T2vindexer: A Generative Video Indexer For Efficient Text-video Retrieval

Abstract

Current text-video retrieval methods mainly rely on cross-modal matching between queries and videos to calculate their similarity scores, which are then sorted to obtain retrieval results. This method considers the matching between each candidate video and the query, but it incurs a significant time cost and will increase notably with the increase of candidates. Generative models are common in natural language processing and computer vision, and have been successfully applied in document retrieval, but their application in multimodal retrieval remains unexplored. To enhance retrieval efficiency, in this paper, we introduce a model-based video indexer named T2VIndexer, which is a sequence-to-sequence generative model directly generating video identifiers and retrieving candidate videos with constant time complexity. T2VIndexer aims to reduce retrieval time while maintaining high accuracy. To achieve this goal, we propose video identifier encoding and query-identifier augmentation approa

Stats

• citations5
• S2 citations—
• github stars15
• HF likes0
• heat score8.24
• arxiv keyli2024t2vindexer

Related papers

• Generative Recall, Dense Reranking: Learning Multi-view Semantic Ids For Efficient Text-to-video Retrieval (2026)0.00
• Viseret: A Simple Yet Effective Approach To Moment Retrieval Via Fine-grained Video Segmentation (2021)0.00
• Video-colbert: Contextualized Late Interaction For Text-to-video Retrieval (2025)5.24
• Dual Encoding For Video Retrieval By Text (2020)16.05
• UATVR: Uncertainty-adaptive Text-video Retrieval (2023)15.46
• Ts2-net: Token Shift And Selection Transformer For Text-video Retrieval (2022)15.51
• T2VLAD: Global-local Sequence Alignment For Text-video Retrieval (2021)16.65
• T2vparser: Adaptive Decomposition Tokens For Partial Alignment In Text To Video Retrieval (2025)0.95