Belinda Zeng

contrastive learning (6) knowledge distillation (4) representation learning (3) visual question answering (2) multi-modal learning (2) semantic similarity (2) vision-language representation (2) cross-modal retrieval (2) adversarial robustness (1) preference learning (1) multi-task learning (1) self-supervised learning (1) transfer learning (1) multimodal learning (1) zero-shot learning (1) adversarial training (1) video retrieval (1) binary classification (1) video understanding (1) few-shot learning (1)