Semi-Supervised Audio-Visual Video Action Recognition with Audio Source Localization Guided Mixup
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912257736179712 |
|---|---|
| author | Kang, Seokun Kim, Taehwan |
| author_facet | Kang, Seokun Kim, Taehwan |
| contents | Video action recognition is a challenging but important task for understanding and discovering what the video does. However, acquiring annotations for a video is costly, and semi-supervised learning (SSL) has been studied to improve performance even with a small number of labeled data in the task. Prior studies for semi-supervised video action recognition have mostly focused on using single modality - visuals - but the video is multi-modal, so utilizing both visuals and audio would be desirable and improve performance further, which has not been explored well. Therefore, we propose audio-visual SSL for video action recognition, which uses both visual and audio together, even with quite a few labeled data, which is challenging. In addition, to maximize the information of audio and video, we propose a novel audio source localization-guided mixup method that considers inter-modal relations between video and audio modalities. In experiments on UCF-51, Kinetics-400, and VGGSound datasets, our model shows the superior performance of the proposed semi-supervised audio-visual action recognition framework and audio source localization-guided mixup. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02284 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Semi-Supervised Audio-Visual Video Action Recognition with Audio Source Localization Guided Mixup Kang, Seokun Kim, Taehwan Computer Vision and Pattern Recognition Artificial Intelligence Video action recognition is a challenging but important task for understanding and discovering what the video does. However, acquiring annotations for a video is costly, and semi-supervised learning (SSL) has been studied to improve performance even with a small number of labeled data in the task. Prior studies for semi-supervised video action recognition have mostly focused on using single modality - visuals - but the video is multi-modal, so utilizing both visuals and audio would be desirable and improve performance further, which has not been explored well. Therefore, we propose audio-visual SSL for video action recognition, which uses both visual and audio together, even with quite a few labeled data, which is challenging. In addition, to maximize the information of audio and video, we propose a novel audio source localization-guided mixup method that considers inter-modal relations between video and audio modalities. In experiments on UCF-51, Kinetics-400, and VGGSound datasets, our model shows the superior performance of the proposed semi-supervised audio-visual action recognition framework and audio source localization-guided mixup. |
| title | Semi-Supervised Audio-Visual Video Action Recognition with Audio Source Localization Guided Mixup |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.02284 |