论文盘点：基于图卷积GNN的多目标跟踪算法解析
Source: PaperWeekly
[1] Jiang X, Li P, Li Y, et al. Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking[J]. arXiv preprint arXiv:1907.05315, 2019.
[2] Ma C, Li Y, Yang F, et al. Deep association: End-to-end graph-based learning for multiple object tracking with conv-graph neural network[C]//Proceedings of the 2019 on International Conference on Multimedia Retrieval. 2019: 253-261.
[3] Jiahe L, Xu G, Tingting J. Graph Networks for Multiple Object Tracking [C]//The IEEE Winter Conference on Applications of Computer Vision (WACV).2020.
[4] Brasó G, Leal-Taixé L. Learning a neural solver for multiple object tracking [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 6247-6257.
[5] Weng X, Wang Y, Man Y, et al. GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning [J]. arXiv preprint arXiv:2006.07327, 2020.
[6] Weng X, Yuan Y, Kitani K. Joint 3d tracking and forecasting with graph neural network and diversity sampling [J]. arXiv preprint arXiv:2003.07847, 2020.
[7] Wang Y, Weng X, Kitani K. Joint Detection and Multi-Object Tracking with Graph Neural Networks [J]. arXiv preprint arXiv:2006.13164, 2020.