BoIR: box-supervised instance representation for multi-person pose estimation
- Title
- BoIR: box-supervised instance representation for multi-person pose estimation
- Authors
- Jeong, Uyoung; Baek, Seungryul; Chang, Hyung Jin; KIM, KWANG IN
- Date Issued
- 2023-11-23
- Publisher
- The British Machine Vision Association
- Abstract
- Single-stage multi-person human pose estimation (MPPE) methods have shown great performance improvements, but existing methods fail to disentangle features by individual instances under crowded scenes. In this paper, we propose a bounding box-level instance representation learning called BoIR, which simultaneously solves instance detection, instance disentanglement, and instance-keypoint association problems. Our new instance embedding loss provides a learning signal on the entire area of the image with bounding box annotations, achieving globally consistent and disentangled instance representation. Our method exploits multi-task learning of bottom-up keypoint estimation, bounding box regression, and contrastive instance embedding learning, without additional computational cost during inference. BoIR is effective for crowded scenes, outperforming state-of-the-art on COCO val (0.8 AP), COCO test-dev (0.5 AP), CrowdPose (4.9 AP), and OCHuman (3.5 AP). Code will be available at https://github.com/uyoung-jeong/BoIR
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/119654
- Article Type
- Conference
- Citation
- British Machine Vision Conference, 2023-11-23
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.