Saved in:
Bibliographic Details
Main Authors: Ying, Xinru, Mo, Jiaqi, Lin, Jingyang, Jin, Canghong, Wang, Fangfang, Wei, Lina
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.03473
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915324018819072
author Ying, Xinru
Mo, Jiaqi
Lin, Jingyang
Jin, Canghong
Wang, Fangfang
Wei, Lina
author_facet Ying, Xinru
Mo, Jiaqi
Lin, Jingyang
Jin, Canghong
Wang, Fangfang
Wei, Lina
contents Partially Relevant Video Retrieval (PRVR) is a challenging task in the domain of multimedia retrieval. It is designed to identify and retrieve untrimmed videos that are partially relevant to the provided query. In this work, we investigate long-sequence video content understanding to address information redundancy issues. Leveraging the outstanding long-term state space modeling capability and linear scalability of the Mamba module, we introduce a multi-Mamba module with temporal fusion framework (MamFusion) tailored for PRVR task. This framework effectively captures the state-relatedness in long-term video content and seamlessly integrates it into text-video relevance understanding, thereby enhancing the retrieval process. Specifically, we introduce Temporal T-to-V Fusion and Temporal V-to-T Fusion to explicitly model temporal relationships between text queries and video moments, improving contextual awareness and retrieval accuracy. Extensive experiments conducted on large-scale datasets demonstrate that MamFusion achieves state-of-the-art performance in retrieval effectiveness. Code is available at the link: https://github.com/Vision-Multimodal-Lab-HZCU/MamFusion.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03473
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MamFusion: Multi-Mamba with Temporal Fusion for Partially Relevant Video Retrieval
Ying, Xinru
Mo, Jiaqi
Lin, Jingyang
Jin, Canghong
Wang, Fangfang
Wei, Lina
Computer Vision and Pattern Recognition
Partially Relevant Video Retrieval (PRVR) is a challenging task in the domain of multimedia retrieval. It is designed to identify and retrieve untrimmed videos that are partially relevant to the provided query. In this work, we investigate long-sequence video content understanding to address information redundancy issues. Leveraging the outstanding long-term state space modeling capability and linear scalability of the Mamba module, we introduce a multi-Mamba module with temporal fusion framework (MamFusion) tailored for PRVR task. This framework effectively captures the state-relatedness in long-term video content and seamlessly integrates it into text-video relevance understanding, thereby enhancing the retrieval process. Specifically, we introduce Temporal T-to-V Fusion and Temporal V-to-T Fusion to explicitly model temporal relationships between text queries and video moments, improving contextual awareness and retrieval accuracy. Extensive experiments conducted on large-scale datasets demonstrate that MamFusion achieves state-of-the-art performance in retrieval effectiveness. Code is available at the link: https://github.com/Vision-Multimodal-Lab-HZCU/MamFusion.
title MamFusion: Multi-Mamba with Temporal Fusion for Partially Relevant Video Retrieval
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.03473