A Universal Action Space for General Behavior Analysis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911437302005760 |
|---|---|
| author | Chang, Hung-Shuo Yang, Yue-Cheng Chen, Yu-Hsi Chen, Wei-Hsin Wang, Chien-Yao Liao, James C. Chen, Chien-Chang Huang, Hen-Hsen Liao, Hong-Yuan Mark |
| author_facet | Chang, Hung-Shuo Yang, Yue-Cheng Chen, Yu-Hsi Chen, Wei-Hsin Wang, Chien-Yao Liao, James C. Chen, Chien-Chang Huang, Hen-Hsen Liao, Hong-Yuan Mark |
| contents | Analyzing animal and human behavior has long been a challenging task in computer vision. Early approaches from the 1970s to the 1990s relied on hand-crafted edge detection, segmentation, and low-level features such as color, shape, and texture to locate objects and infer their identities-an inherently ill-posed problem. Behavior analysis in this era typically proceeded by tracking identified objects over time and modeling their trajectories using sparse feature points, which further limited robustness and generalization. A major shift occurred with the introduction of ImageNet by Deng and Li in 2010, which enabled large-scale visual recognition through deep neural networks and effectively served as a comprehensive visual dictionary. This development allowed object recognition to move beyond complex low-level processing toward learned high-level representations. In this work, we follow this paradigm to build a large-scale Universal Action Space (UAS) using existing labeled human-action datasets. We then use this UAS as the foundation for analyzing and categorizing mammalian and chimpanzee behavior datasets. The source code is released on GitHub at https://github.com/franktpmvu/Universal-Action-Space. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09518 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Universal Action Space for General Behavior Analysis Chang, Hung-Shuo Yang, Yue-Cheng Chen, Yu-Hsi Chen, Wei-Hsin Wang, Chien-Yao Liao, James C. Chen, Chien-Chang Huang, Hen-Hsen Liao, Hong-Yuan Mark Computer Vision and Pattern Recognition Analyzing animal and human behavior has long been a challenging task in computer vision. Early approaches from the 1970s to the 1990s relied on hand-crafted edge detection, segmentation, and low-level features such as color, shape, and texture to locate objects and infer their identities-an inherently ill-posed problem. Behavior analysis in this era typically proceeded by tracking identified objects over time and modeling their trajectories using sparse feature points, which further limited robustness and generalization. A major shift occurred with the introduction of ImageNet by Deng and Li in 2010, which enabled large-scale visual recognition through deep neural networks and effectively served as a comprehensive visual dictionary. This development allowed object recognition to move beyond complex low-level processing toward learned high-level representations. In this work, we follow this paradigm to build a large-scale Universal Action Space (UAS) using existing labeled human-action datasets. We then use this UAS as the foundation for analyzing and categorizing mammalian and chimpanzee behavior datasets. The source code is released on GitHub at https://github.com/franktpmvu/Universal-Action-Space. |
| title | A Universal Action Space for General Behavior Analysis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.09518 |