SFGANS Self-supervised Future Generator for human ActioN Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916078209204224 |
|---|---|
| author | Berman, Or Goldbraikh, Adam Laufer, Shlomi |
| author_facet | Berman, Or Goldbraikh, Adam Laufer, Shlomi |
| contents | The ability to locate and classify action segments in long untrimmed video is of particular interest to many applications such as autonomous cars, robotics and healthcare applications. Today, the most popular pipeline for action segmentation is composed of encoding the frames into feature vectors, which are then processed by a temporal model for segmentation. In this paper we present a self-supervised method that comes in the middle of the standard pipeline and generated refined representations of the original feature vectors. Experiments show that this method improves the performance of existing models on different sub-tasks of action segmentation, even without additional hyper parameter tuning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_00438 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | SFGANS Self-supervised Future Generator for human ActioN Segmentation Berman, Or Goldbraikh, Adam Laufer, Shlomi Computer Vision and Pattern Recognition The ability to locate and classify action segments in long untrimmed video is of particular interest to many applications such as autonomous cars, robotics and healthcare applications. Today, the most popular pipeline for action segmentation is composed of encoding the frames into feature vectors, which are then processed by a temporal model for segmentation. In this paper we present a self-supervised method that comes in the middle of the standard pipeline and generated refined representations of the original feature vectors. Experiments show that this method improves the performance of existing models on different sub-tasks of action segmentation, even without additional hyper parameter tuning. |
| title | SFGANS Self-supervised Future Generator for human ActioN Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.00438 |