Xu Wu

Pretrained time-series foundation models offer surprisingly inconsistent benefits for EMG tasks, with full fine-tuning often outperforming linear probing and few-shot adaptation only partially recovering performance on new users.

REDI-Match not only sets a new benchmark in dense feature matching but also accelerates inference speed, achieving 41 FPS on a single GPU.

Over 20 teams vied to decode human attention in video, revealing new insights into saliency prediction techniques.