Towards Temporal Compositional Reasoning in Long-Form Sports Videos

• URL: http://arxiv.org/abs/2604.22226v1
• Date: Fri, 24 Apr 2026 05:02:03 GMT
• Title: Towards Temporal Compositional Reasoning in Long-Form Sports Videos
• Abstract summary: Chain-of-Time Reasoning (CoTR) treats reasoning as a process of temporally grounded evidence composition.<n>CoTR consistently improves temporal compositional reasoning and step-wise grounding quality over strong MLLM baselines.
• Score: 5.5825182710791275
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sports videos are a challenging domain for multimodal understanding because they involve complex and dynamic human activities. Despite rapid progress in Multimodal Large Language Models (MLLMs), long-horizon reasoning in sports videos remains difficult, as answering questions requires both locating temporally sparse evidence and integrating it into reasoning. We attribute this limitation to two closely coupled factors: insufficient supervision over temporally dispersed evidence, and the lack of methods that require models to identify, localize, and justify temporal evidence. To address these gaps, we introduce SportsTime, a large-scale benchmark for long-form sports video understanding, comprising 14K+ open-ended QA pairs and 50K+ step-wise temporal evidence annotations. Building on SportsTime, we propose Chain-of-Time Reasoning (CoTR), which treats reasoning as a process of temporally grounded evidence composition. Specifically, during training, CoTR introduces a temporal-reward GRPO to encourage temporally grounded reasoning. During inference, it employs an anchor-observe-infer evidence-seeking loop to iteratively localize, verify, and compose temporal evidence before producing the final answer. Experiments demonstrate the usefulness of SportsTime as a benchmark and the effectiveness of CoTR, which consistently improves temporal compositional reasoning and step-wise grounding quality over strong MLLM baselines.

Related papers

• TimeThink: Reasoning with Time for Video LLMs [28.549802513886046]
  We propose TimeThink, a reinforcement learning framework that guides temporal evidence discovery in Video-LLMs.<n>Our key idea is to treat temporal clue steps as the fundamental optimization primitive of video reasoning.<n>To enable scalable training, we construct TimeThink-RFT-20K, a dataset with automatically derived temporal evidence segments.
  arXiv  Detail & Related papers  (2026-07-06T13:50:15Z)
• Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA [16.471093160007587]
  VideoQA systems often rely on spurious statistical correlations rather than answer-relevant causal evidence.<n>Existing methods either rely on cross-modality correlations, costly curated training resources, or insufficient causal assumptions and constraints.<n>We propose a Counterfactual Reasoning framework for fine-grained Evidence Disentanglement (CREDiT)
  arXiv  Detail & Related papers  (2026-06-08T08:20:42Z)
• CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering [27.144152466342103]
  Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs)<n>We introduce CaST-Bench, a benchmark for Causal-Temporal Video Video Reasoning SST-Bench.<n>We construct a high-quality dataset of 2,066 questions over 1,015 videos, with causal chains annotated by temporal segments and bounding-box tracks.
  arXiv  Detail & Related papers  (2026-05-22T04:19:29Z)
• Video-Zero: Self-Evolution Video Understanding [54.992296368077085]
  We argue that the key bottleneck of video self-evolution is not difficulty alone, but grounding.<n>We propose Video-Zero, an annotation-free Questioner-answerr co-evolution framework that centers self-evolution on temporally localized evidence.<n>Video-Zero consistently improves multiple video VLM backbones, demonstrating the effectiveness and transferability of evidence-centered self-evolution.
  arXiv  Detail & Related papers  (2026-05-14T11:56:14Z)
• Structured Causal Video Reasoning via Multi-Objective Alignment [102.61829546891543]
  We propose a compact representation of salient events and their causal relationships, which we name Structured Event Facts, prior to the reasoning stage.<n>This structured prior serves as an explicit constraint to promote concise and causally grounded reasoning.<n>We introduce CausalFact-60K and a four-stage training pipeline comprising facts alignment, format warm-start, thinking warm-start, and reinforcement learning-based post-training.
  arXiv  Detail & Related papers  (2026-04-06T04:49:30Z)
• Process-of-Thought Reasoning for Videos [33.74677144833003]
  Process-of-Thought (PoT) Reasoning for Videos is a framework that makes the reasoning process explicit by structuring video inference into a sequence of lightweight, verifiable steps.<n>PoT interleaves (i) temporal evidence selection, (ii) step-wise state updates, and (iii) constrained answer synthesis, enabling the model to progressively refine hypotheses while maintaining traceability to video evidence.
  arXiv  Detail & Related papers  (2026-02-07T20:25:46Z)
• Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding [56.7383554589569]
  Long video understanding is essential for human-like intelligence, enabling coherent perception and reasoning over extended temporal contexts.<n>We propose SpecTemp, a reinforcement learning-based Speculative Temporal reasoning framework.<n>We show that SpecTemp not only maintains competitive accuracy but also significantly accelerates inference compared with existing thinking-with-frames methods.
  arXiv  Detail & Related papers  (2025-11-30T09:27:59Z)
• Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models [56.851611990473174]
  Reasoning over dynamic visual content remains a central challenge for large language models.<n>We propose a reinforcement learning approach that enhances both temporal precision and reasoning consistency.<n>The resulting model, Video R2, achieves consistently higher TAC, VAS, and accuracy across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-11-28T18:59:58Z)
• StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA [60.86024022291499]
  We introduce StreamingCoT, the first dataset explicitly designed for temporally evolving reasoning in streaming video streams.<n>Our framework generates per-second dense descriptions and constructs temporally-dependent semantic segments through similarity fusion.<n>This dataset establishes a foundation for advancing research in streaming video understanding, complex temporal reasoning, and multimodal inference.
  arXiv  Detail & Related papers  (2025-10-29T09:47:38Z)
• LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering [10.060267989615813]
  We introduce LeAdQA, an innovative approach that bridges these gaps through synergizing causal-aware query refinement with fine-grained visual grounding.<n> Experiments on NExT-QA, IntentQA, and NExT-GQA demonstrate that our method's precise visual grounding substantially enhances the understanding of video-question relationships.
  arXiv  Detail & Related papers  (2025-07-20T01:57:00Z)
• VITED: Video Temporal Evidence Distillation [49.38292490256531]
  We investigate complex video question answering via chain-of-evidence reasoning.<n>Models struggle with multi-step reasoning as they uniformly sample a fixed number of frames.<n>We propose a framework to enhance existing VideoQA datasets with evidence reasoning chains.
  arXiv  Detail & Related papers  (2025-03-17T06:30:02Z)

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.