PBADet: A One-Stage Anchor-Free Approach for Part-Body Association
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913231717531648 |
|---|---|
| author | Gao, Zhongpai Zhou, Huayi Sharma, Abhishek Zheng, Meng Planche, Benjamin Chen, Terrence Wu, Ziyan |
| author_facet | Gao, Zhongpai Zhou, Huayi Sharma, Abhishek Zheng, Meng Planche, Benjamin Chen, Terrence Wu, Ziyan |
| contents | The detection of human parts (e.g., hands, face) and their correct association with individuals is an essential task, e.g., for ubiquitous human-machine interfaces and action recognition. Traditional methods often employ multi-stage processes, rely on cumbersome anchor-based systems, or do not scale well to larger part sets. This paper presents PBADet, a novel one-stage, anchor-free approach for part-body association detection. Building upon the anchor-free object representation across multi-scale feature maps, we introduce a singular part-to-body center offset that effectively encapsulates the relationship between parts and their parent bodies. Our design is inherently versatile and capable of managing multiple parts-to-body associations without compromising on detection accuracy or robustness. Comprehensive experiments on various datasets underscore the efficacy of our approach, which not only outperforms existing state-of-the-art techniques but also offers a more streamlined and efficient solution to the part-body association challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07814 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PBADet: A One-Stage Anchor-Free Approach for Part-Body Association Gao, Zhongpai Zhou, Huayi Sharma, Abhishek Zheng, Meng Planche, Benjamin Chen, Terrence Wu, Ziyan Computer Vision and Pattern Recognition Artificial Intelligence The detection of human parts (e.g., hands, face) and their correct association with individuals is an essential task, e.g., for ubiquitous human-machine interfaces and action recognition. Traditional methods often employ multi-stage processes, rely on cumbersome anchor-based systems, or do not scale well to larger part sets. This paper presents PBADet, a novel one-stage, anchor-free approach for part-body association detection. Building upon the anchor-free object representation across multi-scale feature maps, we introduce a singular part-to-body center offset that effectively encapsulates the relationship between parts and their parent bodies. Our design is inherently versatile and capable of managing multiple parts-to-body associations without compromising on detection accuracy or robustness. Comprehensive experiments on various datasets underscore the efficacy of our approach, which not only outperforms existing state-of-the-art techniques but also offers a more streamlined and efficient solution to the part-body association challenge. |
| title | PBADet: A One-Stage Anchor-Free Approach for Part-Body Association |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2402.07814 |