Kyungsu Kim

multimodal learning (2) attention mechanism (2) neural network (2) question answering (2) video question answering (2) video understanding (2) optimal transport (1) visual question answering (1) semantic segmentation (1) weakly supervised learning (1) adversarial training (1) narrative generation (1) annotation-free learning (1) image captioning (1) medical imaging (1) multi-modal learning (1) feature embedding (1) image editing (1) self-supervised learning (1) adversarial learning (1)