Jingyu Li

speaker verification (4) speaker embedding (3) model compression (2) semi-supervised learning (2) convolutional neural network (2) attention mechanism (2) representation learning (2) reinforcement learning (1) contrastive learning (1) deep reinforcement learning (1) optimal transport (1) self-supervised learning (1) domain adaptation (1) weakly supervised learning (1) trajectory prediction (1) vision transformer (1) vision-language alignment (1) image captioning (1) multimodal learning (1) batch normalization (1)