Jul 2026
Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors
DAFS (Dynamic Attention-based Budget-aware Frame Selection), a training-free frame selector that improves over uniform sampling by up to 6.4 points on Video-MME and outperforms prior training-based selectors under matched frame budgets, while generalizing across selector and answerer backbones, and across tasks, without retraining.
Yilin Wang, Xiangxi Zheng, Dongxing Mao et al.
· arXiv.org · 2 citations