Rethinking the Competition Between Detection and ReID in Multiobject Tracking
University of Electronic Science and Technology of China · Chinese Academy of Sciences · +4 more institutions
Abstract
Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm. This leads to inferior performance compared with existing two-stage methods. In this paper, we first dissect the reasoning process for these two tasks, which reveals that the competition between them inevitably would destroy task-dependent representations learning. To tackle this problem, we propose a novel reciprocal network (REN) with a…
Citation impact
- FWCI
- 29.65
- Percentile
- 100%
- References
- 59
Authors
6- CLChao LiangCorresponding
University of Electronic Science and Technology of China
- ZZZhipeng Zhang
Chinese Academy of Sciences, Institute of Automation, University of Chinese Academy of Sciences
- XZXue Zhou
University of Electronic Science and Technology of China, Yibin University
- BLBing Li
Chinese Academy of Sciences, Institute of Automation, University of Chinese Academy of Sciences
- SZShuyuan Zhu
University of Electronic Science and Technology of China
Topics & keywords
- Computer science
- Reciprocal
- Construct (python library)
- Artificial intelligence
- Task (project management)
- Identification (biology)
- Relation (database)
- Object detection