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

ArXiv CS.CV2026-06-02NEWSen作者: Pengyu Yan, Akhil Gorugantu, Mahesh Bhosale, Abdul Wasi, Vishvesh Trivedi, David Doermann
查看原文 →
关系图谱

TRACE: Evidence Grounding-Guided Multi-Video Event Understanding and Claim Generation · 相关技术

相关技术

LLM3D object detectionOCRLarge vision-language modelLVLMsTRACE