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 401–500 of 1,001
Specular Reflection Separation With Color-Lines Constraint
Ren, W., Tian, J., & Tang, Y. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2675204 · Cited by 50
“Specular reflection often has some negative effects on visual quality and degrades the performance of various computer vision algorithms, such as image segmentation [1], color constancy [2], object detection [3], and visual tracking [4].”
BackgroundVisDrone-SOT2018: The Vision Meets Drone Single-Object Tracking Challenge Results
Wen, L., Zhu, P., Du, D., Bian, X., Ling, H., Hu, Q., Liu, C., Cheng, H., Liu, X., Ma, W., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11021-5_28 · Cited by 54
Object tracking via appearance modeling and sparse representation
Chen, F., Wang, Q., Wang, S., Zhang, W., & Xu, W. (2011) · Image and Vision Computing · doi:10.1016/j.imavis.2011.08.006 · Cited by 51
“Incremental subspace methods based on Principal Component Analysis (PCA) or its variants have also been used for online object representation [8,9].”
InfluentialPlanar Object Tracking in the Wild: A Benchmark
Liang, P., Wu, Y., Lu, H., Wang, L., Liao, C., & Ling, H. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8461037 · Cited by 58
Liu, X., Yang, Y., Ma, C., Li, J., & Zhang, S. (2020) · Applied Sciences · doi:10.3390/app10155064 · Cited by 61
“For”
Deep Architectures for Automated Seizure Detection in Scalp EEGs
Golmohammadi, M., Ziyabari, S., Shah, V., de Diego, S. L., Iyad Obeid, A., & Picone, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.09776 · Cited by 44
“The architecture of our IPCA/LSTM system is presented in Figure 2.”
MethodInfluentialGeneralized mean for robust principal component analysis
Oh, J., & Kwak, N. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.01.002 · Cited by 48
“It is useful in representation of input data in a low dimensional space and it has been successfully applied to face recognition [3,4], visual tracking [5], clustering [6,7], and so on.”
BackgroundAdaptive Local Movement Modeling for Robust Object Tracking
Zhang, B., Li, Z., Perina, A., Bue, A. D., Murino, V., & Liu, J. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2540978 · Cited by 52
Passos, L. A., Papa, J. P., Del Ser, J., Hussain, A., & Adeel, A. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.09.006 · Cited by 47
“After extracting a sequence of individual frames, the lip-regions are identified using Viola-Jones [7] and tracked across a sequence of frames using a method proposed in [31].”
MethodChen, W., Zhang, K., & Liu, Q. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.06.048 · Cited by 49
Wireless big data: transforming heterogeneous networks to smart networks
Huang, Y., Tan, J., & Liang, Y. (2017) · Journal of Communications and Information Networks · doi:10.1007/s41650-017-0002-1 · Cited by 50
“Two bright ways to work out this problem are transfer learning([42]) and incremental learning([43]).”
BackgroundVisual Object Tracking in First Person Vision
Dunnhofer, M., Furnari, A., Farinella, G. M., & Micheloni, C. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01694-6 · Cited by 64
“Preliminary trackers were based on mean shift algorithms [17], key-point [74], part-based meth-ods [14,80], or SVM [45] and incremental [90] learning.”
MethodXiao, J., Stolkin, R., & Leonardis, A. (2015) · 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.2015.7299132 · Cited by 56
On Recognizing Faces in Videos Using Clustering-Based Re-Ranking and Fusion
Bhatt, H. S., Singh, R., & Mayank Vatsa, A. (2014) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2014.2318433 · Cited by 50
“For profile-face videos, a tracking technique [36] is used to track and detect faces.”
MethodImage Alignment by Online Robust PCA via Stochastic Gradient Descent
Song, W., Zhu, J., Li, Y., & Chen, C. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2455711 · Cited by 47
“VTD and IVT both drift from frame #344.”
MethodModeling Hierarchical Brain Networks via Volumetric Sparse Deep Belief Network
Dong, Q., Ge, F., Qiang, N., Zhao, Y., Lv, J., Huang, H., Yuan, J., Jiang, X., Shen, D. G., & Liu, T. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2945231 · Cited by 58
“6) Progressively Loading: Due to the very large size of fMRI dataset, a progressively loading algorithm was used to tackle the issue that big data won’t fit in memory [63].”
MethodLi, Y., Fu, C., Huang, Z., Zhang, Y., & Pan, J. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.2990064 · Cited by 49
Li, Y., Bian, C., & Chen, H. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3204105 · Cited by 59
“Ross et al. [32] proposed incremental 153 learning for visual tracking, effectively improving tracking 154 accuracy and speed.”
BackgroundMore about VLAD: A leap from Euclidean to Riemannian manifolds
Faraki, M., Harandi, M. T., & Porikli, F. (2015) · 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.2015.7299129 · Cited by 53
“[39].”
Teixeira, L. F., & Côrte-Real, L. (2008) · Pattern Recognition Letters · doi:10.1016/j.patrec.2008.04.001 · Cited by 54
“Ross et al. (2007), on the other hand, presented a method that incrementally learns a subspace representation, adapting itself to appearance changes.”
MethodVisual Tracking via Coarse and Fine Structural Local Sparse Appearance Models
Jia, X., Lu, H., & Yang, M. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2592701 · Cited by 47
“On the other hand, the MASLA_4 , SCM and IVT [1] methods do not perform well as the number of particles are fixed in all experiments as a trade-off between speed and accuracy.”
BackgroundMethodInfluentialSelf-citationDeep Architectures for Spatio-Temporal Modeling: Automated Seizure Detection in Scalp EEGs
Golmohammadi, M., Ziyabari, S., Shah, V., Obeid, I., & Picone, J. (2018) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2018.00118 · Cited by 47
Selective Spatial Regularization by Reinforcement Learned Decision Making for Object Tracking
Guo, Q., Han, R., Feng, W., Chen, Z., & Wan, L. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2955292 · Cited by 45
Symbiotic Tracker Ensemble Toward A Unified Tracking Framework
Gao, Y., Ji, R., Zhang, L., & Hauptmann, A. G. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2302366 · Cited by 45
Online State-Based Structured SVM Combined With Incremental PCA for Robust Visual Tracking
Yin, Y., Xu, D., Wang, X., & Bai, M. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2363078 · Cited by 46
“Though IVT and TLD can also handle multiscale case, they cannot track the object in the case of challenging pose variety and the cluttered backgrounds (see the frames #120, #155, #161, and #171 in Fig.”
BackgroundMethodInfluentialVisual Tracking via Particle Filtering on the Affine Group
Kwon, J., & Park, F. C. (2009) · The International Journal of Robotics Research · doi:10.1177/0278364909345167 · Cited by 46
“A number of recent approaches to particle filtering-based visual tracking explicitly make use of the two-dimensional affine transformation as the underlying state space e.g. Zhou et al. (2004), Li et al. (2007), and Ross et al. (2008).”
BackgroundMethodInfluentialHu, W., Gao, J. G., Xing, J., Zhang, C., & Maybank, S. J. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2539944 · Cited by 49
“The effective modeling of object appearance variations plays a critical role in visual object tracking [1], [2], [3], [6], [8], [9], [13], [21].”
BackgroundLearning to Diffuse: A New Perspective to Design PDEs for Visual Analysis
Liu, R., Zhong, G., Cao, J., Lin, Z., Shan, S., & Luo, Z. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2522415 · Cited by 51
“…tracking methods, i.e., DSST [59], TLD [60], ASLA [61], CXT [62], VTD [63], CSK [64], DFT [65], L1APG [66], MTT [67], OAB [68], LOT [69], MIL [70], IVT [36], Frag [71], SPT [72], ORIA [73], CT [74], VR-V [75] and SPOT [76], on the tracking benchmark [77] with 50 challenging video sequences.”
MethodGeng, X., & Smith‐Miles, K. (2009) · Encyclopedia of Biometrics · doi:10.1007/978-0-387-73003-5_304 · Cited by 45
Face Recognition and Retrieval in Video
Shan, C. (2010) · Studies in computational intelligence · doi:10.1007/978-3-642-12900-1_9 · Cited by 49
“[88] represented the target in a low-dimensional subspace which is adaptively updated using the images tracked in the previous frames.”
MethodDeep Learning of Appearance Models for Online Object Tracking
Zhai, M., Chen, L., Mori, G., & Javan, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11018-5_57 · Cited by 49
Mondal, A., Ghosh, S., & Ghosh, A. K. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-016-0959-5 · Cited by 47
“In literature, various tracking techniques (Avidan 2007; Ross et al. 2008; Santner et al. 2010; Kwon and Lee 2010; Babenko et al. 2011; Hare et al. 2011; SevillaLara and Learned-Miller 2012; Jia et al. 2012; Kalal et al. 2012; Zhang et al. 2013; Yang andNevatia 2014; Zhong et al. 2014; Yang et al.…”
BackgroundInfluentialConstrained Superpixel Tracking
Wang, L., Lu, H., & Yang, M. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2675910 · Cited by 49
“Given Xi t of the ith candidate, we apply affine image warp [1] within the foreground map and obtain the region Mi t (which is normalized to 64×64 pixels in our experiment) corresponding to the ith candidate.”
BackgroundMethodInfluentialSelf-citationMatching Construction Workers across Views for Automated 3D Vision Tracking On-Site
Konstantinou, E., & Brilakis, I. (2018) · Journal of Construction Engineering and Management · doi:10.1061/(asce)co.1943-7862.0001508 · Cited by 44
DNN Driven Speaker Independent Audio-Visual Mask Estimation for Speech Separation
Gogate, M., Adeel, A., Marxer, R., Barker, J., & Hussain, A. (2018) · Interspeech (USB) · doi:10.21437/interspeech.2018-2516 · Cited by 44
“Video : The speakers’ lip images are extracted out of the GRID Corpus videos (recorded at 25 frames per second) using a Viola-Jones lip detector [19] and an object tracker [20].”
MethodCorrelation Filter-Based Visual Tracking for UAV with Online Multi-Feature Learning
Fu, C., Lin, F., Li, Y., & Chen, G. (2019) · Remote Sensing · doi:10.3390/rs11050549 · Cited by 44
“The subspace representation [28] is an effective method for visual tracking.”
MethodRobust Visual Tracking via Online Discriminative and Low-Rank Dictionary Learning
Zhou, T., Liu, F., Bhaskar, H., & Yang, J. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2747998 · Cited by 43
“In order to compare the computational demand of the proposed tracker to other state-of-the-art trackers, methods that are implemented using MATLAB code such as SCM [28], SST [61], ASLA [61], IVT [24], and 1 [22] are selected.”
MethodOnline Learning with Self-Organizing Maps for Anomaly Detection in Crowd Scenes
Feng, J., Zhang, C., & Hao, P. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.878 · Cited by 43
“Thus, we integrate a learning rate α to replace the earlier observations with new observations gradually [7].”
ResultVisual tracking by partition-based histogram backprojection and maximum support criteria
Lee, J.-Y., & Yu, W. (2011) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2011.6181739 · Cited by 44
“It is slightly slower than the mean-shift (MS) but much faster than FragT, IncL, and MIL.”
BackgroundMethodInfluentialLong-Term Tracking through Failure Cases
Lebeda, K., Hadfield, S., Matas, J., & Bowden, R. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.26 · Cited by 43
“[15] where the initial target face is so dark that visual features are almost indistinguishable to the human eye.”
BackgroundGraph mode-based contextual kernels for robust SVM tracking
Li, X., Dick, A. R., Wang, H., Shen, C., & van den Hengel, A. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126364 · Cited by 53
“Using the polluted training data, both VTD and IPCA may learn an inaccurate or wrong subspace model for object representation, leading to inaccurate or wrong tracking results.”
BackgroundMethodInfluentialParticle Filter With a Mode Tracker for Visual Tracking Across Illumination Changes
Das, S., Kale, A. A., & Vaswani, N. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2174370 · Cited by 43
Diversity-aware classifier ensemble selection via f-score
Visentini, I., Snidaro, L., & Foresti, G. L. (2015) · Information Fusion · doi:10.1016/j.inffus.2015.07.003 · Cited by 44
The State-of-the-Art in Visual Object Tracking
Jalal, A. S., & Singh, V. (2012) · Informatica · Cited by 60
Structure-Regularized Compressive Tracking With Online Data-Driven Sampling
Guo, Q., Feng, W., Zhou, C., Pun, C., & Wu, B. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2745205 · Cited by 44
“Generative models, such as subspace methods [2], [9] and holistic templates [10], [11],”
MethodTracking Randomly Moving Objects on Edge Box ProposalsPreprint
Zhu, G., Porikli, F., & Li, H. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1507.08085 · Cited by 51
“Particle Based Search: In recent years, tracking algorithms [18, 26, 13] based on particle filtering has been extensively studied.”
BackgroundJain, P., Jin, C., Kakade, S. M., Netrapalli, P., & Sidford, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.06929 · Cited by 127
A multiple template approach for robust tracking of fast motion target
Sun, J., He, F., Chen, Y., & Chen, X. (2016) · Applied mathematics/Applied Mathematics. A Journal of Chinese Universities/Gao-xiao yingyong shuxue xuebao · doi:10.1007/s11766-016-3378-z · Cited by 42
Dynamic Objectness for Adaptive Tracking
Stalder, S., Gräbner, H., & Gool, L. V. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37431-9_4 · Cited by 43
“, a color histogram [4], a subspace model [5], parts [6] or stable structures [7].”
BackgroundUnsupervised Subject Detection via Remote PPG
Wang, W., Stuijk, S., & de Haan, G. (2015) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2015.2438321 · Cited by 43
“To solve this problem, we employ the incremental subspace updating [14] to smoothly adapt the xi ∈ X to real time changes in the time domain.”
Robust Visual Tracking with Deep Convolutional Neural Network Based Object Proposals on PETS
Zhu, G., Porikli, F., & Li, H. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.160 · Cited by 44
“Generative learning based models including the subspace learning [24] and sparse representation [21, 17, 15] mainly concentrate on how to construct an object rep2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops”
MethodEfficient Image Set Classification Using Linear Regression Based Image Reconstruction
Shah, S. A. A., Nadeem, U., Bennamoun, M., Sohel, F. A., & Togneri, R. B. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.88 · Cited by 42
Two-Dimensional Visual Tracking in Construction Scenarios: A Comparative Study
Xiao, B., & Zhu, Z. (2018) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000738 · Cited by 48
Online Robust Low-Rank Tensor Modeling for Streaming Data Analysis
Li, P., Feng, J., Jin, X., Zhang, L., Xu, X., & Yan, S. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2860964 · Cited by 43
“Similar trackers include Incremental Visual Tracking [58] that learns a low-dimensional subspace representation, online robust image alignment (ORIA) [55] that uses wellaligned images to linearly and sparsely reconstruct newly arrived ones after image alignment, and ORPCA-IA [56] that considers geometrical transformat…”
Robust visual object tracking using context-based spatial variation via multi-feature fusion
Elayaperumal, D., & Joo, Y. H. (2021) · Information Sciences · doi:10.1016/j.ins.2021.06.084 · Cited by 42
Object Tracking via 2DPCA and $\ell_{1}$-Regularization
Wang, D., & Lu, H. (2012) · IEEE Signal Processing Letters · doi:10.1109/lsp.2012.2215320 · Cited by 41
“We conduct numerous experiments on challenging image sequences to illustrate the effectiveness of the proposed method.”
BackgroundMethodLearning Local Appearances With Sparse Representation for Robust and Fast Visual Tracking
Bai, T., Li, Y., & Zhou, X. (2014) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2332279 · Cited by 41
“We present empirical results on publicly available benchmark video sequences, and show that the proposed appearance model can lead to more robust and efficient tracking than existing state-of-the-art algorithms in the literature.”
BackgroundMethodResultInfluentialDouble Nuclear Norm-Based Matrix Decomposition for Occluded Image Recovery and Background Modeling
Zhang, F., Yang, J. J., Tai, Y. Y., & Tang, J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2400213 · Cited by 41
MC-HOG Correlation Tracking with Saliency Proposal
Zhu, G., Wang, J., Wu, Y., Zhang, X., & Lu, H. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10450 · Cited by 42
“Generative methods learn an object reference model to locate the object by searching for the most similar image region, such as template matching (Matthews, Ishikawa, and Baker 2004), subspace learning (Ross et al. 2008), sparse representation (Mei et al. 2011).”
MethodJoint Registration and Representation Learning for Unconstrained Face Identification
Hayat, M., Khan, S. H., Werghi, N., & Goecke, R. (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.2017.169 · Cited by 42
“We therefore use tracking [28] to extract face regions from video frames.”
MethodClustering Local Motion Estimates for Robust and Efficient Object Tracking
Maresca, M. E., & Petrosino, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16181-5_17 · Cited by 41
“To model such variability, various approaches have been proposed, such as: updating a low dimensional subspace representation [15], MIL based [1] and template or patch based.”
MethodAre pre-trained CNNs good feature extractors for anomaly detection in surveillance videos?
de Nazaré, T. S., de Mello, R. F., & Ponti, M. A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08495 · Cited by 18
“After normalizing the data we used the Incremental PCA (IPCA) algorithm [24] to reduce data dimensionality to 50 and 100 dimensions.”
MethodA compact association of particle filtering and kernel based object tracking
Yao, A., Lin, X., Wang, G., & Yu, S. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.01.016 · Cited by 40
Learning spatio-temporal discriminative model for affine subspace based visual object tracking
Xu, T., Zhu, X., & Wu, X. (2023) · Visual Intelligence · doi:10.1007/s44267-023-00002-1 · Cited by 46
“Existing visual object tracking approaches include generative learning and discriminative learning, e.g., image matching [25], statistical theory [26], particle filtering framework [27], subspace learning methodology [28], discriminative correlation filters [1], and deep neural networks [29].”
BackgroundRobust Tracking with Weighted Online Structured Learning
Yao, R., Shi, Q., Shen, C., Zhang, Y., & van den Hengel, A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33712-3_12 · Cited by 41
“Our tracker is compared with 8 of the latest state-of-the-art tracking methods named Struck(structured output tracker [14]), MIL(multiple instance boosting-based tracker [11]), OAB(online AdaBoost [9]), Frag(Fragment-based tracker [2]), IVT(incremental subspace visual tracker [3]), VTD(visual tracking decomposition [4…”
BackgroundMethodRobust Visual Tracking via Sparsity-Induced Subspace Learning
Sui, Y., Zhang, S., & Zhang, L. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2462076 · Cited by 41
“tracking [1], where the obtained targets in successive frames”
Visual Object Tracking by Structure Complexity Coefficients
Yuan, Y., Yang, H., Fang, Y., & Lin, W. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2440996 · Cited by 40
“To deal with this problem, several approaches have been proposed such as finding stable local features [9], [10], building appearance subspace robust to multi-view [1], learning part-based appearance models [11]–[13], etc.”
BackgroundMethodResultInfluentialMean-Shift and Sparse Sampling-Based SMC-PHD Filtering for Audio Informed Visual Speaker Tracking
Kılıç, V., Barnard, M., Wang, W., Hilton, A., & Kittler, J. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2599150 · Cited by 43
Pérez, D. L., Leonardi, G. G., Niedźwiecka, A., Radkowska, A., Rączaszek‐Leonardi, J., & Tomalski, P. (2017) · Frontiers in Psychology · doi:10.3389/fpsyg.2017.02228 · Cited by 46
“Other common problems in trackers are those related to occlusions or variations in object appearance (Ross et al., 2007).”
Online Dictionary Learning on Symmetric Positive Definite Manifolds with Vision Applications
Zhang, S., Kasiviswanathan, S. P., Yuen, P. C., & Harandi, M. T. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9595 · Cited by 40
“We compared our approach with four state-of-the-art methods, Incremental Visual Tracking (IVT) (Ross et al. 2008), Sparse Representation Tracking (SRT) (Bao et al. 2012), Online Non-negative Dictionary Learning (ON-NDL) (Wang, Wang, and Yeung 2013), and Log-Euclidean Riemannian Subspace (LogERS)…”
BackgroundMethodInfluentialRecognition From Web Data: A Progressive Filtering Approach
Yang, J., Sun, X., Lai, Y., Zheng, L., & Cheng, M. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2855449 · Cited by 48
“The strategy of progressive learning has been used in data mining [20], pattern recognition [21], computer vision [22]–[24], etc .”
Dual-Force Metric Learning for Robust Distracter-Resistant Tracker
Hong, Z., Mei, X., & Tao, D. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33718-5_37 · Cited by 40
“Generative trackers [4] [14] [25] try to build an appearance model to represent the tracking target.”
BackgroundAdaptive learning of multi-subspace for foreground detection under illumination changes
Dong, Y., & DeSouza, G. N. (2010) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2010.08.003 · Cited by 40
SITUP: Scale Invariant Tracking Using Average Peak-to-Correlation Energy
Ma, H., Acton, S. T., & Lin, Z. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2962694 · Cited by 39
“Examples of generative tracking algorithms are found in [7], [8] and [44].”
BackgroundWang, Z., Li, H.-X., & Chen, C. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2927320 · Cited by 39
“including unsupervised learning [19], supervised learning [40], machine vision [21], evolutionary algorithms [22], system modeling [41], and human–robot interaction [23].”
BackgroundRobust Multi-View Boosting with Priors
Saffari, A., Leistner, C., Godec, M., & Bischof, H. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15558-1_56 · Cited by 41
“The sequences Sylvester and David are taken from [29] and Face Occlusion 1 is taken from [30],”
BackgroundDiscontinuity-aware video object cutout
Zhong, F., Qin, X., Peng, Q., & Meng, X. (2012) · ACM Transactions on Graphics · doi:10.1145/2366145.2366194 · Cited by 39
Co-training framework of generative and discriminative trackers with partial occlusion handling
Dinh, T. B., & Medioni, G. (2011) · Proceedings · doi:10.1109/wacv.2011.5711565 · Cited by 39
“[21], but with partial occlusion handling.”
BackgroundObject tracking using incremental 2D-LDA learning and Bayes inference
Li, G., Liang, D., Huang, Q., Jiang, S., & Gao, W. (2008) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2008.4712068 · Cited by 39
Robust object tracking based on adaptive templates matching via the fusion of multiple features
Li, Z., Gao, S., & Nai, K. (2017) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2017.01.012 · Cited by 39
Inverse Sparse Group Lasso Model for Robust Object Tracking
Zhou, Y., Han, J., Yuan, X., Wei, Z., & Hong, R. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2689918 · Cited by 43
“In [20], the incremental visual tracker (IVT) learns a subspace model that cope with the appearance changes.”
BackgroundMethodGaussian-response correlation filter for robust visual object tracking
Moorthy, S., Choi, J. Y., & Joo, Y. H. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.06.016 · Cited by 40
The cyber-physical bike: a step towards safer green transportation
Smaldone, S., Tonde, C., Ananthanarayanan, V. K., Elgammal, A., & Iftode, L. (2011) · IEEE Workshop on Mobile Computing Systems and Applications (WMCSA) · doi:10.1145/2184489.2184502 · Cited by 49
Robust Visual Tracking Using an Effective Appearance Model Based on Sparse Coding
Zhang, S., Yao, H., Sun, X., & Liu, S. (2012) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2168752.2168757 · Cited by 38
Real-time object tracking via compressive feature selection
Li, K., He, F., & Chen, X. (2016) · Frontiers of Computer Science · doi:10.1007/s11704-016-5106-5 · Cited by 38
Vision-based motion prediction for construction workers safety in real-time multi-camera system
Jeon, Y., Tran, D. Q., Kulinan, A. S., Kim, T., Park, M., & Park, S. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102898 · Cited by 48
Visual Tracking Using a Pixelwise Spatiotemporal Oriented Energy Representation
Cannons, K. J., Gryn, J. M., & Wildes, R. P. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15561-1_37 · Cited by 39
“To illustrate the efficacy of this representation, an affine motion model is used to capture target interframe motion, as applicable when the target depth variation is small relative to the camera-to-target distance [25,22,23].”
BackgroundMethodInfluentialRobust Object Tracking Via Active Feature Selection
Zhang, K., Zhang, L., Yang, M., & Hu, Q. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2269772 · Cited by 42
“Note that the source code of the MIL tracker is written in C + +, which runs at 10 FPS, while the MIL15 tracker runs at 25 FPS.”
MethodSelf-citationKuen, J., Lim, K. M., & Lee, C. P. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.02.012 · Cited by 37
“A typical visual tracking method is dependent on its two major components [1], namely dynamic model (motion estimation) and observational model.”
MethodInteractive Open-Ended Learning for 3D Object Recognition: An Approach and Experiments
Kasaei, H., de Oliveira, M. A. R., Lim, G. H., Lopes, L. S., & Tomé, A. M. (2015) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-015-0189-z · Cited by 38
“In most of the proposed systems, training and testing are separated processes [18], and since limited sample data are used for the training, the systems are unable to adapt to dynamic environments [22].”
BackgroundTracker-Level Fusion for Robust Bayesian Visual Tracking
Biresaw, T. A., Cavallaro, A., & Regazzoni, C. S. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2360027 · Cited by 39
“A region tracker [33] robust to target scale changes (SCs) and in-plane rotations can be fused with an object tracker robust to out-of-plane rotations and deformations [14].”
BackgroundMethodRobust Discriminative Tracking via Landmark-Based Label Propagation
Wu, Y., Pei, M., Yang, M., Yuan, J., & Jia, Y. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2405479 · Cited by 40
“2405479 roughly categorized as either generative [3]–[7] or discriminative [8]–[14] approaches.”
BackgroundSelf-citationZhou, X., Li, Y., & He, B. (2013) · Signal Processing · doi:10.1016/j.sigpro.2013.08.002 · Cited by 38
“Currently, many approaches [1–6] have been proposed for single target visual tracking (STVT).”
BackgroundFusion with Diffusion for Robust Visual Tracking
Zhou, Y. C., Bai, X., Liu, W., & Latecki, L. J. (2012) · neural information processing systems · Cited by 38
Multiple Feature Fusion via Weighted Entropy for Visual Tracking
Ma, L., Lu, J., Feng, J., & Zhou, J. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.358 · Cited by 38
“Due to the computational convenience, single feature descriptor has been widely used in appearance based visual tracking models [4, 16, 28, 37].”
BackgroundMethodInfluentialAction Recognition from Still Images Based on Deep VLAD Spatial Pyramids
Yan, S., Smith, J. S., & Zhang, B. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.03.010 · Cited by 41
Learning Linear Regression via Single-Convolutional Layer for Visual Object Tracking
Chen, K., & Tao, W. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2846405 · Cited by 39
Do not Lose the Details: Reinforced Representation Learning for High Performance Visual Tracking
Wang, Q., Zhang, M., Xing, J., Gao, J. G., Hu, W., & Maybank, S. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/137 · Cited by 40
“Although much progress [Ross et al., 2008; Hare et al., 2011; Henriques et al., 2015] has been made in the past decade, it remains very challenging for a tracker to work at a high speed and to be adaptive and robust to complex tracking scenarios including significant object appearance changes, pose variations, severe…”
BackgroundA Global Optimization Method for Specular Highlight Removal From a Single Image
Xia, W., Chen, E. C. S., Pautler, S. E., & Peters, T. M. (2019) · IEEE Access · doi:10.1109/access.2019.2939229 · Cited by 38
“INTRODUCTION Digital images captured under discrete source illumination often contain specular reflections, which conceal useful image features such as colors and textures [1], [2].”
BackgroundInfluentialA New Hybrid Synthetic Aperture Imaging Model for Tracking and Seeing People Through Occlusion
Yang, T., Zhang, Y., Tong, X., Zhang, X., & Yu, R. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2242553 · Cited by 38
“The standard incremental learning-based tracker in [10] needs to be manually initialized.”
Influential
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.