VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ren, Xubin, Xu, Lingrui, Xia, Long, Wang, Shuaiqiang, Yin, Dawei, Huang, Chao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916595264126976
author Ren, Xubin
Xu, Lingrui
Xia, Long
Wang, Shuaiqiang
Yin, Dawei
Huang, Chao
author_facet Ren, Xubin
Xu, Lingrui
Xia, Long
Wang, Shuaiqiang
Yin, Dawei
Huang, Chao
contents Retrieval-Augmented Generation (RAG) has demonstrated remarkable success in enhancing Large Language Models (LLMs) through external knowledge integration, yet its application has primarily focused on textual content, leaving the rich domain of multi-modal video knowledge predominantly unexplored. This paper introduces VideoRAG, the first retrieval-augmented generation framework specifically designed for processing and understanding extremely long-context videos. Our core innovation lies in its dual-channel architecture that seamlessly integrates (i) graph-based textual knowledge grounding for capturing cross-video semantic relationships, and (ii) multi-modal context encoding for efficiently preserving visual features. This novel design empowers VideoRAG to process unlimited-length videos by constructing precise knowledge graphs that span multiple videos while maintaining semantic dependencies through specialized multi-modal retrieval paradigms. Through comprehensive empirical evaluation on our proposed LongerVideos benchmark-comprising over 160 videos totaling 134+ hours across lecture, documentary, and entertainment categories-VideoRAG demonstrates substantial performance compared to existing RAG alternatives and long video understanding methods. The source code of VideoRAG implementation and the benchmark dataset are openly available at: https://github.com/HKUDS/VideoRAG.
format Preprint
id arxiv_https___arxiv_org_abs_2502_01549
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos
Ren, Xubin
Xu, Lingrui
Xia, Long
Wang, Shuaiqiang
Yin, Dawei
Huang, Chao
Information Retrieval
Artificial Intelligence
Computer Vision and Pattern Recognition
Retrieval-Augmented Generation (RAG) has demonstrated remarkable success in enhancing Large Language Models (LLMs) through external knowledge integration, yet its application has primarily focused on textual content, leaving the rich domain of multi-modal video knowledge predominantly unexplored. This paper introduces VideoRAG, the first retrieval-augmented generation framework specifically designed for processing and understanding extremely long-context videos. Our core innovation lies in its dual-channel architecture that seamlessly integrates (i) graph-based textual knowledge grounding for capturing cross-video semantic relationships, and (ii) multi-modal context encoding for efficiently preserving visual features. This novel design empowers VideoRAG to process unlimited-length videos by constructing precise knowledge graphs that span multiple videos while maintaining semantic dependencies through specialized multi-modal retrieval paradigms. Through comprehensive empirical evaluation on our proposed LongerVideos benchmark-comprising over 160 videos totaling 134+ hours across lecture, documentary, and entertainment categories-VideoRAG demonstrates substantial performance compared to existing RAG alternatives and long video understanding methods. The source code of VideoRAG implementation and the benchmark dataset are openly available at: https://github.com/HKUDS/VideoRAG.
title VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos
topic Information Retrieval
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.01549