MUSE: Mamba Is Efficient Multi-scale Learner For Text-video Retrieval

Abstract

Text-Video Retrieval (TVR) aims to align and associate relevant video content with corresponding natural language queries. Most existing TVR methods are based on large-scale pre-trained vision-language models (e.g., CLIP). However, due to the inherent plain structure of CLIP, few TVR methods explore the multi-scale representations which offer richer contextual information for a more thorough understanding. To this end, we propose MUSE, a multi-scale mamba with linear computational complexity for efficient cross-resolution modeling. Specifically, the multi-scale representations are generated by applying a feature pyramid on the last single-scale feature map. Then, we employ the Mamba structure as an efficient multi-scale learner to jointly learn scale-wise representations. Furthermore, we conduct comprehensive studies to investigate different model structures and designs. Extensive results on three popular benchmarks have validated the superiority of MUSE.

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keytang2024muse

Related papers

• Mamfusion: Multi-mamba With Temporal Fusion For Partially Relevant Video Retrieval (2025)1.69
• MUVR: A Multi-modal Untrimmed Video Retrieval Benchmark With Multi-level Visual Correspondence (2025)1.40
• Mv-adapter: Multimodal Video Transfer Learning For Video Text Retrieval (2023)9.76
• CLIMP: Contrastive Language-image Mamba Pretraining (2026)0.00
• Bidirectional Likelihood Estimation With Multi-modal Large Language Models For Text-video Retrieval (2025)2.76
• Improving Video-text Retrieval By Multi-stream Corpus Alignment And Dual Softmax Loss (2021)0.00
• MURE: Hierarchical Multi-resolution Encoding Via Vision-language Models For Visual Document Retrieval (2026)0.00
• CLIP2TV: Align, Match And Distill For Video-text Retrieval (2021)0.00