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

• URL: http://arxiv.org/abs/2511.14186v1
• Date: Tue, 18 Nov 2025 06:45:42 GMT
• Title: Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation
• Abstract summary: Event spotting is a key component of sports analytics.<n>Current methods rely on domain-specific, end-to-end training with large labeled datasets.<n>We propose a Unified Multi-Entity Graph Network (UMEG-Net) for few-shot PES.
• Score: 15.108898002423734
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras [40.06828305096689]
  We introduce the first event matching model that achieves cross-dataset wide-baseline correspondence in a zero-shot manner.<n>We introduce a motion-robust and computationally efficient attention backbone that learns multi-timescale features from event streams.<n>Our framework achieves a 37.7% improvement over the previous best event feature matching methods.
  arXiv  Detail & Related papers  (2026-04-20T18:48:53Z)
• Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation [64.23194519770897]
  We build a comprehensive RL-ready visual reasoning dataset from 46 data sources across 8 dimensions.<n>We propose an influence function based data selection and difficulty based filtering strategy to identify high-quality training samples from this dataset.<n>We train the VLM, referred to as Vision-G1, using multi-round RL with a data curriculum to iteratively improve its visual reasoning capabilities.
  arXiv  Detail & Related papers  (2025-08-18T07:24:33Z)
• Particle Trajectory Representation Learning with Masked Point Modeling [0.0]
  Liquid Argon Time Projection Chambers (LArTPCs) provide high-resolution 3D imaging for fundamental physics.<n>We introduce the Point-based Liquid Argon Masked Autoencoder (PoLAr-MAE), applying masked point modeling to unlabeled LArTPC images.<n>We show this SSL approach learns physically meaningful trajectory representations directly from data.
  arXiv  Detail & Related papers  (2025-02-04T18:31:56Z)
• Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph [4.075741925017479]
  Group Activity Recognition aims to understand collective activities from videos.<n>Existing solutions rely on the RGB modality, which encounters challenges such as background variations.<n>We design a panoramic graph that incorporates multi-person skeletons and objects to encapsulate group activity.
  arXiv  Detail & Related papers  (2024-07-28T13:57:03Z)
• GraphFM: A Scalable Framework for Multi-Graph Pretraining [2.882104808886318]
  We introduce a scalable multi-graph multi-task pretraining approach specifically tailored for node classification tasks across diverse graph datasets from different domains. We demonstrate the efficacy of our approach by training a model on 152 different graph datasets comprising over 7.4 million nodes and 189 million edges. Our results show that pretraining on a diverse array of real and synthetic graphs improves the model's adaptability and stability, while performing competitively with state-of-the-art specialist models.
  arXiv  Detail & Related papers  (2024-07-16T16:51:43Z)
• Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking [61.69892497726235]
  Composite Node Message Passing Network (CoNo-Link) is a framework for modeling ultra-long frames information for association. In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction. Our model can learn better predictions on longer-time scales by adding composite nodes.
  arXiv  Detail & Related papers  (2023-12-14T14:00:30Z)
• Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking [55.13878429987136]
  We propose a simple yet effective two-stage feature learning paradigm to jointly learn single-shot and multi-shot features for different targets. Our method has achieved significant improvements on MOT17 and MOT20 datasets while reaching state-of-the-art performance on DanceTrack dataset.
  arXiv  Detail & Related papers  (2023-11-17T08:17:49Z)
• ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking [11.619493960418176]
  Multi-Camera Multi-Object Tracking (MC-MOT) utilizes information from multiple views to better handle problems with occlusion and crowded scenes. Current graph-based methods do not effectively utilize information regarding spatial and temporal consistency. We propose a novel reconfigurable graph model that first associates all detected objects across cameras spatially before reconfiguring it into a temporal graph.
  arXiv  Detail & Related papers  (2023-08-25T08:02:04Z)
• A Dynamic Graph CNN with Cross-Representation Distillation for Event-Based Recognition [21.225945234873745]
  We present a new event-based graph learning framework called graph cross-representation distillation (CRD) CRD provides additional supervision and prior knowledge for the event graph. Our model and learning framework are effective and generalize well across multiple vision tasks.
  arXiv  Detail & Related papers  (2023-02-08T16:35:39Z)
• Multi-Environment Pretraining Enables Transfer to Action Limited Datasets [129.24823721649028]
  In reinforcement learning, available data of decision making is often not annotated with actions. We propose combining large but sparsely-annotated datasets from a emphtarget environment of interest with fully-annotated datasets from various other emphsource environments. We show that utilizing even one additional environment dataset of sequential labelled data during IDM pretraining gives rise to substantial improvements in generating action labels for unannotated sequences.
  arXiv  Detail & Related papers  (2022-11-23T22:48:22Z)
• One-shot Key Information Extraction from Document with Deep Partial Graph Matching [60.48651298832829]
  Key Information Extraction (KIE) from documents improves efficiency, productivity, and security in many industrial scenarios. Existing supervised learning methods for the KIE task need to feed a large number of labeled samples and learn separate models for different types of documents. We propose a deep end-to-end trainable network for one-shot KIE using partial graph matching.
  arXiv  Detail & Related papers  (2021-09-26T07:45:53Z)
• ResNeSt: Split-Attention Networks [86.25490825631763]
  We present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification.
  arXiv  Detail & Related papers  (2020-04-19T20:40:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.