Yan-Bo Lin

multimodal learning (3) continual learning (1) diffusion model (1) zero-shot learning (1) vision transformer (1) domain adaptation (1) video generation (1) self-supervised learning (1) video question answering (1) audio-visual learning (1) cross-modal learning (1) person re-identification (1) semantic alignment (1) weakly-supervised learning (1) catastrophic forgetting (1) multimodal fusion (1) cross-dataset generalization (1) parameter efficiency (1) contrastive learning (1) representation learning (1)