Category Query Learning for Human-Object Interaction Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912416245219328 |
|---|---|
| author | Xie, Chi Zeng, Fangao Hu, Yue Liang, Shuang Wei, Yichen |
| author_facet | Xie, Chi Zeng, Fangao Hu, Yue Liang, Shuang Wei, Yichen |
| contents | Unlike most previous HOI methods that focus on learning better human-object features, we propose a novel and complementary approach called category query learning. Such queries are explicitly associated to interaction categories, converted to image specific category representation via a transformer decoder, and learnt via an auxiliary image-level classification task. This idea is motivated by an earlier multi-label image classification method, but is for the first time applied for the challenging human-object interaction classification task. Our method is simple, general and effective. It is validated on three representative HOI baselines and achieves new state-of-the-art results on two benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_14005 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Category Query Learning for Human-Object Interaction Classification Xie, Chi Zeng, Fangao Hu, Yue Liang, Shuang Wei, Yichen Computer Vision and Pattern Recognition Artificial Intelligence Unlike most previous HOI methods that focus on learning better human-object features, we propose a novel and complementary approach called category query learning. Such queries are explicitly associated to interaction categories, converted to image specific category representation via a transformer decoder, and learnt via an auxiliary image-level classification task. This idea is motivated by an earlier multi-label image classification method, but is for the first time applied for the challenging human-object interaction classification task. Our method is simple, general and effective. It is validated on three representative HOI baselines and achieves new state-of-the-art results on two benchmarks. |
| title | Category Query Learning for Human-Object Interaction Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2303.14005 |