• Semantic Segmentation Graph Cut Functionality 3D Reconstruction Computer Vision Deep Learning Embodied Vision Vision-Language Navigation Scene Arrangement Reinforcement Learning MCTS
• 「Semantic Segmentation」 Joint Labelling and Segmentation for 3D Scanned Human Body
• 「Graph Cut」 Joint Labelling and Segmentation for 3D Scanned Human Body
• 「Functionality」 Transferring Objects: Joint Inference of Container and Human Pose
• 「3D Reconstruction」 Deep Single-View 3D Object Reconstruction with Visual Hull Embedding
• 「Computer Vision」 Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering Active Perception for Visual-Language Navigation
  
  Towards Versatile Embodied Navigation
  
  Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation Structured Scene Memory for Vision-Language Navigation Active Visual Information Gathering for Vision-Language Navigation Deep Single-View 3D Object Reconstruction with Visual Hull Embedding
• 「Deep Learning」 Deep Single-View 3D Object Reconstruction with Visual Hull Embedding
• 「Embodied Vision」 Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering Active Perception for Visual-Language Navigation
  
  Towards Versatile Embodied Navigation
  
  Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation Structured Scene Memory for Vision-Language Navigation Active Visual Information Gathering for Vision-Language Navigation
• 「Vision-Language Navigation」 Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering Active Perception for Visual-Language Navigation
  
  Towards Versatile Embodied Navigation
  
  Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation Structured Scene Memory for Vision-Language Navigation Active Visual Information Gathering for Vision-Language Navigation
• 「Scene Arrangement」 Scene Mover: Automatic Move Planning for Scene Arrangement by Deep Reinforcement Learning
• 「Reinforcement Learning」 Scene Mover: Automatic Move Planning for Scene Arrangement by Deep Reinforcement Learning
• 「MCTS」 Scene Mover: Automatic Move Planning for Scene Arrangement by Deep Reinforcement Learning