Jin-Hwa Kim

text-to-image generation (4) multimodal learning (3) generative model (2) neural network (2) contrastive learning (2) visual dialog (2) spurious correlation (2) transfer learning (2) video moment retrieval (2) large language model (2) data augmentation (2) visual question answering (2) camera pose (2) knowledge distillation (2) self-supervised learning (1) semi-supervised learning (1) video prediction (1) benchmark evaluation (1) graph learning (1) scene understanding (1)