CoChat
Sign Up
Cited by 246Video Surveillance and Tracking MethodsAutonomous Vehicle Technology and SafetyAdvanced Neural Network Applications

FAMNet: Joint Learning of Feature, Affinity and Multi-Dimensional Assignment for Online Multiple Object Tracking

Open access
Chu, Peng, Ling, Haibin·2019·2019 IEEE/CVF International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2019.00627
Open this paper in CoChat — free accountOpen PDF

Abstract

Data association-based multiple object tracking (MOT) involves multiple separated modules processed or optimized differently, which results in complex method design and requires non-trivial tuning of parameters. In this paper, we present an end-to-end model, named FAMNet, where Feature extraction, Affinity estimation and Multi-dimensional assignment are refined in a single network. All layers in FAMNet are designed differentiable thus can be optimized jointly to learn the discriminative features and higher-order affinity model for robust MOT, which is supervised by the loss directly from the assignment ground truth. In addition, we integrate single object tracking technique and a dedicated target management scheme into the FAMNet-based tracking system to further recover false negatives and inhibit noisy target candidates generated by the external detector. The proposed method is evaluated on a diverse set of benchmarks including MOT2015, MOT2017, KITTI-Car and UA-DETRAC, and achieves promising performance on all of them in comparison with state-of-the-arts.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/iccv.2019.00627

Cites

7 of 7 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • TrackFormer's tracking-by-attention approach achieves top performance via global attention without relying on additional motion or appearance models.

    “Our tracking-by-attention approach achieves top performance via global attention without relying on additional motion [4, 10] or appearance models [4, 8, 10].”

    From TrackFormer: Multi-Object Tracking with Transformers (2022) · cites this paper as [10]

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

Flagged first, then by citations

Research works printed but not linked: 40

  1. S.-H. Bae and K.-J. Yoon. Confidence-based data associa- tion and discriminative deep appearance learning for robust online multi-object tracking. TPAMI, 2018. 1, 2, 8
  2. W. Choi. Near-online multi-target tracking with aggregated local flow descriptor. In ICCV, 2015. 8
  3. Q. Chu, W. Ouyang, H. Li, X. Wang, B. Liu, and N. Yu. Online multi-object tracking using cnn-based single object tracker with spatial-temporal attention mechanism. ICCV, 2017. 1
  4. R. T. Collins. Multitarget data association with higher-order motion models. In CVPR, 2012. 2
  5. A. Dehghan, Y. Tian, P. H. Torr, and M. Shah. Target identity-aware network flow for online multiple target track- ing. In CVPR, 2015. 2
  6. P. Dollár, R. Appel, S. Belongie, and P. Perona. Fast feature pyramids for object detection. TPAMI, 2014. 7
  7. L. Fagot-Bouquet, R. Audigier, Y. Dhome, and F. Lerasle. Improving multi-frame data association with sparse repre- sentations for robust near-online multi-object tracking. In ECCV, 2016. 1
  8. K. Fang, Y. Xiang, X. Li, and S. Savarese. Recurrent autore- gressive networks for online multi-object tracking. In WACV, 2018. 2
  9. A. Geiger, P. Lenz, and R. Urtasun. Are we ready for au- tonomous driving? the kitti vision benchmark suite. In CVPR, 2012. 7, 8
  10. K. He, G. Gkioxari, P. Dollár, and R. Girshick. Mask r-cnn. In ICCV, 2017. 7
  11. C. Huang, B. Wu, and R. Nevatia. Robust object tracking by hierarchical association of detection responses. In ECCV, 2008. 2
  12. M. Keuper, E. Levinkov, N. Bonneel, G. Lavoué, T. Brox, and B. Andres. Efficient decomposition of image and mesh graphs by lifted multicuts. In ICCV, 2015. 6
  13. M. Keuper, S. Tang, B. Andres, T. Brox, and B. Schiele. Mo- tion segmentation & multiple object tracking by correlation co-clustering. TPAMI, 2018. 1, 7
  14. C. Kim, F. Li, A. Ciptadi, and J. M. Rehg. Multiple hypoth- esis tracking revisited. In ICCV, 2015. 2, 7
  15. C. Kim, F. Li, and J. M. Rehg. Multi-object tracking with neural gating using bilinear lstm. In ECCV, 2018. 7
  16. L. Leal-Taixé, A. Milan, I. Reid, S. Roth, and K. Schindler. MOTChallenge 2015: Towards a benchmark for multi-target tracking. arXiv:1504.01942, 2015. 7 · arXiv
  17. P. Lenz, A. Geiger, and R. Urtasun. Followme: Efficient on- line min-cost flow tracking with bounded memory and com- putation. In ICCV, 2015. 8
  18. A. Milan, S. H. Rezatofighi, A. R. Dick, I. D. Reid, and K. Schindler. Online multi-target tracking using recurrent neural networks. In AAAI, 2017. 2, 7
  19. A. Milan, S. Roth, and K. Schindler. Continuous energy min- imization for multitarget tracking. TPAMI, 2014. 7, 8
  20. A. Milan, K. Schindler, and S. Roth. Detection-and trajectory-level exclusion in multiple object tracking. In CVPR, 2013. 8
  21. A. Milan, K. Schindler, and S. Roth. Multi-target tracking by discrete-continuous energy minimization. TPAMI, 2016. 1
  22. P. Ondruska and I. Posner. Deep tracking: Seeing beyond seeing using recurrent neural networks. In AAAI, 2016. 2
  23. A. Osep, W. Mehner, M. Mathias, and B. Leibe. Combined image-and world-space tracking in traffic scenes. In ICRA, 2017. 8
  24. A. Sadeghian, A. Alahi, and S. Savarese. Tracking the un- trackable: Learning to track multiple cues with long-term dependencies. arXiv:1701.01909, 2017. 2, 7 · arXiv
  25. X. Shi, H. Ling, Y. Pang, W. Hu, P. Chu, and J. Xing. Rank- 1 tensor approximation for high-order association in multi- target tracking. IJCV, 2019. 2, 3, 5, 7, 8
  26. J. Son, M. Baek, M. Cho, and B. Han. Multi-object tracking with quadruplet convolutional neural networks. In CVPR, 2017. 1, 2
  27. S. Tang, M. Andriluka, B. Andres, and B. Schiele. Mul- tiple people tracking by lifted multicut and person re- identification. In CVPR, 2017. 2, 7
  28. S. Wang and C. C. Fowlkes. Learning optimal parameters for multi-target tracking with contextual interactions. IJCV, 2017. 8
  29. X. Wang, E. Türetken, F. Fleuret, and P. Fua. Tracking inter- acting objects using intertwined flows. TPAMI, 2016. 1
  30. X. Wang, M. Yang, S. Zhu, and Y. Lin. Regionlets for generic object detection. In ICCV, 2013. 8
  31. L. Wen, D. Du, Z. Cai, Z. Lei, M.-C. Chang, H. Qi, J. Lim, M.-H. Yang, and S. Lyu. Ua-detrac: A new bench- mark and protocol for multi-object detection and tracking. arXiv:1511.04136, 2015. 7, 8 · arXiv
  32. L. Wen, W. Li, J. Yan, Z. Lei, D. Yi, and S. Z. Li. Multi- ple target tracking based on undirected hierarchical relation hypergraph. In CVPR, 2014. 8
  33. Y. Xiang, A. Alahi, and S. Savarese. Learning to track: Online multi-object tracking by decision making. In ICCV, 2015. 1
  34. F. Yang, W. Choi, and Y. Lin. Exploit all the layers: Fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers. In CVPR, 2016. 8
  35. J. H. Yoon, C.-R. Lee, M.-H. Yang, and K.-J. Yoon. Online multi-object tracking via structural constraint event aggrega- tion. In CVPR, 2016. 7
  36. J. H. Yoon, M.-H. Yang, J. Lim, and K.-J. Yoon. Bayesian multi-object tracking using motion context from multiple ob- jects. In WACV, 2015. 8
  37. A. R. Zamir, A. Dehghan, and M. Shah. Gmcp-tracker: Global multi-object tracking using generalized minimum clique graphs. In ECCV. 2012. 2
  38. A. Zanfir and C. Sminchisescu. Deep learning of graph matching. In CVPR, 2018. 5
  39. L. Zhang, Y. Li, and R. Nevatia. Global data association for multi-object tracking using network flows. In CVPR, 2008. 2
  40. J. Zhu, H. Yang, N. Liu, M. Kim, W. Zhang, and M.-H. Yang. Online multi-object tracking with dual matching at- tention networks. In ECCV, 2018. 2, 7

Cited by

Sorted by citations

Authors
Chu, P., & Ling, H.
Affiliations
  • Temple University (US)
  • Stony Brook University (US)
ORCID
Venue
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2019-10
Pages
6171-6180
DOI
10.1109/iccv.2019.00627
OpenAlex
W2986732333
Cited by
246
References
7
Citations by year
2026: 4 · 2025: 11 · 2024: 28 · 2023: 35 · 2022: 50 · 2021: 60 · 2020: 55 · 2019: 3
FWCI
13.69
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
data association, end-to-end learning, feature extraction, single object tracking, target management

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