DeepTrack: Learning Discriminative Feature Representations by Convolutional Neural Networks for Visual Tracking
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Defining hand-crafted feature representations needs expert knowledge, requires timeconsuming manual adjustments, and besides, it is arguably one of the limiting factors of object tracking. In this paper, we propose a novel solution to automatically relearn the most useful feature representations during the tracking process in order to accurately adapt appearance changes, pose and scale variations while preventing from drift and tracking failures. We employ a candidate pool of multiple Convolutional Neural Networks (CNNs) as a data-driven model of different instances of the target object. Individually, each CNN maintains a specific set of kernels that favourably discriminate object patches from their surrounding background using all available low-level cues. These kernels are updated in an online manner at each frame after being trained with just one instance at the initialization of the corresponding CNN. Given a frame, the most promising CNNs in the pool are selected to evaluate the hypothesises for the target object. The hypothesis with the highest score is assigned as the current detection window and the selected models are retrained using a warm-start back-propagation which optimizes a structural loss function. In addition to the model-free tracker, we introduce a class-specific version of the proposed method that is tailored for tracking of a particular object class such as human faces. Our experiments on a large selection of videos from the recent benchmarks demonstrate that our method outperforms the existing state-of-the-art algorithms and rarely loses the track of the target object.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
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 2×
“We compare our method with 9 other state-of-the-art trackers including TLD [12], CXT [6], ASLA [11], Struck [9], SCM [19], and the classical tracking algorithms, e.g., Frag [1], CPF [15], IVT [16] and MIL [2].”
BackgroundMulti-column deep neural network for traffic sign classification
Cireşan, D., Meier, U., Masci, J., & Schmidhuber, J. (2012) · Neural Networks · doi:10.1016/j.neunet.2012.02.023 · Cited by 1,057
Robust object tracking via sparsity-based collaborative model
Zhong, W., Lu, H., & Yang, M.-H. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247882 · Cited by 990 · cited 2×
“We compare our method with 9 other state-of-the-art trackers including TLD [12], CXT [6], ASLA [11], Struck [9], SCM [19], and the classical tracking algorithms, e.g., Frag [1], CPF [15], IVT [16] and MIL [2].”
Method
Cited by
Recent advances in convolutional neural networks
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., et al. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.013 · Cited by 6,576
Learning Multi-domain Convolutional Neural Networks for Visual Tracking
Nam, H., & Han, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.465 · Cited by 2,806
“Despite such huge success of CNNs, only a limited number of tracking algorithms using the representations from CNNs have been proposed so far [10, 20, 28, 39].”
BackgroundMethodHierarchical Convolutional Features for Visual Tracking
Ma, C., Huang, J.-B., Yang, X., & Yang, M.-H. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.352 · Cited by 1,776
Siamese Instance Search for Tracking
Tao, R., Gavves, E., & Smeulders, A. W. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.158 · Cited by 1,208
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
Metadata
- Authors
- Li, H., Li, Y., & Porikli, F.
- Venue
- Proceedings of the British Machine Vision Conference 2014
- Publisher
- British Machine Vision Association
- Published
- 2014
- Pages
- 56.1-56.12
- OpenAlex
- W2069332137
- Cited by
- 137
- References
- 5
- FWCI
- 12.43
- Type
- conference paper
- Language
- en
- Open access
- closed
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.