BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin
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_ | 1866913262158741504 |
|---|---|
| author | Fang, Qihang Tang, Chengcheng Ma, Shugao Yang, Yanchao |
| author_facet | Fang, Qihang Tang, Chengcheng Ma, Shugao Yang, Yanchao |
| contents | Skeleton-based motion representations are robust for action localization and understanding for their invariance to perspective, lighting, and occlusion, compared with images. Yet, they are often ambiguous and incomplete when taken out of context, even for human annotators. As infants discern gestures before associating them with words, actions can be conceptualized before being grounded with labels. Therefore, we propose the first unsupervised pre-training framework, Boundary-Interior Decoding (BID), that partitions a skeleton-based motion sequence into discovered semantically meaningful pre-action segments. By fine-tuning our pre-training network with a small number of annotated data, we show results out-performing SOTA methods by a large margin. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07354 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin Fang, Qihang Tang, Chengcheng Ma, Shugao Yang, Yanchao Computer Vision and Pattern Recognition 68T45 I.4.8 Skeleton-based motion representations are robust for action localization and understanding for their invariance to perspective, lighting, and occlusion, compared with images. Yet, they are often ambiguous and incomplete when taken out of context, even for human annotators. As infants discern gestures before associating them with words, actions can be conceptualized before being grounded with labels. Therefore, we propose the first unsupervised pre-training framework, Boundary-Interior Decoding (BID), that partitions a skeleton-based motion sequence into discovered semantically meaningful pre-action segments. By fine-tuning our pre-training network with a small number of annotated data, we show results out-performing SOTA methods by a large margin. |
| title | BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin |
| topic | Computer Vision and Pattern Recognition 68T45 I.4.8 |
| url | https://arxiv.org/abs/2403.07354 |