ATOM: Accurate Tracking by Overlap Maximization
Open accessAbstract
While recent years have witnessed astonishing improvements in visual tracking robustness, the advancements in tracking accuracy have been limited. As the focus has been directed towards the development of powerful classifiers, the problem of accurate target state estimation has been largely overlooked. In fact, most trackers resort to a simple multi-scale search in order to estimate the target bounding box. We argue that this approach is fundamentally limited since target estimation is a complex task, requiring high-level knowledge about the object. We address this problem by proposing a novel tracking architecture, consisting of dedicated target estimation and classification components. High level knowledge is incorporated into the target estimation through extensive offline learning. Our target estimation component is trained to predict the overlap between the target object and an estimated bounding box. By carefully integrating target-specific information, our approach achieves previously unseen bounding box accuracy. We further introduce a classification component that is trained online to guarantee high discriminative power in the presence of distractors. Our final tracking framework sets a new state-of-the-art on five challenging benchmarks. On the new large-scale TrackingNet dataset, our tracker ATOM achieves a relative gain of 15% over the previous best approach, while running at over 30 FPS. Code and models are available at https://github.com/visionml/pytracking.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Previous long-term tracking methods usually consist of multiple components, such as base trackers, target verification modules, and global detectors.
“Specifically, previous methods usually consist of multiple components, such as base trackers [9, 50], target verification modules [21], and global detectors [40, 19].”
From Learning Spatio-Temporal Transformer for Visual Tracking (2021) · cites this paper as [9]
The citation is attached to “global detectors.” ATOM instead describes a target classification module and a target estimation module (Proposed Method, §3), and says it extracts features at the previously estimated target location during tracking (Online Tracking Approach, §3.3). Our copy therefore describes local tracking, not ATOM as a global detector. (LLM, conf=0.82)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredFor most popular trackers, correlation plays a critical role in integrating the template or target information into the regions of interest.
“For most of the popular trackers (such as SiamFC [1], SiamRPN [22], and ATOM [9]), correlation plays a critical role in integrating the template or target information into the regions of interest (ROI).”
From Transformer Tracking (2021) · cites this paper as [9]
The Related Work section says correlation-based trackers are popular, supporting the general background claim. But ATOM’s Target Estimation section says it incorporates reference-target information into candidate regions through channel-wise modulation of pooled features, not correlation. Thus the cited paper does not support describing correlation as ATOM’s mechanism for that step; our copy gives no page number for these passages. (LLM, conf=0.86)
Experimental — accuracy not yet measuredPrevious Siamese trackers only exploit spatial information for tracking, while online methods use historical predictions for model updates.
“Previous Siamese trackers [25, 51, 14, 6] only exploit the spatial information for tracking, while online methods [54, 57, 9, 3] use historical predictions for model updates.”
From Learning Spatio-Temporal Transformer for Visual Tracking (2021) · cites this paper as [9]
LTMU B takes the combination of ATOM and SiamMask as the short-term tracker, MDNet as the verifier, and GlobalTrack as the global detector.
“To be specific, LTMU B takes the combination of ATOM [9] and SiamMask [50] as the short-term tracker, MDNet [37] as the verifier, and GlobalTrack [19] as the global detector.”
From Learning Spatio-Temporal Transformer for Visual Tracking (2021) · cites this paper as [9]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · see citing works
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · see citing works
High-Speed Tracking with Kernelized Correlation Filters
Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2345390 · Cited by 5,753 · see citing works
Fully-Convolutional Siamese Networks for Object Tracking
Bertinetto, L., Valmadre, J., Henriques, J. F., Vedaldi, A., & Torr, P. H. S. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-48881-3_56 · Cited by 4,546 · see citing works
Wu, Y., Lim, J., & Yang, M.-H. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2388226 · Cited by 3,371 · cited 1× · see citing works
“In visual tracking, the target state is often represented by a bounding box, either axis aligned [9, 37] or rotated [17].”
BackgroundECO: Efficient Convolution Operators for Tracking
Danelljan, M., Bhat, G., Khan, F. S., & Felsberg, M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.733 · Cited by 2,805 · see citing works
Self-citationLaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking
Fan, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, Y., Liao, C., & Ling, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00552 · Cited by 1,742 · cited 5× · see citing works
“We evaluate the proposed tracker ATOM on five benchmarks: Need for Speed (NFS) [9], UAV123 [24], TrackingNet [25], LaSOT [8], and VOT2018 [17].”
MethodInfluential
Flagged first, then by citations
Research works printed but not linked: 33
- L. Bertinetto, J. Valmadre, S. Golodetz, O. Miksik, and P. H. S. Torr. Staple: Complementary learners for real-time tracking. In CVPR, 2016. 8
- G. Bhat, J. Johnander, M. Danelljan, F. S. Khan, and M. Fels- berg. Unveiling the power of deep tracking. In ECCV, 2018. 1, 2, 6, 8
- M. Danelljan, G. Häger, F. S. Khan, and M. Felsberg. Dis- criminative scale space tracking. TPAMI, 39(8):1561-1575, 2017.
- M. Danelljan, G. Häger, F. Shahbaz Khan, and M. Felsberg. Learning spatially regularized correlation filters for visual tracking. In ICCV, 2015. 1, 2
- M. Danelljan, A. Robinson, F. Khan, and M. Felsberg. Be- yond correlation filters: Learning continuous convolution operators for visual tracking. In ECCV, 2016. 2, 5, 8, 12
- H. K. Galoogahi, A. Fagg, C. Huang, D. Ramanan, and S. Lucey. Need for speed: A benchmark for higher frame rate object tracking. In ICCV, 2017. 2, 6, 7, 8, 11
- Q. Guo, W. Feng, C. Zhou, R. Huang, L. Wan, and S. Wang. Learning dynamic siamese network for visual object track- ing. In ICCV, 2017. 8
- A. He, C. Luo, X. Tian, and W. Zeng. Towards a better match in siamese network based visual object tracker. In ECCV workshop, 2018. 8
- P. Jaccard. The distribution of the flora in the alpine zone. New Phytologist, 11(2):37-50, 1912. 2
- B. Jiang, R. Luo, J. Mao, T. Xiao, and Y. Jiang. Acquisition of localization confidence for accurate object detection. In ECCV, 2018. 2, 3, 5
- D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. In ICLR, 2014. 5
- M. Kristan, A. Leonardis, J. Matas, M. Felsberg, R. Pfugfelder, L. C. Zajc, T. Vojir, G. Bhat, A. Lukezic, A. Eldesokey, G. Fernandez, and et al. The sixth visual ob- ject tracking vot2018 challenge results. In ECCV workshop, 2018. 1, 2, 6, 8
- B. Li, J. Yan, W. Wu, Z. Zhu, and X. Hu. High performance visual tracking with siamese region proposal network. In CVPR, 2018. 2, 6, 8
- F. Li, C. Tian, W. Zuo, L. Zhang, and M. Yang. Learn- ing spatial-temporal regularized correlation filters for visual tracking. In CVPR, 2018. 8
- Y. Li and J. Zhu. A scale adaptive kernel correlation filter tracker with feature integration. In ECCV workshop, 2014. 2, 8
- T. Lin, M. Maire, S. J. Belongie, L. D. Bourdev, R. B. Gir- shick, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick. Microsoft COCO: common objects in context. In ECCV, 2014. 4, 12
- A. Lukezic, T. Vojír, L. C. Zajc, J. Matas, and M. Kris- tan. Discriminative correlation filter tracker with channel and spatial reliability. IJCV, 126(7):671-688, 2018. 1, 8
- C. Ma, J.-B. Huang, X. Yang, and M.-H. Yang. Hierarchical convolutional features for visual tracking. In ICCV, 2015. 2
- M. Mueller, N. Smith, and B. Ghanem. A benchmark and simulator for uav tracking. In ECCV, 2016. 2, 6, 7, 8, 12, 13
- M. Müller, A. Bibi, S. Giancola, S. Al-Subaihi, and B. Ghanem. Trackingnet: A large-scale dataset and bench- mark for object tracking in the wild. In ECCV, 2018. 2, 4, 6, 8, 12
- H. Nam and B. Han. Learning multi-domain convolutional neural networks for visual tracking. In CVPR, 2016. 2, 6, 8
- E. Real, J. Shlens, S. Mazzocchi, X. Pan, and V. Vanhoucke. Youtube-boundingboxes: A large high-precision human- annotated data set for object detection in video. CVPR, 2017. 13
- J. Redmon and A. Farhadi. Yolo9000: Better, faster, stronger. In CVPR, 2017. 3
- S. Ren, K. He, R. B. Girshick, and J. Sun. Faster R-CNN: towards real-time object detection with region proposal net- works. In NIPS, 2015. 3
- Y. Song, C. Ma, X. Wu, L. Gong, L. Bao, W. Zuo, C. Shen, R. W. H. Lau, and M.-H. Yang. VITAL: Visual tracking via adversarial learning. In CVPR, 2018. 8
- C. Sun, D. Wang, H. Lu, and M. Yang. Correlation tracking via joint discrimination and reliability learning. In CVPR, 2018. 1, 5, 8
- R. Tao, E. Gavves, and A. W. M. Smeulders. Siamese in- stance search for tracking. In CVPR, 2016. 8
- J. Valmadre, L. Bertinetto, J. F. Henriques, A. Vedaldi, and P. H. S. Torr. End-to-end representation learning for correla- tion filter based tracking. In CVPR, 2017. 1, 8, 12
- T. Xu, Z. Feng, X. Wu, and J. Kittler. Learning adaptive dis- criminative correlation filters via temporal consistency pre- serving spatial feature selection for robust visual tracking. CoRR, abs/1807.11348, 2018. 8 · arXiv
- Y. Yao, X. Wu, S. Shan, and W. Zuo. Joint representation and truncated inference learning for correlation filter based tracking. In ECCV, 2018. 12
- J. Zhang, S. Ma, and S. Sclaroff. MEEM: robust tracking via multiple experts using entropy minimization. In ECCV, 2014. 1
- Y. Zhang, L. Wang, J. Qi, D. K. Wang, M. Feng, and H. Lu. Structured siamese network for real-time visual tracking. In ECCV, 2018. 8
- Z. Zhu, Q. Wang, L. Bo, W. Wu, J. Yan, and W. Hu. Distractor-aware siamese networks for visual object track- ing. In ECCV, 2018. 1, 2, 4, 6, 8, 12, 13
Cited by
Sorted by citations
Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., & Lu, H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00803 · Cited by 1,588 · see citing works
Detection and tracking meet drones challenge
Zhu, P., Wen, L., Du, D., Bian, X., Fan, H., Hu, Q., & Ling, H. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3119563 · Cited by 1,336 · see citing works
Learning Spatio-Temporal Transformer for Visual Tracking
Yan, B., Peng, H., Fu, J., Wang, D., & Lu, H. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01028 · Cited by 1,280 · see citing works
“To be specific, LTMU B takes the combination of ATOM [11] and SiamMask [57] as the short-term tracker, MDNet [44] as the verifier, and GlobalTrack [21] as the global detector.”
BackgroundMethodInfluentialSiamese Box Adaptive Network for Visual Tracking
Chen, Z., Zhong, B., Li, G., Zhang, S., & Ji, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00670 · Cited by 1,052 · see citing works
SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking
Guo, D., Wang, J., Cui, Y., Wang, Z., & Chen, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00630 · Cited by 984 · see citing works
SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines
Xu, Y., Wang, Z., Li, Z., Yuan, Y., & Yu, G. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6944 · Cited by 974 · see citing works
Probabilistic Regression for Visual Tracking
Danelljan, M., Van Gool, L., & Timofte, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00721 · Cited by 798 · see citing works
Self-citationDeformable Siamese Attention Networks for Visual Object Tracking
Yu, Y., Xiong, Y., Huang, W., & Scott, M. R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00676 · Cited by 495 · see citing works
LaSOT: A High-quality Large-scale Single Object Tracking Benchmark
Fan, H., Bai, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Harshit, Huang, M., Liu, J., et al. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01387-y · Cited by 360 · see citing works
D3S – A Discriminative Single Shot Segmentation Tracker
Lukezic, A., Matas, J., & Kristan, M. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00716 · Cited by 300 · see citing works
GlobalTrack: A Simple and Strong Baseline for Long-Term Tracking
Huang, L., Zhao, X., & Huang, K. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6758 · Cited by 279 · see citing works
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
Yan, B., Peng, H., Wu, K., Wang, D., Fu, J., & Lu, H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01493 · Cited by 277 · see citing works
‘Skimming-Perusal’ Tracking: A Framework for Real-Time and Robust Long-Term Tracking
Yan, B., Zhao, H., Wang, D., Lu, H., & Yang, X. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00247 · Cited by 218 · see citing works
Tracking by Instance Detection: A Meta-Learning Approach
Wang, G., Luo, C., Sun, X., Xiong, Z., & Zeng, W. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00632 · Cited by 206 · see citing works
Siam R-CNN: Visual Tracking by Re-Detection
Voigtlaender, P., Luiten, J., Torr, P. H. S., & Leibe, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00661 · Cited by 115 · see citing works
Towards Accurate Pixel-wise Object Tracking by Attention Retrieval
Zhang, Z., Li, B., Hu, W., & Peng, H. (2020) · arXiv · doi:10.48550/arxiv.2008.02745 · Cited by 32 · see citing works
- Authors
- Danelljan, M., Bhat, G., Khan, F. S., & Felsberg, M.
- Affiliations
- ETH Zurich (CH)
- Inception Institute of Artificial Intelligence (AE)
- Linköping University (SE)
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 4655-4664
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2901751835
- Cited by
- 1,591
- References
- 7
- Citations by year
- 2026: 88 · 2025: 200 · 2024: 296 · 2023: 311 · 2022: 294 · 2021: 230 · 2020: 147 · 2019: 25
- FWCI
- 56.73
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Vetenskapsrådet (2018-04673, 2018-)
- 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 Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- visual object tracking, target state estimation, bounding box estimation, online classification, offline learning, real-time 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
