SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy

• URL: http://arxiv.org/abs/2605.09598v2
• Date: Tue, 12 May 2026 09:02:50 GMT
• Title: SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy
• Abstract summary: Vision-language models (VLMs) have recently shown strong potential in soccer video understanding.<n>Existing evaluation protocols focus on classification accuracy and do not assess visual grounding.<n>We introduce SoccerLens, a benchmark for grounded soccer video understanding.
• Score: 52.09081885158698
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models (VLMs) have recently shown strong potential in soccer video understanding. However, given the high complexity of soccer videos due to large viewpoint variations, rapid shot transitions, and cluttered scenes, it remains unclear on whether VLMs rely on meaningful visual evidence or exploit spurious correlations and shortcut learning. Existing evaluation protocols focus primarily on classification accuracy and do not assess visual grounding. To address this limitation, we introduce SoccerLens, a benchmark for grounded soccer video understanding. The benchmark contains annotated video segments spanning $13$ common soccer events, with structured visual cues organized into three levels of semantic relevance. We further extend the attribution method of Chefer [arXiv:2103.15679] to jointly model spatial and temporal attention, and introduce evaluation metrics that measure whether model attention aligns with annotated cues or drifts toward spurious regions. Our evaluation of state-of-the-art soccer VLMs shows that, despite strong classification accuracy, current models fail to exceed $50\%$ grounding performance even under the loosest cue definitions and consistently underutilize temporal information. These results reveal a substantial gap between predictive performance and true visual grounding, highlighting the need for grounded evaluation in complex spatio-temporal domains such as soccer.

Related papers

• SportsGrounder: Proposal-Aided Interleaved Grounding for Dense Sports Video Reasoning [46.575904751578236]
  Sports video analysis is crucial for athletic analytics and broadcasting enhancement.<n>Current Large Multimodal Models (LMMs) inherently struggle with such dense visual complexities.<n>We propose textbfSportsGrounder, a framework that leverages an open-vocabulary visual expert to aid interleaved grounding.<n>SportsGrounder significantly improves fine-grained reasoning and achieves state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2026-08-08T05:39:48Z)
• VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting [58.508924874097715]
  VisonCoach consists of two components: (1) Visual Prompt Selector, which predicts appropriate prompt types conditioned on the video and question, and (2) Spatio-Reasoner, optimized with RL under visual prompt guidance and object grounding rewards.<n>Our results show that visual prompting during training improves grounded video reasoning, while distract-distillationSense enables the model to this ability without requiring prompts at inference time.
  arXiv  Detail & Related papers  (2026-03-15T23:32:02Z)
• Do We Need Large VLMs for Spotting Soccer Actions? [4.175749804472612]
  We propose a shift from this video-centric approach to a text-based task, making it lightweight and scalable.<n>We posit that expert commentary, which provides rich descriptions and contextual cues contains sufficient information to reliably spot key actions in a match.<n>Our experiments show that this language-centric approach performs effectively in detecting critical match events coming close to state-of-the-art video-based spotters.
  arXiv  Detail & Related papers  (2025-06-20T16:45:54Z)
• Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos [1.4249472316161877]
  State-of-the-art,temporal action detection methods show promising results for extracting events from broadcast videos.<n>Many false positives could be resolved by considering a broader sequence of actions and game-state information.<n>We address this by reasoning at the game level and improving STAD through the addition of a denoising sequence task.
  arXiv  Detail & Related papers  (2025-05-14T15:05:36Z)
• TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation [13.835968474349034]
  TimeSoccer is the first end-to-end soccer MLLM for Single-anchor Video Captioning (SDVC) in full-match soccer videos.<n>TimeSoccer jointly predicts timestamps and generates captions in a single pass, enabling global context modeling.<n>MoFA-Select is a training-free, motion-aware frame compression module that adaptively selects representative frames.
  arXiv  Detail & Related papers  (2025-04-24T08:27:42Z)
• Towards Active Learning for Action Spotting in Association Football Videos [59.84375958757395]
  Analyzing football videos is challenging and requires identifying subtle and diverse-temporal patterns. Current algorithms face significant challenges when learning from limited annotated data. We propose an active learning framework that selects the most informative video samples to be annotated next.
  arXiv  Detail & Related papers  (2023-04-09T11:50:41Z)
• A Graph-Based Method for Soccer Action Spotting Using Unsupervised Player Classification [75.93186954061943]
  Action spotting involves understanding the dynamics of the game, the complexity of events, and the variation of video sequences. In this work, we focus on the former by (a) identifying and representing the players, referees, and goalkeepers as nodes in a graph, and by (b) modeling their temporal interactions as sequences of graphs. For the player identification task, our method obtains an overall performance of 57.83% average-mAP by combining it with other modalities.
  arXiv  Detail & Related papers  (2022-11-22T15:23:53Z)
• SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos [62.686484228479095]
  We propose a novel dataset for multiple object tracking composed of 200 sequences of 30s each. The dataset is fully annotated with bounding boxes and tracklet IDs. Our analysis shows that multiple player, referee and ball tracking in soccer videos is far from being solved.
  arXiv  Detail & Related papers  (2022-04-14T12:22:12Z)
• Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts [86.56462654572813]
  We focus our analysis on action spotting in soccer broadcast, which consists in temporally localizing the main actions in a soccer game. We propose a novel feature pooling method based on NetVLAD, dubbed NetVLAD++, that embeds temporally-aware knowledge. We train and evaluate our methodology on the recent large-scale dataset SoccerNet-v2, reaching 53.4% Average-mAP for action spotting.
  arXiv  Detail & Related papers  (2021-04-14T11:09:03Z)

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.