Chaofan Ma

semantic segmentation (3) vision transformer (1) self-supervised learning (1) weakly supervised learning (1) synthetic data generation (1) audio-visual fusion (1) synthetic datum (1) vision-language pre-training (1) open vocabulary (1) segment anything model (1) zero-shot segmentation (1) audio-visual segmentation (1) audio-visual interaction (1) prototypical learning (1) contrastive learning (1) attribute decomposition (1)