Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Visual representation is crucial for visual tracking methodÂ?s performances. Conventionally, visual representations adopted in visual tracking rely on hand-crafted computer vision descriptors. These descriptors were developed generically without considering tracking-specific information. In this paper, we propose to learn complex-valued invariant representations from tracked sequential image patches, via strong temporal slowness constraint and stacked convolutional autoencoders. The deep slow local representations are learned offline on unlabeled data and transferred to the observational model of our proposed tracker. The proposed observational model retains old training samples to alleviate drift, and collect negative samples which are coherent with targetÂ?s motion pattern for better discriminative tracking. With the learned representation and online training samples, a logistic regression classifier is adopted to distinguish target from background, and retrained online to adapt to appearance changes. Subsequently, the observational model is integrated into a particle filter framework to perform visual tracking. Experimental results on various challenging benchmark sequences demonstrate that the proposed tracker performs favorably against several state-of-the-art trackers. HighlightsTemporal slowness principle is exploited for learning tracking representation.Learned invariant representation is decomposed into amplitude and phase features.Higher-level features are learned by stacking autoencoders convolutionally.A novel observational model to counter drift and collect relevant samples online.Tracking experiments show our method is superior to state-of-the-art trackers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Online Object Tracking: A Benchmark
Wu, Y., Lim, J., & Yang, M.-H. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.312 · Cited by 4,138
Incremental Learning for Robust Visual Tracking
Ross, D. A., Lim, J., Lin, R.-S., & Yang, M.-H. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0075-7 · Cited by 3,061 · cited 1×
“A typical visual tracking method is dependent on its two major components [1], namely dynamic model (motion estimation) and observational model.”
MethodReal-Time Tracking via On-line Boosting
Grabner, H., Grabner, M., & Bischof, H. (2006) · Procedings of the British Machine Vision Conference 2006 · doi:10.5244/c.20.6 · Cited by 1,198 · cited 1×
“Representation learning techniques seek to bypass the conventional way of labor-intensive feature engineering, by disentangling the underlying explanatory factors for the observed input.”
BackgroundA survey of appearance models in visual object tracking
Li, X., Hu, W., Shen, C., Zhang, Z., Dick, A., & Hengel, A. V. D. (2013) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2508037.2508039 · Cited by 705 · cited 1×
“With the learned representation and online training samples, a logistic regression classifier is adopted to distinguish target from background, and retrained online to adapt to appearance changes.”
MethodDeep learning from temporal coherence in video
Mobahi, H., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553469 · Cited by 328 · cited 2×
“To account for object appearance changes, Wang and Yeung [20] pre-trained a stacked denoising autoencoders and finetuned the deep neural network online during tracking.”
BackgroundMethod
Cited by
Learning to Track at 100 FPS with Deep Regression Networks
Held, D., Thrun, S., & Savarese, S. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_45 · Cited by 1,199
Deep visual tracking: Review and experimental comparison
Li, P., Wang, D., Wang, L., & Lu, H. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.11.007 · Cited by 517
Auto-Encoders in Deep Learning—A Review with New Perspectives
Chen, S., & Guo, W. (2023) · Mathematics · doi:10.3390/math11081777 · Cited by 318
A comprehensive review of recent advances on deep vision systems
Abbas, Q., Ibrahim, M. E. A., & Jaffar, M. A. (2019) · Artificial Intelligence Review · doi:10.1007/s10462-018-9633-3 · Cited by 99
Metadata
- Authors
- Kuen, J., Lim, K. M., & Lee, C. P.
- Venue
- Pattern Recognition
- Publisher
- Elsevier BV
- Published
- 2015-10
- Volume
- 48
- Issue
- 10
- Pages
- 2964-2982
- ISSN
- 0031-3203 (ISSN-L)
- OpenAlex
- W1982344527
- Cited by
- 37
- References
- 5
- FWCI
- 4.91
- Type
- journal article
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle. https://app.cochat.ai/papers/10.1016/j.patcog.2015.02.012
- The paper
- Kuen, J., Lim, K. M., & Lee, C. P. (2015). Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle. Pattern Recognition. https://doi.org/10.1016/j.patcog.2015.02.012
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.