Sangho Lee

multimodal learning (3) image generation (2) mutual information (2) self-supervised learning (2) benchmark evaluation (1) image captioning (1) transformer architecture (1) pose estimation (1) contrastive learning (1) visual question answering (1) video captioning (1) online learning (1) audio-visual learning (1) self-attention mechanism (1) representation learning (1) depth estimation (1) image synthesis (1) instruction following (1) efficient computing (1) unsupervised learning (1)