Details for entry KeyTrack

Short Name:
KeyTrack
Long Name:
15 Keypoints Is All You Need
Use MPII Pose for training:
no
Use COCO for training:
yes
Use external training:
no
Use multiple frames for pose estimation:
yes
Predict pose tracks:
yes
URL:
https://arxiv.org/abs/1912.02323
Description:
Pose tracking is an important problem that requires identifying unique human pose-instances and matching them temporally across different frames of 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 information to track human keypoints in real-time. Keypoints are tracked using our Pose Entailment method, in which, first, a pair of pose estimates is sampled from different frames in a video and tokenized. Then, a Transformer-based network makes a binary classification as to whether one pose temporally follows another. Furthermore, we improve our top-down pose estimation method with a novel, parameter-free, keypoint refinement technique that improves the keypoint estimates used during the Pose Entailment step. We achieve state-of-the-art results on the PoseTrack'17 and the PoseTrack'18 benchmarks while using only a fraction of the computation required by most other methods for computing the tracking information.
Bibtex:
Specs:
NVIDIA GTX 1080Ti
Runtime:
1
Open Source:
no
Number of submissions:
2
Last Submission:
2019-11-21 19:23:59
Published:
2019-11-21 20:35:55

Imprint | Data Protection


© PoseTrack