paper-with-me

홈 › Papers

Multi-Focus Temporal Shifting for Precise Event Spotting in Sports Videos

2025-07-10 · Hao Xu, Xinyu Wei, Sam Wells, Sunil Aryal arxiv

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).

📄 PDF Abstract BibTeX arXiv:2507.07381

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Improving Shared Argument Identification in Japanese Event Knowledge Acquisition

2017-08-01 · WS 2017 8 · Yin Jou Huang, Sadao Kurohashi

Event knowledge represents the knowledge of causal and temporal relations between events. Shared arguments of event knowledge encode patterns of role shifting in successive events. A two-stage framework was proposed for …

Coreference ResolutionText Generation

Mind the Time: Temporally-Controlled Multi-Event Video Generation

2024-12-06 · CVPR 2025 1 · Ziyi Wu, Aliaksandr Siarohin, Willi Menapace, Ivan Skorokhodov 외

Real-world videos consist of sequences of events. Generating such sequences with precise temporal control is infeasible with existing video generators that rely on a single paragraph of text as input. When tasked with ge…

Video Generation

Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting

2026-03-09 · Azul Garza, Renée Rosillo, Rodrigo Mendoza-Smith, David Salinas 외 arxiv

Recent advances in time-series forecasting increasingly rely on pre-trained foundation-style models. While these models often claim broad generalization, existing evaluation protocols provide limited evidence. Indeed, mo…

Time Series Forecasting

Retrieval and Distill: A Temporal Data Shift-Free Paradigm for Online Recommendation System

2024-04-24 · Lei Zheng, Ning li, Weinan Zhang, Yong Yu

Current recommendation systems are significantly affected by a serious issue of temporal data shift, which is the inconsistency between the distribution of historical data and that of online data. Most existing models fo…

Recommendation SystemsRetrieval

When and Where do Events Switch in Multi-Event Video Generation?

2025-10-03 · Ruotong Liao, Guowen Huang, Qing Cheng, Thomas Seidl 외 arxiv

Text-to-video (T2V) generation has surged in response to challenging questions, especially when a long video must depict multiple sequential events with temporal coherence and controllable content. Existing methods that …

Video Generation