2021/07/22 by Chenyu Tian, Tian, Chenyu, Ran Yu +9
Computer Science · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Video Surveillance and Tracking Methods #cs.CV
paper · pdf · doi:10.48550/arxiv.2107.10466
10 pages, 5 figures
openalex publication_date 2021/07/22 · arxiv created 2021/07/27 · arxiv updated 2021/07/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Current methods of multi-person pose estimation typically treat the localization and the association of body joints separately. It is convenient but inefficient, leading to additional computation and a waste of time. This paper, however, presents a novel framework PoseDet (Estimating Pose by Detection) to localize and associate body joints simultaneously at higher inference speed. Moreover, we propose the keypoint-aware pose embedding to represent an object in terms of the locations of its keypoints. The proposed pose embedding contains semantic and geometric information, allowing us to access discriminative and informative features efficiently. It is utilized for candidate classification and body joint localization in PoseDet, leading to robust predictions of various poses. This simple framework achieves an unprecedented speed and a competitive accuracy on the COCO benchmark compared with state-of-the-art methods. Extensive experiments on the CrowdPose benchmark show the robustness in the crowd scenes. Source code is available.