Dong-Jin Kim

image captioning (5) semi-supervised learning (3) adversarial learning (2) generative adversarial network (2) video captioning (1) multi-task learning (1) zero-shot learning (1) part-of-speech tagging (1) domain adaptation (1) visual question answering (1) transfer learning (1) knowledge distillation (1) natural language generation (1) multimodal learning (1) video understanding (1) feature learning (1) human-object interaction (1) text-to-image generation (1) semantic segmentation (1) representation learning (1)