TRACE: Evidence Grounding-Guided Multi-Video Event Understanding and Claim Generation
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 detec...
| Authors | Pengyu Yan, Akhil Gorugantu, Mahesh Bhosale et al. |
|---|---|
| Primary category | cs.CV |
| Published | 16 May 2026 |
| Last updated at source | 1 June 2026 |
Models and datasets referencing this paper
- akhilvssg/TRACE-MAGMaR-2026Dataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.