S., Lu, Q., Shen, W., & Zhang, L. (2017) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.07.009 · Cited by 35
Parallel Tracking and Verifying
Fan, H., & Ling, H. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2904789 · Cited by 37
“To this end, numerous object appearance modeling approaches have been proposed, including incremental subspace learning [39], sparse principal component analysis (SPCA) [40] and sparse representation [41]–[44].”
MethodRemote-Sensing Image Denoising With Multi-Sourced Information
Liu, P., Wang, M., Wang, L., & Han, W. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2891566 · Cited by 35
“[42], we then have”
Adeel, A., Ahmad, J. E., Larijani, H., & Hussain, A. (2019) · Cognitive Computation · doi:10.1007/s12559-019-09653-z · Cited by 42
“The video files were processed by extracting a sequence of individual frames and applying a Viola-Jones lip detector [37] and object tracker [38].”
MethodEvent-based Star Tracking via Multiresolution Progressive Hough Transforms
Bagchi, S., & Chin, T.-J. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093309 · Cited by 41
“This can be achieved using incremental PCA [37].”
Robust Method for Measuring the Position and Orientation of Drogue Based on Stereo Vision
Zhang, J., Liu, Z., Gao, Y., & Zhang, G. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.2982089 · Cited by 39
“For reliability of the algorithm verification we compare the proposedalgorithmwiththestate-of-the-arttrackingalgorithms, KCF[31],ECO[37],L1APG[38],ORIA[39],MTT[40],CSK [41],DFT[42],IVT[43],ASLA[44],andCT[45],inmultiple datasets.”
MethodRobust visual tracking via online multiple instance learning with Fisher information
Xu, C., Tao, W., Meng, Z., & Feng, Z. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.06.004 · Cited by 37
Hu, Q., He, S., Wang, S., Liu, Y., Zhang, Z., He, L., Wang, F., Cai, Q., Shi, R., & Yang, Y. (2017) · Sensors · doi:10.3390/s17061305 · Cited by 35
“Thus, a number of object tracking algorithms have been proposed, such as tracking learning detection (TLD) [35], visual tracking decomposition (VTD) [36], incremental visual tracking (IVT) [37], multi-task tracking (MTT) [38], visual tracker sampler (VTS) [39], and CMT [40,41].”
BackgroundXie, Y., Zhang, W., Qu, Y., & Zhang, Y. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.07.010 · Cited by 34
Severely Blurred Object Tracking by Learning Deep Image Representations
Ding, J., Huang, Y., Liu, W., & Huang, K. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2406231 · Cited by 34
“Our method is also compared with results reported in [21], which reports performances of 8 state-of-the-art trackers (DLT [21], multi-task tracking (MTT) [31], compressed tracking (CT) [32], visual tracking decomposition (VTD) [15], MIL [16], a latest variant of L1T [33], TLD [23], and IVT [11]) on 10 challenging benc…”
BackgroundMethodInfluentialRobust object tracking using semi-supervised appearance dictionary learning
Zhang, L., Wu, W. J., Chen, T., Strobel, N. K., & Comaniciu, D. (2015) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.04.010 · Cited by 34
Discriminative Low-Rank Tracking
Sui, Y., Tang, Y., & Zhang, L. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.344 · Cited by 37
“’s benchmark, including IVT [27], 2DPCA [31], LRST [38], LSST [33], PCOM [32], LSGPR [29].”
BackgroundMethodInfluentialWhen Correlation Filters Meet Siamese Networks for Real-Time Complementary Tracking
Li, D., Porikli, F., Wen, G., & Kuai, Y. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2892759 · Cited by 35
“[4], [5], [6] and discriminative methods [7], [8], [9].”
Semi-supervised learning approaches to class assignment in ambiguous microstructures
Kunselman, C., Attari, V., McClenny, L. D., Braga-Neto, U., & Arróyave, R. (2020) · Acta Materialia · doi:10.1016/j.actamat.2020.01.046 · Cited by 27
Enabling On-Device CNN Training by Self-Supervised Instance Filtering and Error Map Pruning
Wu, Y., Wang, Z., Shi, Y., & Hu, J. (2020) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2020.3012216 · Cited by 56
“This enables incremental/lifelong learning [5] to train an existing model to update its knowledge, and device personalization [6] by learning features from the specific user and improving model accuracy.”
BackgroundImproving Person Tracking Using an Inexpensive Thermal Infrared Sensor
Kumar, S., Marks, T. K., & Jones, M. (2014) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2014.41 · Cited by 34
“To deal with appearance ambiguities, a variety of methods have been proposed based on sparse representation [2], template selection and update [1], subspace-based tracking [17], and feature descriptors [16].”
MethodVisual tracking and learning using speeded up robust features
Li, J., Wang, Y., & Wang, Y. (2012) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.08.002 · Cited by 38
Hu, K., He, W. P., Ye, J., Zhao, L., Peng, H. F., & Pi, J. (2019) · Symmetry · doi:10.3390/sym11060832 · Cited by 34
Gawande, U., Hajari, K., & Golhar, Y. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-023-10630-0 · Cited by 31
Online discriminative dictionary learning for visual tracking
Yang, F., Jiang, Z., & Davis, L. S. (2014) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2014.6836014 · Cited by 35
“In [24], an incremental visual tracker (IVT) using holistic features is presented, but it is less effective in handling high levels of occlusion or non-rigid distortion.”
BackgroundMethodInfluentialGraph-based transductive learning for robust visual tracking
Zha, Y., Yang, Y., & Du-yan, B. (2009) · Pattern Recognition · doi:10.1016/j.patcog.2009.06.011 · Cited by 33
“From the results, when the object undergoes large pose, illumination and cluster, the proposed method performs better than the IVT [15], and graph embedding tracker [19].”
BackgroundMethodInfluentialA large margin framework for single camera offline tracking with hybrid cues
Khanloo, B. Y. S., Stefanus, F., Ranjbar, M., Li, Z.-N., Saunier, N., Sayed, T., & Mori, G. (2012) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2012.01.004 · Cited by 35
“[23], which models the targets dynamics as Gaussians centered on its previous state.”
Background3D object tracking via image sets and depth-based occlusion detection
Chen, Y., Shen, Y., Liu, X., & Zhong, B. (2014) · Signal Processing · doi:10.1016/j.sigpro.2014.08.046 · Cited by 37
Object Tracking by Occlusion Detection via Structured Sparse Learning
Zhang, T., Ghanem, B., Xu, C., & Ahuja, N. (2013) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2013.150 · Cited by 33
“IVT is hardly affected by parameter settings and obtains good results in the absence of severe illumination changes.”
MethodInfluentialRobust visual tracking with discriminative sparse learning
Lu, X., Yuan, Y., & Yan, P. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.11.016 · Cited by 34
Discriminative key-component models for interaction detection and recognition
Sefidgar, Y. S., Vahdat, A., Se, S., & Mori, G. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.02.012 · Cited by 33
Visual Object Tracking Based on Combination of Local Description and Global Representation
Sun, L., & Liu, G. (2010) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2010.2087815 · Cited by 33
“The technical details can be found in [30].”
BackgroundMethodResultInfluentialRobust object tracking by online Fisher discrimination boosting feature selection
Yang, J., Zhang, K., & Liu, Q. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.02.003 · Cited by 35
Graph Regularized and Locality-Constrained Coding for Robust Visual Tracking
Zhou, T., Bhaskar, H., Liu, F., & Yang, J. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2576941 · Cited by 33
“1, in the first N frames, it is assumed that the location of target has been obtained using the IVT method [7].”
BackgroundMethodInfluentialOcclusion-Aware Fragment-Based Tracking With Spatial-Temporal Consistency
Sun, C., Wang, D., & Lu, H. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2580463 · Cited by 33
“φt ( b j t , b j t−1, p j t ) = [ dx ′, ( dx ′ )2 , d y ′, ( d y ′ )2] dx ′ = x j t − x j t−1 − p j t [1] d y ′ = y j t − y j t−1 − p j t [2] .”
BackgroundInfluentialVisual tracking via Boolean map representations
Zhang, K., Liu, Q., Yang, J. J., & Yang, M. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.03.029 · Cited by 34
Self-citationReal time tracking using an active pan-tilt-zoom network camera
Dinh, T. B., Yu, Q., & Medioni, G. G. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5353915 · Cited by 33
Bach, C., Ceglia, D., Song, L., & Duddeck, F. M. E. (2018) · International Journal for Numerical Methods in Engineering · doi:10.1002/nme.6009 · Cited by 42
Robust object tracking based on tracking-learning-detection
Nebehay, G. (2012) · reposiTUm (TU Wien) · Cited by 50
Multiple Cameras Using Real Time Object Tracking for Surveillance and Security System
Susheel Kumar, K., Prasad, S., Saroj, P. K., & Tripathi, R. C. (2010) · 2010 3rd International Conference on Emerging Trends in Engineering and Technology · doi:10.1109/icetet.2010.30 · Cited by 32
Visual tracking via exemplar regression model
Ma, X., Liu, Q., He, Z., Zhang, X., & Chen, W.-S. (2016) · Knowledge-Based Systems · doi:10.1016/j.knosys.2016.05.028 · Cited by 32
“Among the achievements in visual tracking research, the discriminative approaches [1, 2, 3, 4, 5, 6, 7, 8, 9] provide an online mechanism that adapts appearance variations of the target, and achieve better results than their generative rivals [10, 11, 12, 13] on some hard sequences [14].”
BackgroundMethodInfluentialFeature extraction and health status prediction in PV systems
Sepúlveda-Oviedo, E. H., Travé-Massuyès, L., Subias, A., Alonso, C., & Pavlov, M. (2022) · Advanced Engineering Informatics · doi:10.1016/j.aei.2022.101696 · Cited by 39
Enhancing Facial Feature Detection: Hybrid Active Shape and Active Appearance Model (HASAAM)
Iqtait, M., Ababneh, J., Rasmi, M., Abu-Jassar, A. T., & Abuowaida, S. F. A. (2024) · IEEE Access · doi:10.1109/access.2024.3505536 · Cited by 40
Dou, J., & Li, J. (2014) · Neurocomputing · doi:10.1016/j.neucom.2013.12.049 · Cited by 32
Online multiple support instance tracking
Zhou, Q.-H., Lu, H., & Yang, M. (2011) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2011.5771456 · Cited by 32
“Our tracker is bootstrapped with the IVT method [18] for collecting positive and negative samples in the first few frames.”
MethodSelf-citationRobust 3D visual tracking using particle filtering on the SE(3) group
Choi, C., & Christensen, H. I. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980245 · Cited by 32
Robust visual tracking using template anchors
Zajc, L. Č., Leonardis, A., & Kristan, M. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477570 · Cited by 32
Wan, M., Gu, G., Qian, W., Ren, K., Chen, Q., Zhang, H., & Maldague, X. (2018) · Remote Sensing · doi:10.3390/rs10040510 · Cited by 32
“…incrementally learning a low-dimensional subspace representation and achieves promising computational efficiency in practice, but it turns out to be less effective on the condition that the occlusion is heavy or that the distortion is non-rigid due to its adopted holistic appearance model [15,16].”
BackgroundMethodLearning Scale-Adaptive Tight Correlation Filter for Object Tracking
Zhang, S., Lu, W. B., Xing, W., & Zhang, L. (2018) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2868782 · Cited by 35
“visual tracking [5], and the anchor template tracker (NCC) [66] in the VOT2016 dataset, and show the comparison results in Table II following the evaluation framework of VOT.”
MethodReal-time EEG classification via coresets for BCI applications
Netzer, E., Frid, A., & Feldman, D. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2019.103455 · Cited by 37
Vision Tracking: A Survey of the State-of-the-Art
Dutta, A., Mondal, A., Dey, N., Sen, S., Moraru, L., & Hassanien, A. E. (2020) · SN Computer Science · doi:10.1007/s42979-019-0059-z · Cited by 37
Joint t -SNE for Comparable Projections of Multiple High-Dimensional Datasets
Wang, Y., Chen, L., Jo, J., & Wang, Y. (2021) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2021.3114765 · Cited by 32
“Takanori et al. [13] augmented an existing incremental PCA algorithm [36] by applying an affine transformation to find the best overlap of common data points in two adjacent projections and presenting a position estimation algorithm to support adding data points with a non-uniform number of…”
MethodWide-Angle Image Rectification: A Survey
Fan, J., Zhang, J., Maybank, S. J., & Tao, D. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-021-01562-9 · Cited by 40
“…and color information in a scene and are widely used in different computer vision tasks including 3D reconstruction, object detection and tracking (Ross et al., 2008; Everingham et al., 2010; Chen et al., 2020), semantic segmentation, and visual location and navigation (Royer et al., 2007).”
MethodModeling local behavior for predicting social interactions towards human tracking
Yan, X., Kakadiaris, I. A., & Shah, S. K. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.10.019 · Cited by 38
“To account for appearance variation of the target caused by change of illumination, deformation and pose, a large amount of work has been proposed [12–17] and these methods perform well and get good results.”
MethodXiao, J., Stolkin, R., Oussalah, M., & Leonardis, A. (2016) · IEEE Sensors Journal · doi:10.1109/jsen.2016.2514704 · Cited by 33
“CSK [12], and IVT [3], which all reported excellent performance in [10], summerized in Tab.”
Backgrounddarfix – data analysis for dark-field X-ray microscopy
Ferrer, J. G., Rodríguez-Lamas, R., Payno, H., Nolf, W. D., Cook, P., Solé, V. A., Yildirim, C., & Detlefs, C. (2023) · Journal of Synchrotron Radiation · doi:10.1107/s1600577523001674 · Cited by 46
Tracking benchmark and evaluation for manipulation tasks
Roy, A., Zhang, X., Wolleb, N., Quintero, C. P., & Jägersand, M. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139526 · Cited by 35
“2) Online Learning Based: Three online learning based trackers were used, IVT [5] , L1-APG [13] and TLD [6].”
BackgroundMethodInfluentialObject Tracking via Robust Multitask Sparse Representation
Bai, Y., & Tang, M. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2320291 · Cited by 31
“To evaluate our robust multitask tracker (RMTT), twelve challenging sequences from prior work [3], [5], [18] are used.”
MethodColor Invariant SURF in Discriminative Object Tracking
Chu, D. M., & Smeulders, A. W. M. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35740-4_6 · Cited by 32
“For comparison purpose, three other state-of-the-art trackers are considered: the foreground background tracker (FBT) in [2]; the incremental visual tracker (IVT) in [3] and the Kalman predictive tracker (KAT) in [4].”
BackgroundHybrid support vector machines for robust object tracking
Zhang, S., Sui, Y., Yu, X., Zhao, S., & Zhang, L. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.02.008 · Cited by 33
Visual tracking via incremental self-tuning particle filtering on the affine group
Li, M., Chen, W. R., Huang, K., & Tan, T. (2010) · 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.2010.5539815 · Cited by 31
“They are the ”Trellis” (Figure 4), ”Sylvester” (Figure 7 1st column), ”Dudek” (Figure 8), ”Cubic” (Figure 7 2nd column) and ”Headshoulder” (Figure 7 3rd column) sequences, with the first three from Ross’s datasets [ 18 ].”
MethodInfluentialRobust visual tracking via efficient manifold ranking with low-dimensional compressive features
Zhou, T., He, X., Xie, K., Fu, K., Zhang, J., & Yang, J. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.03.008 · Cited by 31
“Comparatively, our method and IVT exhibit a better discriminative ability and outperform other methods at frames #495 and #535.”
MethodInfluentialVisual Tracking Via Kernel Sparse Representation With Multikernel Fusion
Wang, L., Yan, H., Lv, K., & Pan, C. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2302496 · Cited by 31
“To solve this problem, on one hand, some methods [7], [8] are proposed to improve template representation.”
MethodInfluentialLearning online structural appearance model for robust object tracking
Yang, M., Pei, M., Wu, Y., & Jia, Y. (2015) · Science China Information Sciences · doi:10.1007/s11432-014-5177-6 · Cited by 31
Self-citationParticle filter with occlusion handling for visual tracking
Lin, S. D., Lin, J., & Chuang, C.-Y. (2015) · IET Image Processing · doi:10.1049/iet-ipr.2014.0666 · Cited by 31
Using FTOC to track shuttlecock for the badminton robot
Chen, W., Liao, T., Li, Z., Lin, H., Xue, H., Zhang, L., Guo, J., & Cao, Z. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.023 · Cited by 34
Deep visual nerve tracking in ultrasound images
Alkhatib, M., Hafiane, A., Vieyres, P., & Delbos, A. (2019) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2019.05.007 · Cited by 33
An Online Classification Method for Fault Diagnosis of Railway Turnouts
Ou, D., Ji, Y., Zhang, L., & Liu, H. (2020) · Sensors · doi:10.3390/s20164627 · Cited by 31
An Experimental Comparison of Anomaly Detection Methods for Collaborative Robot Manipulators
Graabæk, S. G., Ancker, E. V., Fugl, A. R., & Christensen, A. L. (2023) · IEEE Access · doi:10.1109/access.2023.3289068 · Cited by 35
Active learning for adaptive surrogate model improvement in high-dimensional problems
Guo, Y., Nath, P., Mahadevan, S., & Witherell, P. (2024) · Structural and Multidisciplinary Optimization · doi:10.1007/s00158-024-03816-9 · Cited by 43
“For problems with a large number of training samples, incremental PCA (Levy and Lindenbaum 1998; Ross et al. 2008) can overcome the memory limitations by processing the dataset in mini-batch fashion.”
MethodRobust visual tracking via incremental low-rank features learning
Zhang, C., Liu, R., Qiu, T., & Su, Z. (2013) · Neurocomputing · doi:10.1016/j.neucom.2013.10.020 · Cited by 30
Large-Scale Situation Awareness With Camera Networks and Multimodal Sensing
Ramachandran, U., Hong, K., Iftode, L., Jain, R., Kumar, R., Rothermel, K., Shin, J., & Sivakumar, R. (2012) · Proceedings of the IEEE · doi:10.1109/jproc.2011.2182093 · Cited by 30
Incremental MPCA for Color Object Tracking
Wang, D., Lu, H., & Chen, Y. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.433 · Cited by 30
“IMPCA TRACKING USING BAYES INFERENCE Visual tracking can be considered as a Bayesian inference task in a Markov model with hidden state variables [3].”
BackgroundMethodOnline Kernel Slow Feature Analysis for Temporal Video Segmentation and Tracking
Liwicki, S., Zafeiriou, S. P., & Pantić, M. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2428052 · Cited by 30
“A simple modification of ˜X δ allows for changing means [9], [10].”
BackgroundMethodInfluentialA real-time visual object tracking system based on Kalman filter and MB-LBP feature matching
Cai, Z., Gu, Z., Yu, Z. L., Liu, H., & Zhang, K. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2411-6 · Cited by 31
“The selected trackers are Multiple Instance Learning (MIL) [6], the online AdaBoost method (OAB) [13], the online Discriminative Feature Selection (ODFS) [24], Semi-supervised online boosting (SemiBoost) [14], the fragment tracker (Frag) [4], Incremental learning for robust Visual Tracker (IVT) [33],Tracking-Learning-…”
MethodInfluentialVisual object tracking via enhanced structural correlation filter
Chen, K., Tao, W., & Han, S. (2017) · Information Sciences · doi:10.1016/j.ins.2017.02.012 · Cited by 34
“in terms of their accuracy and the robustness of visual tracking [4, 11, 14, 20, 24, 27, 34, 36, 38].”
BackgroundDeep learning assisted robust visual tracking with adaptive particle filtering
Qian, X., Han, L., Wang, Y., & Ding, M. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.09.001 · Cited by 31
Zhang, X., Ren, K., Wan, M., Gu, G., & Chen, Q. (2017) · Infrared Physics & Technology · doi:10.1016/j.infrared.2017.10.003 · Cited by 30
Adaptive skew-sensitive ensembles for face recognition in video surveillance
De‐la‐Torre, M., Granger, É., Sabourin, R., & Gorodnichy, D. O. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.05.008 · Cited by 30
“implemented using the incremental visual tracking (IVT) algorithm, which incrementally learns the low-dimensional subspace representation (Eigen basis) by efficiently adapting online to changes in the appearance of the face model [40].”
MethodSong, X., Shao, X., Zhang, Q., Shibasaki, R., Zhao, H., Cui, J., & Zha, H. (2013) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2438653.2438670 · Cited by 30
A novel supervised level set method for non-rigid object tracking
Sun, X., Yao, H., & Zhang, S. (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.2011.5995656 · Cited by 30
“Ross et al. [19] use the incremental principal component analysis to adaptively track object with large changes in pose, scale, and illumination.”
BackgroundA hybrid mobile object tracker based on the modified Cuckoo Search algorithm and the Kalman Filter
Ljouad, T., Amine, A., & Rziza, M. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.04.003 · Cited by 30
Learning a Tracking and Estimation Integrated Graphical Model for Human Pose Tracking
Zhao, L., Gao, X., Tao, D., & Li, X. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2411287 · Cited by 30
“1) Pictorial Structure: The complete configuration of a pose is denoted as P = {Pi }Ki=1, where K is the total number of parts (e.g., K = 8 in our case).”
BackgroundCorrelation filters based on temporal regularization and background awareness,
Zhao, J.-W., Lu, Y., & Zhou, Z.-H. (2020) · Computers & electrical engineering · doi:10.1016/j.compeleceng.2020.106757 · Cited by 26
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.