[1]
Tang, H. et al. 2025. MUSE: Mamba Is Efficient Multi-scale Learner for Text-video Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence. 39, 7 (Apr. 2025), 7238–7246. DOI:https://doi.org/10.1609/aaai.v39i7.32778.