• Full Text
    • Scholarly Journal

    DeepAF: Transformer-Based Deep Data Association and Track Filtering Network for Multi-Target Tracking in Clutter

    ; 
    ; 
    ; 
    ; 
    . 
    ; Basel Vol. 12, Iss. 3,  (2025): 194.     DOI:10.3390/aerospace12030194
    PDF CiteCite
    Copy URLPrintAll Options

    References (67)

    • 1.

      High-speed tracking-by-detection without using image information

      E. Bochinski; V. Eiselein; T. Sikora. Proceedings of the 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS): 1-6.
    • 2.

      Simple online and realtime tracking with a deep association metric

      Wojke, N; Bewley, A; Paulus, D. Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP).
    • 3.

      DeepDA: LSTM-based deep data association network for multi-targets tracking in clutter

      H. Liu; H. Zhang; C. Mertz. Proceedings of the 2019 22th International Conference on Information Fusion (FUSION): 1-8.
    • 4.

      Learning to multi-target tracking in dense clutter environment with JPDA-recurrent neural networks

      H. Zhang; H.-j. Liu; C.-l. Wang. Proceedings of the 2019 3rd International Conference on Control Engineering and Artificial Intelligence (CCEAI): 012011-.
    • 5.

      Improved IMM algorithm based on RNNs

      L. Deng; D. Li; R. Li. Proceedings of the 2020 4th International Conference on Machine Vision and Information Technology (CMVIT): 012055-.
    • 6.

      How to train your deep multi-object tracker

      Y. Xu; A. Osep; Y. Ban; R. Horaud; L. Leal-Taixé; X. Alameda-Pineda. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition: 6787-6796.
    • 7.

      Retinatrack: Online single stage joint detection and tracking

      Z. Lu; V. Rathod; R. Votel; J. Huang. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): 14668-14678.
    • 8.

      A unified object motion and affinity model for online multi-object tracking

      J. Yin; W. Wang; Q. Meng; R. Yang; J. Shen. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): 6768-6777.
    • 9.

      GMOT-40: A benchmark for generic multiple object tracking

      H. Bai; W. Cheng; P. Chu; J. Liu; K. Zhang; H. Ling. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): 6719-6728.
    • 10.

      Track to detect and segment: An online multi-object tracker

      J. Wu; J. Cao; L. Song; Y. Wang; M. Yang; J. Yuan. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
    • 11.

      An Overview of Machine Learning Methods for Multiple Target Tracking

      C.-Y. Chong. Proceedings of the 2021 IEEE 24th International Conference on Information Fusion (FUSION): 1-9.
    • 12.

      Global tracking transformers

      X. Zhou; T. Yin; V. Koltun; P. Krähenbühl. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): 8771-8780.
    • 13.

      Unified transformer tracker for object tracking

      F. Ma; M.Z. Shou; L. Zhu; H. Fan; Y. Xu; Y. Yang; Z. Yan. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): 8781-8790.
    • 14.

      Towards real-time multi-object tracking

      Z. Wang; L. Zheng; Y. Liu; Y. Li; S. Wang. Proceedings of the European Conference on Computer Vision: 107-122.
    • 15.

      Learning of Global Objective for Network Flow in Multi-Object Tracking

      S. Li; Y. Kong; H. Rezatofighi. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.
    • 16.

      Memot: Multi-object tracking with memory

      J. Cai; M. Xu; W. Li; Z. Xiong; W. Xia; Z. Tu; S. Soatto. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
    • 17.

      Bridging the gap between detection and tracking: A unified approach

      L. Huang; X. Zhao; K. Huang. Proceedings of the IEEE/CVF International Conference on Computer Vision: 3999-4009.
    • 18.

      Joint monocular 3D vehicle detection and tracking

      H.N. Hu; Q.Z. Cai; D. Wang; J. Lin; M. Sun; P. Krahenbuhl; T. Darrell; F. Yu. Proceedings of the IEEE/CVF International Conference on Computer Vision: 5390-5399.
    • 19.

      Pyramid vision transformer: A versatile backbone for dense prediction without convolutions

      W. Wang; E. Xie; X. Li; D.-P. Fan; K. Song; D. Liang; T. Lu; P. Luo; L. Shao. Proceedings of the IEEE/CVF International Conference on Computer Vision: 568-578.
    • 20.

      Spatial-temporal relation networks for multi-object tracking

      Xu, J; Cao, Y; Zhang, Z; Hu, H. Proceedings of the IEEE/CVF International Conference on Computer Vision.