Xiangdong Zhang

self-supervised learning (2) point cloud (2) multimodal learning (1) scene graph (1) speech enhancement (1) variance maximization (1) mutual information (1) worst-case optimization (1) hypergraph clustering (1) 3d object classification (1) speech intelligibility (1) structure alignment (1) distribution alignment (1) masked autoencoder (1) center prediction (1) view reconstruction (1) self-supervised pre-training (1) language description (1) fairness constraint (1) discriminative feature selection (1)