Kazuhito Koishida

speech enhancement (6) knowledge distillation (2) gui grounding (2) multimodal learning (2) convolutional neural network (2) embedding learning (1) visual perception (1) representation learning (1) speaker verification (1) ensemble learning (1) channel attention (1) feature embedding (1) scene graph generation (1) visual grounding (1) attention mechanism (1) deep learning (1) efficient inference (1) speaker embedding (1) visual question answering (1) metric learning (1)