Yanli Ji

representation learning (2) cross-modal learning (2) transformer architecture (1) contrastive learning (1) semantic segmentation (1) metric learning (1) few-shot learning (1) neural network optimization (1) transfer learning (1) feature selection (1) audio-visual learning (1) adversarial learning (1) multi-modal learning (1) video understanding (1) unsupervised learning (1) sound separation (1) conjugate gradient (1) multi-source domain adaptation (1) 3d human pose estimation (1) feature alignment (1)