Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zhaoyu, Jiang, Kan, Ma, Murong, Hou, Zhe, Lin, Yun, Dong, Jin Song
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908662020177920
author Liu, Zhaoyu
Jiang, Kan
Ma, Murong
Hou, Zhe
Lin, Yun
Dong, Jin Song
author_facet Liu, Zhaoyu
Jiang, Kan
Ma, Murong
Hou, Zhe
Lin, Yun
Dong, Jin Song
contents Precise event spotting (PES) aims to recognize fine-grained events at exact moments and has become a key component of sports analytics. This task is particularly challenging due to rapid succession, motion blur, and subtle visual differences. Consequently, most existing methods rely on domain-specific, end-to-end training with large labeled datasets and often struggle in few-shot conditions due to their dependence on pixel- or pose-based inputs alone. However, obtaining large labeled datasets is practically hard. We propose a Unified Multi-Entity Graph Network (UMEG-Net) for few-shot PES. UMEG-Net integrates human skeletons and sport-specific object keypoints into a unified graph and features an efficient spatio-temporal extraction module based on advanced GCN and multi-scale temporal shift. To further enhance performance, we employ multimodal distillation to transfer knowledge from keypoint-based graphs to visual representations. Our approach achieves robust performance with limited labeled data and significantly outperforms baseline models in few-shot settings, providing a scalable and effective solution for few-shot PES. Code is publicly available at https://github.com/LZYAndy/UMEG-Net.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14186
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation
Liu, Zhaoyu
Jiang, Kan
Ma, Murong
Hou, Zhe
Lin, Yun
Dong, Jin Song
Computer Vision and Pattern Recognition
Artificial Intelligence
Precise event spotting (PES) aims to recognize fine-grained events at exact moments and has become a key component of sports analytics. This task is particularly challenging due to rapid succession, motion blur, and subtle visual differences. Consequently, most existing methods rely on domain-specific, end-to-end training with large labeled datasets and often struggle in few-shot conditions due to their dependence on pixel- or pose-based inputs alone. However, obtaining large labeled datasets is practically hard. We propose a Unified Multi-Entity Graph Network (UMEG-Net) for few-shot PES. UMEG-Net integrates human skeletons and sport-specific object keypoints into a unified graph and features an efficient spatio-temporal extraction module based on advanced GCN and multi-scale temporal shift. To further enhance performance, we employ multimodal distillation to transfer knowledge from keypoint-based graphs to visual representations. Our approach achieves robust performance with limited labeled data and significantly outperforms baseline models in few-shot settings, providing a scalable and effective solution for few-shot PES. Code is publicly available at https://github.com/LZYAndy/UMEG-Net.
title Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.14186