Publication Date: 6/14/2020
Event: CVPR 2020
Reference: pp. 6737-6747, 2020
Authors: Michael Snower, NEC Laboratories America, Inc., Brown University; Asim Kadav, NEC Laboratories America, Inc.; Farley Lai, NEC Laboratories America, Inc.; Hans Peter Graf, NEC Laboratories America, Inc.
Abstract: Pose-tracking is an important problem that requires identifying unique human pose-instances and matching them temporally across different frames in a video. However, existing pose-tracking methods are unable to accurately model temporal relationships and require significant computation, often computing the tracks offline. We present an efficient multi-person pose-tracking method, KeyTrack that only relies on keypoint information without using any RGB or optical flow to locate and track human keypoints in real-time. KeyTrack is a top-down approach that learns spatio-temporal pose relationships by modeling the multi-person pose-tracking problem as a novel Pose Entailment task using a Transformer based architecture. Furthermore, KeyTrack uses a novel, parameter-free, keypoint refinement technique that improves the keypoint estimates used by the Transformers. We achieve state-of-the-art results on PoseTrack’17 and PoseTrack’18 benchmarks while using only a fraction of the computation used by most other methods for computing the tracking information.
Publication Link: https://ieeexplore.ieee.org/document/9157545