Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2403.01543 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911315830767616 |
|---|---|
| author | Ma, Xiaoxuan Li, Zishi Shang, Qiuyan Zhu, Wentao Ci, Hai Qiao, Yu Wang, Yizhou |
| author_facet | Ma, Xiaoxuan Li, Zishi Shang, Qiuyan Zhu, Wentao Ci, Hai Qiao, Yu Wang, Yizhou |
| contents | Temporal repetition counting aims to quantify the repeated action cycles within a video. The majority of existing methods rely on the similarity correlation matrix to characterize the repetitiveness of actions, but their scalability is hindered due to the quadratic computational complexity. In this work, we introduce a novel approach that employs an action query representation to localize repeated action cycles with linear computational complexity. Based on this representation, we further develop two key components to tackle the essential challenges of temporal repetition counting. Firstly, to facilitate open-set action counting, we propose the dynamic update scheme on action queries. Unlike static action queries, this approach dynamically embeds video features into action queries, offering a more flexible and generalizable representation. Secondly, to distinguish between actions of interest and background noise actions, we incorporate inter-query contrastive learning to regularize the video representations corresponding to different action queries. As a result, our method significantly outperforms previous works, particularly in terms of long video sequences, unseen actions, and actions at various speeds. On the challenging RepCountA benchmark, we outperform the state-of-the-art method TransRAC by 26.5% in OBO accuracy, with a 22.7% mean error decrease and 94.1% computational burden reduction. Code is available at https://github.com/lizishi/DeTRC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01543 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Action Counting with Dynamic Queries Ma, Xiaoxuan Li, Zishi Shang, Qiuyan Zhu, Wentao Ci, Hai Qiao, Yu Wang, Yizhou Computer Vision and Pattern Recognition Temporal repetition counting aims to quantify the repeated action cycles within a video. The majority of existing methods rely on the similarity correlation matrix to characterize the repetitiveness of actions, but their scalability is hindered due to the quadratic computational complexity. In this work, we introduce a novel approach that employs an action query representation to localize repeated action cycles with linear computational complexity. Based on this representation, we further develop two key components to tackle the essential challenges of temporal repetition counting. Firstly, to facilitate open-set action counting, we propose the dynamic update scheme on action queries. Unlike static action queries, this approach dynamically embeds video features into action queries, offering a more flexible and generalizable representation. Secondly, to distinguish between actions of interest and background noise actions, we incorporate inter-query contrastive learning to regularize the video representations corresponding to different action queries. As a result, our method significantly outperforms previous works, particularly in terms of long video sequences, unseen actions, and actions at various speeds. On the challenging RepCountA benchmark, we outperform the state-of-the-art method TransRAC by 26.5% in OBO accuracy, with a 22.7% mean error decrease and 94.1% computational burden reduction. Code is available at https://github.com/lizishi/DeTRC. |
| title | Efficient Action Counting with Dynamic Queries |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.01543 |