Novel Machine Learning Algorithms for Centrality and Cliques Detection in Youtube Social Networks. Compositional Languages Emerge in a Neural Iterated Learning Model. Self-supervised Single-view 3D Reconstruction via Semantic Consistency. STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Ima …

Focus on Semantic Consistency for Cross-domain Crowd Understanding. InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining. Expressing Objects just like Words: Recurrent Visual Embedding for Image-Text Matching. Estimating Treatment Effects with Observed Confounders and Mediators. Meta3D: Single-View 3D Object Reconstruction from Sh …