由于输入视频序列的每一帧被分割成任意形状的视频对象平面(VOP)，这样每个VOP描述了一个语义意义的对象或所感兴趣的视频内容。
Each frame of the input sequence is segmented into arbitrarily shaped image regions (VOP's) such that each VOP describes one semantically meaningful object or video content of interest.
由于输入视频序列的每一帧被分割成任意形状的视频对象平面(VOP)，这样每个VOP描述了一个语义意义的对象或所感兴趣的视频内容。
Each frame of the input sequence is segmented into arbitrarily shaped image regions (VOP's) such that each VOP describes one semantically meaningful object or video content of interest.
应用推荐