TRACE: Evidence Grounding-Guided Multi-Video Event Understanding and Claim Generation

• URL: http://arxiv.org/abs/2605.16740v1
• Date: Sat, 16 May 2026 01:37:10 GMT
• Title: TRACE: Evidence Grounding-Guided Multi-Video Event Understanding and Claim Generation
• Abstract summary: We introduce TRACE, an evidence grounding-guided framework for multi-video event reasoning.<n>Our approach first builds a structured, text-searchable timeline for each video using OCR and object detection.<n>A text-only LLM then conducts query-aware evidence localization, selecting relevant moments prior to any downstream visual reasoning.
• Score: 2.3450855956637913
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-video event understanding demands models that can locate and attribute query-relevant evidence scattered across long, heterogeneous video corpora. Existing large vision-language models (LVLMs) often underperform in this regime because they quickly exhaust their context budget and struggle to precisely localize evidentially important segments, frequently missing dense informational cues such as broadcast graphics, subtitles, and scoreboards. We introduce TRACE, an evidence grounding-guided framework that follows a ground-before-reasoning strategy for multi-video event reasoning. Our approach first builds a structured, text-searchable timeline for each video using OCR and object detection. A text-only LLM then conducts query-aware evidence localization, selecting relevant moments prior to any downstream visual reasoning. The retrieved frames and their grounding summaries are subsequently used to steer LVLM-based claim generation and cross-video citation consolidation. Experiments on MAGMaR 2026 and WikiVideo demonstrate that structured grounding markedly boosts factual completeness and attribution fidelity. On the MAGMaR validation split, TRACE raises macro-average MiRAGE F1 from 0.705 to 0.811 compared to an unguided Qwen3-VL-30B baseline, with especially strong improvements in citation recall from 0.440 to 0.628. The method also attains state-of-the-art results on the official MAGMaR 2026 leaderboard.

Related papers

• Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs [16.29545034560019]
  Video(VR) organizes each video into a question-agnostic temporal hierarchy.<n> nodes capture broad storyline context and event progression.<n>Lower-level nodes preserve fine-grained local details and evidence-bearing moments.
  arXiv  Detail & Related papers  (2026-08-06T04:27:59Z)
• Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events [52.031070006859544]
  Video multimodal large language models (MLLMs) have made rapid progress on general and long-form video understanding, yet their ability to preserve brief answer-critical visual evidence remains underexplored.<n>We introduce Moment-Video, a benchmark for diagnosing the temporal fidelity of video MLLMs through momentary visual event understanding.
  arXiv  Detail & Related papers  (2026-06-01T17:32:20Z)
• Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding [86.37002814396674]
  We propose Foresee-to-Ground (F2G) for Video Temporal Grounding.<n>F2G integrates Predictive Temporal Perception with Evidence-Driven Reasoning.<n>It consistently improves grounding accuracy across diverse benchmarks.
  arXiv  Detail & Related papers  (2026-05-21T04:03:25Z)
• CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering [2.3450855956637913]
  Grounded multi-video question answering over real-world news events requires systems to surface query-relevant evidence across heterogeneous archives.<n>We introduce CRAFT, a query-conditioned pipeline that combines dynamic selection, per-video ASR with multilingual fallback, and a hybrid critic loop.<n>On MAGMaR 2026, CRAFT achieves the best overall average (0.739), reference recall (0.810), and citation F1 (0.635)
  arXiv  Detail & Related papers  (2026-05-18T20:01:05Z)
• VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG [33.938909878793815]
  VideoStir is a structured and multimodal intent-aware long-video RAG framework.<n>It structures a video as atemporal graph at clip level, and then performs multi-hop retrieval to aggregate evidence.<n>It also introduces an MLLM-backed intent-relevance scorer that retrieves frames based on their alignment with the query's reasoning intent.
  arXiv  Detail & Related papers  (2026-04-07T04:26:59Z)
• Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding [98.3098451637867]
  Video-MME-v2 is a comprehensive benchmark designed to rigorously evaluate the robustness and faithfulness of video understanding.<n>To guarantee data quality, Video-MME-v2 is constructed through a rigorously controlled human annotation pipeline.
  arXiv  Detail & Related papers  (2026-04-06T17:59:56Z)
• SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding [36.30263540665245]
  We propose a framework for effective and reliable long video understanding.<n>SeViCES is training-free and model-agnostic, and introduces two key components.<n> experiments on long video understanding benchmarks show that SeViCES consistently outperforms state-of-the-art methods in both accuracy and robustness.
  arXiv  Detail & Related papers  (2025-10-23T14:55:28Z)
• iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning [51.15353027471834]
  iFinder is a semantic grounding framework that translates dash-cam videos into a hierarchical, interpretable data structure for large language models.<n>iFinder operates as a training-free pipeline that employs pretrained vision models to extract critical cues.<n>It significantly outperforms end-to-end V-VLMs on four zero-shot driving benchmarks.
  arXiv  Detail & Related papers  (2025-09-23T20:25:53Z)
• Episodic Memory Representation for Long-form Video Understanding [52.33907540905242]
  Large Video Language Models excel at general video understanding but struggle with long-form context window limits.<n>We introduce Video-EM, a training free framework inspired by the principles of human memory.<n>Video-EM achieves performance gains of 4-9 percent over respective baselines while utilizing fewer frames.
  arXiv  Detail & Related papers  (2025-08-13T04:33:07Z)
• A Survey on Video Temporal Grounding with Multimodal Large Language Model [107.24431595873808]
  Recent advancement in temporal grounding (VTG) has significantly enhanced fine-grained video understanding.<n>With superior multimodal comprehension and reasoning abilities, VTG approaches based on MLLMs (VTG-MLLMs) are gradually surpassing traditional fine-tuned methods.<n>Despite extensive surveys on general video-language understanding, comprehensive reviews specifically addressing VTG-MLLMs remain scarce.
  arXiv  Detail & Related papers  (2025-08-07T08:52:11Z)
• ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning [68.76048244253582]
  We introduce ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in video understanding.<n>ViaRL utilizes the answer accuracy of a downstream model as a reward signal to train a frame selector through trial-and-error.<n>ViaRL consistently delivers superior temporal grounding performance and robust generalization across diverse video understanding tasks.
  arXiv  Detail & Related papers  (2025-05-21T12:29:40Z)

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.