Over the last several years, a new probabilistic representation for 3-d volumetric modeling has been developed. The main purpose of the model is to detect deviations from the norm...
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...
— In this work we introduce a novel approach for detecting spatiotemporal object-action relations, leading to both, action recognition and object categorization. Semantic scene g...
Eren Erdal Aksoy, Alexey Abramov, Florentin Wö...
We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects....
We present a framework for learning object representations for fast recognition of a large number of different objects. Rather than learning and storing feature representations s...