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.
@article{arxiv.2103.08808,
title = {Track to Detect and Segment: An Online Multi-Object Tracker},
author = {Jialian Wu and Jiale Cao and Liangchen Song and Yu Wang and Ming Yang and Junsong Yuan},
journal= {arXiv preprint arXiv:2103.08808},
year = {2021}
}