Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval

About

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.

Haoran Tang, Meng Cao, Jinfa Huang, Ruyang Liu, Peng Jin, Ge Li, Xiaodan Liang• 2024

Related benchmarks

TaskDatasetResultRank
Text-to-Video RetrievalMSR-VTT (1k-A)
R@1085.6
211
Video-to-Text retrievalMSR-VTT (1k-A)
Recall@577.8
74
Showing 2 of 2 rows

Other info

Follow for update