Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.07381 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914179248553984 |
|---|---|
| author | Xu, Hao Wei, Xinyu Wells, Sam Aryal, Sunil |
| author_facet | Xu, Hao Wei, Xinyu Wells, Sam Aryal, Sunil |
| contents | Precise Event Spotting (PES) in sports videos requires frame-level recognition of fine-grained actions from single-camera footage. Existing PES models typically incorporate lightweight temporal modules such as the Gate Shift Module (GSM) or the Gate Shift Fuse to enrich 2D CNN feature extractors with temporal context. However, these modules are limited in both temporal receptive field and spatial adaptability. We propose Multi-Focus Temporal Shifting Module (MFS) that enhances GSM with multi-scale temporal shifts and Group Focus Module, enabling efficient modeling of both short and long-term dependencies while focusing on salient regions. MFS is a lightweight, plug-and-play module that integrates seamlessly with diverse 2D backbones. To further advance the field, we introduce the Table Tennis Australia dataset, the first PES benchmark for table tennis containing over 4,800 precisely annotated events. Extensive experiments across five PES benchmarks demonstrate that MFS consistently improves performance with minimal overhead, achieving leading results among lightweight methods (+4.09 mAP, 45 GFLOPs). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07381 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Focus Temporal Shifting for Precise Event Spotting in Sports Videos Xu, Hao Wei, Xinyu Wells, Sam Aryal, Sunil Computer Vision and Pattern Recognition Precise Event Spotting (PES) in sports videos requires frame-level recognition of fine-grained actions from single-camera footage. Existing PES models typically incorporate lightweight temporal modules such as the Gate Shift Module (GSM) or the Gate Shift Fuse to enrich 2D CNN feature extractors with temporal context. However, these modules are limited in both temporal receptive field and spatial adaptability. We propose Multi-Focus Temporal Shifting Module (MFS) that enhances GSM with multi-scale temporal shifts and Group Focus Module, enabling efficient modeling of both short and long-term dependencies while focusing on salient regions. MFS is a lightweight, plug-and-play module that integrates seamlessly with diverse 2D backbones. To further advance the field, we introduce the Table Tennis Australia dataset, the first PES benchmark for table tennis containing over 4,800 precisely annotated events. Extensive experiments across five PES benchmarks demonstrate that MFS consistently improves performance with minimal overhead, achieving leading results among lightweight methods (+4.09 mAP, 45 GFLOPs). |
| title | Multi-Focus Temporal Shifting for Precise Event Spotting in Sports Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.07381 |