Son Tran

contrastive learning (4) video understanding (2) self-supervised learning (2) zero-shot learning (2) visual question answering (2) feature embedding (2) representation learning (2) vision-language representation (2) cross-modal retrieval (2) knowledge distillation (2) video retrieval (2) multi-modal learning (1) preference optimization (1) question answering (1) automated planning (1) text-to-image generation (1) personalized generation (1) pseudo labeling (1) visual reasoning (1) attention mechanism (1)