2020/03/04 by Sanghoon Hong, Hong, Sanghoon, Hunchul Park +7
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.2003.02170
Presented at "Joint COCO and Mapillary Workshop at ICCV 2019: Keypoint Detection Challenge Track"
arxiv created 2020/03/04 · openalex publication_date 2020/03/04 · arxiv updated 2020/03/05 · openalex created_date 2024/04/11 · openalex updated_date 2026/07/28
Most of the top-down pose estimation models assume that there exists only one person in a bounding box. However, the assumption is not always correct. In this technical report, we introduce two ideas, instance cue and recurrent refinement, to an existing pose estimator so that the model is able to handle detection boxes with multiple persons properly. When we evaluated our model on the COCO17 keypoints dataset, it showed non-negligible improvement compared to its baseline model. Our model achieved 76.2 mAP as a single model and 77.3 mAP as an ensemble on the test-dev set without additional training data. After additional post-processing with a separate refinement network, our final predictions achieved 77.8 mAP on the COCO test-dev set.