Tang H, Cao M, Huang J, Liu R, Jin P, Li G, et al. MUSE: Mamba Is Efficient Multi-scale Learner for Text-video Retrieval. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 10];39(7):7238-46. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/32778