TennisVAR: A Stroke-Evidence-Grounded Multimodal Large Language Model for Tactical Reasoning in Tennis Videos

• URL: http://arxiv.org/abs/2608.12920v1
• Date: Thu, 13 Aug 2026 08:01:22 GMT
• Title: TennisVAR: A Stroke-Evidence-Grounded Multimodal Large Language Model for Tactical Reasoning in Tennis Videos
• Abstract summary: We develop a new rally-level task that requires models to jointly predict an open-ended answer, a hierarchical tactic label, an ordered sequence of supporting strokes, and decisive key actions.<n>We further introduce TRACE, a large-scale expert-annotated benchmark containing 11,189 rally videos, 41,485 stroke events, 25,429 units, and 11,189 question-answer pairs.<n>Building on TRACE, we propose Tennis VARI (Tennis Video Action-chain Reasoner), an evidence-grounded multimodal large language model that follows an "event-relation-evidence-tactic" reasoning paradigm.
• Score: 38.69856460966809
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sports-video understanding is moving beyond event recognition toward explaining how actions collectively shape match progression, however, existing tennis-video methods either perceive individual strokes without modeling their tactical dependencies or generate high-level analyses without grounding them in the underlying events. To bridge this perception-to-understanding gap, we formulate stroke-evidence-grounded tactical reasoning, a new rally-level task that requires models to jointly predict an open-ended answer, a hierarchical tactic label, an ordered sequence of supporting strokes, and decisive key actions, with each evidence stroke anchored to its racket-ball contact frame. We further introduce TRACE (Tactical Reasoning with Action-Chain Evidence in Tennis), a large-scale expert-annotated benchmark containing 11,189 rally videos, 41,485 stroke events, 25,429 tactical units, and 11,189 question-answer pairs, which unifies fine-grained stroke attributes, cross-stroke tactical relations, hierarchical tactic annotations, and evidence-grounded questions across factual perception, tactical understanding, and decision reasoning. Building on TRACE, we propose TennisVAR (Tennis Video Action-chain Reasoner), an evidence-grounded multimodal large language model that follows an "event-relation-evidence-tactic" reasoning paradigm, where an Event Parsing Module converts continuous rallies into explicit stroke-event sequences while a Tactical Graph-Guided Temporal Reasoner jointly models rally progression and same-player decision dependencies to identify question-relevant evidence and decisive actions.

Related papers

• DoublesEval: Diagnosing Multi-Agent Tactical Reasoning in Vision-Language Models via Professional Doubles Badminton [1.6892008660392037]
  Visual Language Models (VLMs) excel at describing visible scene content but struggle to reason about dynamic multi-agent interactions.<n>We formalize this capability as textbfmulti-agent tactical reasoning and introduce textbfDoublesEval, a diagnostic evaluation framework.<n>DoublesEval employs a key-moment-based protocol that decomposes rallies into tactically salient instants and probes models across four interpretable dimensions.
  arXiv  Detail & Related papers  (2026-08-25T11:51:01Z)
• A Skill-augmented Agentic Framework and Benchmark for Multi-Video Understanding [69.31609753061137]
  Multimodal Large Language Models have achieved strong performance in single-video understanding, yet their ability to reason across multiple videos remains limited.<n>Existing approaches typicallyulate multiple videos into a single input and performulate direct inference, which introduces training-inference mismatch.<n>Current multi-video benchmarks primarily emphasize event-level comparison, leaving identity-level matching, fine-grained discrimination, and structured multi-step reasoning underexplored.<n>We propose SAMA, a Skill-Augmented Agentic Framework for Multi-Video Understanding, which integrates visual tools, task-specific skills, and a conflict-aware verification mechanism
  arXiv  Detail & Related papers  (2026-03-16T02:09:48Z)
• TennisExpert: Towards Expert-Level Analytical Sports Video Understanding [16.625250626542208]
  Tennis is one of the most widely followed sports, generating extensive broadcast footage with strong potential for professional analysis, automated coaching, and real-time commentary.<n>However, automatic tennis understanding remains underexplored due to lack of large-scale benchmarks with fine-grained annotations and expert-level commentary.<n>To address these challenges, we introduce TennisVL, a large-scale tennis benchmark comprising over 200 professional matches (471.9 hours) and 40,000+ rally-level clips.<n>We propose TennisExpert, a multimodal tennis understanding framework that integrates a video semantic with a memory-augmented model built on Qwen3-VL-8B
  arXiv  Detail & Related papers  (2026-03-11T15:12:10Z)
• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• CourtMotion: Learning Event-Driven Motion Representations from Skeletal Data for Basketball [45.88028371034407]
  CourtMotion is atemporal modeling framework for analyzing and predicting game events and plays in professional basketball.<n>Our two-stage approach first processes skeletal tracking data through Graph Neural Networks to capture nuanced motion patterns.<n>We introduce event projection heads that explicitly connect player movements to basketball events like passes, shots, and steals, training the model to associate physical motion patterns with their purposes.
  arXiv  Detail & Related papers  (2025-12-01T09:58:24Z)
• STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training [87.58996020705258]
  Video Large Language Models (Video-LLMs) have recently shown strong derivation in basic video understanding tasks.<n>Video-LLMs struggle with compositional reasoning that requires multi-step explicit-temporal inference across object relations, interactions and events.<n>We propose STEP, a novel graph-guided self-training method that enables VideoLLMs to generate reasoning-rich finetuning data from any raw videos to improve itself.
  arXiv  Detail & Related papers  (2024-11-29T11:54:55Z)
• Harnessing Temporal Causality for Advanced Temporal Action Detection [53.654457142657236]
  We introduce CausalTAD, which combines causal attention and causal Mamba to achieve state-of-the-art performance on benchmarks. We ranked 1st in the Action Recognition, Action Detection, and Audio-Based Interaction Detection tracks at the EPIC-Kitchens Challenge 2024, and 1st in the Moment Queries track at the Ego4D Challenge 2024.
  arXiv  Detail & Related papers  (2024-07-25T06:03:02Z)
• ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis [19.945083591851517]
  ViSTec is a Video-based Sports Technique recognition model inspired by human cognition. Our approach integrates a graph to explicitly model strategic knowledge in stroke sequences and enhance technique recognition with contextual inductive bias. Case studies with experts from the Chinese national table tennis team validate our model's capacity to automate analysis.
  arXiv  Detail & Related papers  (2024-02-25T02:04:56Z)
• Where Will Players Move Next? Dynamic Graphs and Hierarchical Fusion for Movement Forecasting in Badminton [6.2405734957622245]
  We focus on predicting what types of returning strokes will be made, and where players will move to based on previous strokes. Existing sequence-based models neglect the effects of interactions between players, and graph-based models still suffer from multifaceted perspectives. We propose a novel Dynamic Graphs and Hierarchical Fusion for Movement Forecasting model (DyMF) with interaction style extractors.
  arXiv  Detail & Related papers  (2022-11-22T12:21:24Z)
• Learning to reason about and to act on physical cascading events [72.90358875111883]
  We introduce a new supervised learning setup called em Cascade where an agent is shown a video of a physically simulated dynamic scene. The agent is asked to intervene and trigger a cascade of events, such that the system reaches a "counterfactual" goal. We demonstrate that our approach learns to effectively follow instructions to intervene in previously unseen complex scenes.
  arXiv  Detail & Related papers  (2022-02-02T16:17:42Z)

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.