VideoRAG: Retrieval-Augmented Generation over Video Corpus

• URL: http://arxiv.org/abs/2501.05874v2
• Date: Tue, 04 Mar 2025 07:29:52 GMT
• Title: VideoRAG: Retrieval-Augmented Generation over Video Corpus
• Authors: Soyeong Jeong, Kangsan Kim, Jinheon Baek, Sung Ju Hwang,
• Abstract summary: VideoRAG is a framework that dynamically retrieves videos based on their relevance with queries.<n>VideoRAG is powered by recent Large Video Language Models (LVLMs)<n>We experimentally validate the effectiveness of VideoRAG, showcasing that it is superior to relevant baselines.
• Score: 57.68536380621672
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-Augmented Generation (RAG) is a powerful strategy for improving the factual accuracy of models by retrieving external knowledge relevant to queries and incorporating it into the generation process. However, existing approaches primarily focus on text, with some recent advancements considering images, and they largely overlook videos, a rich source of multimodal knowledge capable of representing contextual details more effectively than any other modality. While very recent studies explore the use of videos in response generation, they either predefine query-associated videos without retrieval or convert videos into textual descriptions losing multimodal richness. To tackle these, we introduce VideoRAG, a framework that not only dynamically retrieves videos based on their relevance with queries but also utilizes both visual and textual information. The operation of VideoRAG is powered by recent Large Video Language Models (LVLMs), which enable the direct processing of video content to represent it for retrieval and the seamless integration of retrieved videos jointly with queries for response generation. Also, inspired by that the context size of LVLMs may not be sufficient to process all frames in extremely long videos and not all frames are equally important, we introduce a video frame selection mechanism to extract the most informative subset of frames, along with a strategy to extract textual information from videos (as it can aid the understanding of video content) when their subtitles are not available. We experimentally validate the effectiveness of VideoRAG, showcasing that it is superior to relevant baselines. Code is available at https://github.com/starsuzi/VideoRAG.

Related papers

• WikiVideo: Article Generation from Multiple Videos [67.59430517160065]
  We present the challenging task of automatically creating a high-level Wikipedia-style article that aggregates information from multiple videos about real-world events. We introduce WikiVideo, a benchmark consisting of expert-written articles and densely annotated videos that provide evidence for articles' claims. We propose Collaborative Article Generation (CAG), a novel interactive method for article creation from multiple videos.
  arXiv  Detail & Related papers  (2025-04-01T16:22:15Z)
• VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos [25.770675590118547]
  VideoRAG is 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.
  arXiv  Detail & Related papers  (2025-02-03T17:30:19Z)
• SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis [52.050036778325094]
  We introduce SALOVA: Segment-Augmented Video Assistant, a novel video-LLM framework designed to enhance the comprehension of lengthy video content. We present a high-quality collection of 87.8K long videos, each densely captioned at the segment level to enable models to capture scene continuity and maintain rich context. Our framework mitigates the limitations of current video-LMMs by allowing for precise identification and retrieval of relevant video segments in response to queries.
  arXiv  Detail & Related papers  (2024-11-25T08:04:47Z)
• Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension [83.00346826110041]
  Video-RAG is a training-free and cost-effective pipeline that employs visually-aligned auxiliary texts to help facilitate cross-modality alignment. Our model demonstrates superior performance over proprietary models like Gemini-1.5-Pro and GPT-4o when utilized with a 72B model.
  arXiv  Detail & Related papers  (2024-11-20T07:44:34Z)
• GQE: Generalized Query Expansion for Enhanced Text-Video Retrieval [56.610806615527885]
  This paper introduces a novel data-centric approach, Generalized Query Expansion (GQE), to address the inherent information imbalance between text and video. By adaptively segmenting videos into short clips and employing zero-shot captioning, GQE enriches the training dataset with comprehensive scene descriptions. GQE achieves state-of-the-art performance on several benchmarks, including MSR-VTT, MSVD, LSMDC, and VATEX.
  arXiv  Detail & Related papers  (2024-08-14T01:24:09Z)
• Towards Retrieval Augmented Generation over Large Video Libraries [0.0]
  We introduce the task of Video Library Question Answering (VLQA) through an interoperable architecture. We propose a system that uses large language models (LLMs) to generate search queries, retrieving relevant video moments. An answer generation module then integrates user queries with this metadata to produce responses with specific video timestamps.
  arXiv  Detail & Related papers  (2024-06-21T07:52:01Z)
• TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment [42.557643515992005]
  Video understanding remains a challenge despite the availability of substantial web video-text data. We introduce Text-Only Pre-Alignment (TOPA), a novel approach to extend large language models (LLMs) for video understanding.
  arXiv  Detail & Related papers  (2024-05-22T18:35:10Z)
• iRAG: Advancing RAG for Videos with an Incremental Approach [3.486835161875852]
  One-time, upfront conversion of all content in large corpus of videos into text descriptions entails high processing times. We propose an incremental RAG system called iRAG, which augments RAG with a novel incremental workflow to enable interactive querying of video data. iRAG is the first system to augment RAG with an incremental workflow to support efficient interactive querying of a large corpus of videos.
  arXiv  Detail & Related papers  (2024-04-18T16:38:02Z)
• HaVTR: Improving Video-Text Retrieval Through Augmentation Using Large Foundation Models [11.883785732720094]
  We present a novel video-text learning paradigm, HaVTR, which augments video and text data to learn more generalized features. To bring richer information into video and text, we propose a hallucination-based augmentation method. Benefiting from the enriched data, extensive experiments on several video-text retrieval benchmarks demonstrate the superiority of HaVTR over existing methods.
  arXiv  Detail & Related papers  (2024-04-07T21:46:47Z)
• Scaling Up Video Summarization Pretraining with Large Language Models [73.74662411006426]
  We introduce an automated and scalable pipeline for generating a large-scale video summarization dataset. We analyze the limitations of existing approaches and propose a new video summarization model that effectively addresses them. Our work also presents a new benchmark dataset that contains 1200 long videos each with high-quality summaries annotated by professionals.
  arXiv  Detail & Related papers  (2024-04-04T11:59:06Z)
• Composed Video Retrieval via Enriched Context and Discriminative Embeddings [118.66322242183249]
  Composed video retrieval (CoVR) is a challenging problem in computer vision. We introduce a novel CoVR framework that leverages detailed language descriptions to explicitly encode query-specific contextual information. Our approach achieves gains as high as around 7% in terms of recall@K=1 score.
  arXiv  Detail & Related papers  (2024-03-25T17:59:03Z)
• Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement [72.7576395034068]
  Video Corpus Moment Retrieval (VCMR) is a new video retrieval task aimed at retrieving a relevant moment from a large corpus of untrimmed videos using a text query. We argue that effectively capturing the partial relevance between the query and video is essential for the VCMR task. For video retrieval, we introduce a multi-modal collaborative video retriever, generating different query representations for the two modalities. For moment localization, we propose the focus-then-fuse moment localizer, utilizing modality-specific gates to capture essential content.
  arXiv  Detail & Related papers  (2024-02-21T07:16:06Z)
• Zero-shot Audio Topic Reranking using Large Language Models [42.774019015099704]
  Multimodal Video Search by Examples (MVSE) investigates using video clips as the query term for information retrieval. This work aims to compensate for any performance loss from this rapid archive search by examining reranking approaches. Performance is evaluated for topic-based retrieval on a publicly available video archive, the BBC Rewind corpus.
  arXiv  Detail & Related papers  (2023-09-14T11:13:36Z)
• InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation [90.71796406228265]
  InternVid is a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations. The InternVid dataset contains over 7 million videos lasting nearly 760K hours, yielding 234M video clips accompanied by detailed descriptions of total 4.1B words.
  arXiv  Detail & Related papers  (2023-07-13T17:58:32Z)

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.