HintPose (COCO 2019 Keypoint Detection Task)
ICCV 2019 Joint COCO and Mapillary Workshop (Most innovative award)
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.
홍상훈(카카오브레인), 박헌철(카카오브레인), 박종혁(서울대학교), 조석현(서울대학교), 박희웅(서울대학교)