1.
Xue W, Qian C, Wu J, Zhou Y, Liu W, Ren J, et al. ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 13];39(9):9050-8. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/32979