Tomokazu Sato

Latest

• Finding important people in a video using deep neural networks with conditional random fields
• Iterative applications of image completion with CNN-based failure detection
• Summarization of user-generated sports video by using deep action recognition features
• Augmented reality marker hiding with texture deformation
• Novel view synthesis with light-weight view-dependent texture mapping for a stereoscopic HMD
• Video summarization using textual descriptions for authoring video blogs
• Increasing pose comprehension through augmented reality reenactment
• ReMagicMirror: Action learning using human reenactment with the mirror metaphor