In this paper, we address the problem of detecting pedestrians in still images. We introduce an algorithm for learning shapelet features, a set of mid?level features. These featur...
Fine-grained categorization refers to the task of classifying objects that belong to the same basic-level class (e.g. different bird species) and share similar shape or visual app...
This paper proposes a novel approach to recognize object categories in point clouds. By quantizing 3D SURF local descriptors, computed on partial 3D shapes extracted from the poin...
Recent research has shown the effectiveness of using sparse coding(Sc) to solve many computer vision problems. Motivated by the fact that kernel trick can capture the nonlinear sim...
Psychologists have proposed that many human-object interaction activities form unique classes of scenes. Recognizing these scenes is important for many social functions. To enable...