The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion fiel...
A common approach in machine learning is to use a large amount of labeled data to train a model. Usually this model can then only be used to classify data in the same feature spac...
The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely ch...
Intensive computations required for sensing and processing perceptual information can impose significant burdens on personal computer systems. We explore several policies for sel...
This paper presents a novel approach to skim and describe 3D videos. 3D video is an imaging technology which consists in a stream of 3D models in motion captured by a synchronized ...
Tony Tung (Kyoto University), Takashi Matsuyama (K...