Prototype Learning for Micro-gesture Classification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910557692493824 |
|---|---|
| author | Chen, Guoliang Wang, Fei Li, Kun Wu, Zhiliang Fan, Hehe Yang, Yi Wang, Meng Guo, Dan |
| author_facet | Chen, Guoliang Wang, Fei Li, Kun Wu, Zhiliang Fan, Hehe Yang, Yi Wang, Meng Guo, Dan |
| contents | In this paper, we briefly introduce the solution developed by our team, HFUT-VUT, for the track of Micro-gesture Classification in the MiGA challenge at IJCAI 2024. The task of micro-gesture classification task involves recognizing the category of a given video clip, which focuses on more fine-grained and subtle body movements compared to typical action recognition tasks. Given the inherent complexity of micro-gesture recognition, which includes large intra-class variability and minimal inter-class differences, we utilize two innovative modules, i.e., the cross-modal fusion module and prototypical refinement module, to improve the discriminative ability of MG features, thereby improving the classification accuracy. Our solution achieved significant success, ranking 1st in the track of Micro-gesture Classification. We surpassed the performance of last year's leading team by a substantial margin, improving Top-1 accuracy by 6.13%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_03097 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prototype Learning for Micro-gesture Classification Chen, Guoliang Wang, Fei Li, Kun Wu, Zhiliang Fan, Hehe Yang, Yi Wang, Meng Guo, Dan Computer Vision and Pattern Recognition In this paper, we briefly introduce the solution developed by our team, HFUT-VUT, for the track of Micro-gesture Classification in the MiGA challenge at IJCAI 2024. The task of micro-gesture classification task involves recognizing the category of a given video clip, which focuses on more fine-grained and subtle body movements compared to typical action recognition tasks. Given the inherent complexity of micro-gesture recognition, which includes large intra-class variability and minimal inter-class differences, we utilize two innovative modules, i.e., the cross-modal fusion module and prototypical refinement module, to improve the discriminative ability of MG features, thereby improving the classification accuracy. Our solution achieved significant success, ranking 1st in the track of Micro-gesture Classification. We surpassed the performance of last year's leading team by a substantial margin, improving Top-1 accuracy by 6.13%. |
| title | Prototype Learning for Micro-gesture Classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.03097 |