机译:单眼视频序列的视频对象分割和3D轨迹估计
Centre for Signal Processing, Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Kowloon, Hong Kong,TNList and Department of Automation, Tsinghua, University, Beijing 100086, China0;
Centre for Signal Processing, Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Kowloon, Hong Kong;
TNList and Department of Automation, Tsinghua, University, Beijing 100086, China;
2d-to-3d video conversion; 3d trajectory estimation; video-object segmentation;
机译:使用可变形曲面和径向基函数的单眼视频序列中的3-D头部姿势估计
机译:用于视频对象分割的VLSI架构
机译:用于视频对象分割的VLSI架构
机译:来自街道场景的单眼电视框架序列的移动汽车的体积模型和3D轨迹
机译:通过单眼视频序列基于3D姿势估计的人类动作识别。
机译:视频序列中基于GrabCut的人类分割
机译:单眼视频序列的视频对象分割和3D轨迹估计