作者:Kaer Huang, Bingchuan Sun, Feng Chen, Tao Zhang, Jun Xie, Jian Li, Christopher Walter Twombly, Zhepeng Wang
**作者单位:**联想、清华大学
发布时间:2023
发布期刊/会议:CVPRW
出版商:Arxiv
**论文全称:**ReIDTrack:Multi-Object Track and Segmentation Without Motion
论文地址:https://arxiv.org/abs/2308.01622
论文代码:
地位:CVPR2023 WAD研讨会的MOTS赛道上获得第一名,在MOT赛道上获得第二名
In recent years, dominant Multi-object tracking (MOT) and segmentation (MOTS) methods mainly follow the tracking-by-detection paradigm. Transformer-based end-to-end (E2E) solutions bring some ideas to MOT and MOTS, but they cannot achieve a new state-of-theart (SOTA) performance in major MOT and MOTS benchmarks. Detection and association are two main modules of the tracking-by-detection paradigm. Association techniques mainly depend on the combination of motion and appearance information. As deep learning has been recently developed, the performance of the detection and appearance model is rapidly improved. These trends made us consider whether we can achieve SOTA based on only high-performance detection and appearance model. Our paper mainly focuses on exploring this direction based on CBNetV2 with Swin-B as a detection model and MoCo-v2 as a self-supervised appearance model. Motion information and IoU mapping were removed during the association. Our method wins 1st place on the MOTS track and wins 2nd on the MOT track in the CVPR2023 WAD workshop. We hope our simple and effective method can give some insights to the MOT and MOTS research community.