JungIn Park

contrastive learning (2) multimodal learning (2) video grounding (2) self-supervised learning (2) action recognition (2) video representation (2) semantic segmentation (2) attention mechanism (1) visual question answering (1) vision transformer (1) domain adaptation (1) video understanding (1) transfer learning (1) context-aware learning (1) domain generalization (1) temporal reasoning (1) data augmentation (1) emotion recognition (1) temporal modeling (1) zero-shot learning (1)