Towards Retrieval Augmented Generation over Large Video Libraries
This addresses the problem of inefficient manual or automated searches for video content creators, though it appears incremental as it applies existing RAG methods to video data.
The paper tackles the challenge of repurposing content from large video libraries by introducing Video Library Question Answering (VLQA), using Retrieval Augmented Generation (RAG) to retrieve relevant video moments and generate responses with timestamps.
Video content creators need efficient tools to repurpose content, a task that often requires complex manual or automated searches. Crafting a new video from large video libraries remains a challenge. In this paper we introduce the task of Video Library Question Answering (VLQA) through an interoperable architecture that applies Retrieval Augmented Generation (RAG) to video libraries. We propose a system that uses large language models (LLMs) to generate search queries, retrieving relevant video moments indexed by speech and visual metadata. An answer generation module then integrates user queries with this metadata to produce responses with specific video timestamps. This approach shows promise in multimedia content retrieval, and AI-assisted video content creation.