Classification Matters: Improving Video Action Detection with Class-Specific Attention
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_ | 1866917772660834304 |
|---|---|
| author | Lee, Jinsung Kim, Taeoh Lee, Inwoong Shim, Minho Wee, Dongyoon Cho, Minsu Kwak, Suha |
| author_facet | Lee, Jinsung Kim, Taeoh Lee, Inwoong Shim, Minho Wee, Dongyoon Cho, Minsu Kwak, Suha |
| contents | Video action detection (VAD) aims to detect actors and classify their actions in a video. We figure that VAD suffers more from classification rather than localization of actors. Hence, we analyze how prevailing methods form features for classification and find that they prioritize actor regions, yet often overlooking the essential contextual information necessary for accurate classification. Accordingly, we propose to reduce the bias toward actor and encourage paying attention to the context that is relevant to each action class. By assigning a class-dedicated query to each action class, our model can dynamically determine where to focus for effective classification. The proposed model demonstrates superior performance on three challenging benchmarks with significantly fewer parameters and less computation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_19698 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Classification Matters: Improving Video Action Detection with Class-Specific Attention Lee, Jinsung Kim, Taeoh Lee, Inwoong Shim, Minho Wee, Dongyoon Cho, Minsu Kwak, Suha Computer Vision and Pattern Recognition Video action detection (VAD) aims to detect actors and classify their actions in a video. We figure that VAD suffers more from classification rather than localization of actors. Hence, we analyze how prevailing methods form features for classification and find that they prioritize actor regions, yet often overlooking the essential contextual information necessary for accurate classification. Accordingly, we propose to reduce the bias toward actor and encourage paying attention to the context that is relevant to each action class. By assigning a class-dedicated query to each action class, our model can dynamically determine where to focus for effective classification. The proposed model demonstrates superior performance on three challenging benchmarks with significantly fewer parameters and less computation. |
| title | Classification Matters: Improving Video Action Detection with Class-Specific Attention |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.19698 |