Search papers, labs, and topics across Lattice.
This paper introduces TennisVAR, a multimodal large language model designed for tactical reasoning in tennis videos, addressing the gap between stroke recognition and understanding match dynamics. By formulating a new task of stroke-evidence-grounded tactical reasoning, the authors create the TRACE benchmark, which includes extensive annotations for rally videos, stroke events, and tactical units. The key finding reveals that TennisVAR effectively utilizes an event-relation-evidence-tactic reasoning paradigm to enhance understanding of match progression and decision-making in tennis.
TennisVAR redefines sports video analysis by grounding tactical reasoning in stroke-level evidence, enabling deeper insights into match strategies.
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.
