MoExDA: Domain Adaptation for Edge-based Action Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908478742724608 |
|---|---|
| author | Sugimoto, Takuya Ding, Ning Tamaki, Toru |
| author_facet | Sugimoto, Takuya Ding, Ning Tamaki, Toru |
| contents | Modern action recognition models suffer from static bias, leading to reduced generalization performance. In this paper, we propose MoExDA, a lightweight domain adaptation between RGB and edge information using edge frames in addition to RGB frames to counter the static bias issue. Experiments demonstrate that the proposed method effectively suppresses static bias with a lower computational cost, allowing for more robust action recognition than previous approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02981 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MoExDA: Domain Adaptation for Edge-based Action Recognition Sugimoto, Takuya Ding, Ning Tamaki, Toru Computer Vision and Pattern Recognition Modern action recognition models suffer from static bias, leading to reduced generalization performance. In this paper, we propose MoExDA, a lightweight domain adaptation between RGB and edge information using edge frames in addition to RGB frames to counter the static bias issue. Experiments demonstrate that the proposed method effectively suppresses static bias with a lower computational cost, allowing for more robust action recognition than previous approaches. |
| title | MoExDA: Domain Adaptation for Edge-based Action Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.02981 |