Open-Vocabulary Action Localization with Iterative Visual Prompting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912312355454976 |
|---|---|
| author | Wake, Naoki Kanehira, Atsushi Sasabuchi, Kazuhiro Takamatsu, Jun Ikeuchi, Katsushi |
| author_facet | Wake, Naoki Kanehira, Atsushi Sasabuchi, Kazuhiro Takamatsu, Jun Ikeuchi, Katsushi |
| contents | Video action localization aims to find the timings of specific actions from a long video. Although existing learning-based approaches have been successful, they require annotating videos, which comes with a considerable labor cost. This paper proposes a training-free, open-vocabulary approach based on emerging off-the-shelf vision-language models (VLMs). The challenge stems from the fact that VLMs are neither designed to process long videos nor tailored for finding actions. We overcome these problems by extending an iterative visual prompting technique. Specifically, we sample video frames and create a concatenated image with frame index labels, allowing a VLM to identify the frames that most likely correspond to the start and end of the action. By iteratively narrowing the sampling window around the selected frames, the estimation gradually converges to more precise temporal boundaries. We demonstrate that this technique yields reasonable performance, achieving results comparable to state-of-the-art zero-shot action localization. These results support the use of VLMs as a practical tool for understanding videos. Sample code is available at https://microsoft.github.io/VLM-Video-Action-Localization/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_17422 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Open-Vocabulary Action Localization with Iterative Visual Prompting Wake, Naoki Kanehira, Atsushi Sasabuchi, Kazuhiro Takamatsu, Jun Ikeuchi, Katsushi Computer Vision and Pattern Recognition Artificial Intelligence Robotics Video action localization aims to find the timings of specific actions from a long video. Although existing learning-based approaches have been successful, they require annotating videos, which comes with a considerable labor cost. This paper proposes a training-free, open-vocabulary approach based on emerging off-the-shelf vision-language models (VLMs). The challenge stems from the fact that VLMs are neither designed to process long videos nor tailored for finding actions. We overcome these problems by extending an iterative visual prompting technique. Specifically, we sample video frames and create a concatenated image with frame index labels, allowing a VLM to identify the frames that most likely correspond to the start and end of the action. By iteratively narrowing the sampling window around the selected frames, the estimation gradually converges to more precise temporal boundaries. We demonstrate that this technique yields reasonable performance, achieving results comparable to state-of-the-art zero-shot action localization. These results support the use of VLMs as a practical tool for understanding videos. Sample code is available at https://microsoft.github.io/VLM-Video-Action-Localization/ |
| title | Open-Vocabulary Action Localization with Iterative Visual Prompting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2408.17422 |