TechRxiv
wacv.pdf (8.35 MB)

Conditional Link Prediction of Category-Implicit Keypoint Detection

Download (8.35 MB)
preprint
posted on 10.11.2020, 20:53 by Ellen Yi-Ge, Rui Fan, Zechun Liu, Zhiqiang Shen
Keypoints of objects reflect their concise abstractions, while the corresponding connection links (CL) build the skeleton by detecting the intrinsic relations between keypoints. Existing approaches are typically computationally-intensive, inapplicable for instances belonging to multiple classes, and/or infeasible to simultaneously encode connection information. To address the aforementioned issues, we propose an end-to-end category-implicit Keypoint and Link Prediction Network (KLPNet), which is the first approach for simultaneous semantic keypoint detection (for multi-class instances) and CL rejuvenation. In our KLPNet, a novel Conditional Link Prediction Graph is proposed for link prediction among keypoints that are contingent on a predefined category. Furthermore, a Cross-stage Keypoint Localization Module (CKLM) is introduced to explore feature aggregation for coarse-to-fine keypoint localization. Comprehensive experiments conducted on three publicly available benchmarks demonstrate that our KLPNet consistently outperforms all other state-of-the-art approaches. Furthermore, the experimental results of CL prediction also show the effectiveness of our KLPNet with respect to occlusion problems.

History

Email Address of Submitting Author

ranger_fan@outlook.com

ORCID of Submitting Author

0000-0003-2593-6596

Submitting Author's Institution

UC San Diego

Submitting Author's Country

United States of America

Licence

Exports

Licence

Exports