Geondo Park

model compression (1) unsupervised learning (1) representation learning (1) zero-shot learning (1) transfer learning (1) visual question answering (1) medical imaging (1) knowledge distillation (1) image captioning (1) neural architecture search (1) magnetic resonance imaging (1) visual-semantic embedding (1) visual semantic embedding (1) language model (1) image-text retrieval (1) novel class (1) multi-head self-attention (1) self-attention network (1) multi-head attention (1) model interpretation (1)