Track to Detect and Segment: An Online Multi-Object Tracker

Jialian Wu, Jiale Cao, Liangchen Song, Yu Wang, Ming Yang, Junsong Yuan

CVPR 2021 pp. 12352-12361

doi:10.1109/CVPR46437.2021.01217 /cvpr/2021/wu2021cvpr-track/

Abstract

Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking. In this paper, we present a new online joint detection and tracking model, TraDeS (TRAck to DEtect and Segment), exploiting tracking clues to assist detection end-to-end. TraDeS infers object tracking offset by a cost volume, which is used to propagate previous object features for improving current object detection and segmentation. Effectiveness and superiority of TraDeS are shown on 4 datasets, including MOT (2D tracking), nuScenes (3D tracking), MOTS and Youtube-VIS (instance segmentation tracking). Project page: https://jialianwu.com/projects/TraDeS.html.

PDF CVPR Semantic Scholar

Cite

Text

Wu et al. "Track to Detect and Segment: An Online Multi-Object Tracker." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.01217

Markdown

[Wu et al. "Track to Detect and Segment: An Online Multi-Object Tracker." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/wu2021cvpr-track/) doi:10.1109/CVPR46437.2021.01217

BibTeX

@inproceedings{wu2021cvpr-track,
  title     = {{Track to Detect and Segment: An Online Multi-Object Tracker}},
  author    = {Wu, Jialian and Cao, Jiale and Song, Liangchen and Wang, Yu and Yang, Ming and Yuan, Junsong},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  pages     = {12352-12361},
  doi       = {10.1109/CVPR46437.2021.01217},
  url       = {https://mlanthology.org/cvpr/2021/wu2021cvpr-track/}
}