This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
A successful representation of objects in the literature is as a collection of patches, or parts, with a certain appearance and position. The relative locations of the different p...
Given sensors to detect object use, commonsense priors of object usage in activities can reduce the need for labeled data in learning activity models. It is often useful, however,...
Shiaokai Wang, William Pentney, Ana-Maria Popescu,...
In this paper, we address the tasks of detecting, segmenting, parsing, and matching deformable objects. We use a novel probabilistic object model that we call a hierarchical defor...
With recent advances in sensory and mobile computing technology, enormous amounts of data about moving objects are being collected. One important application with such data is aut...
Xiaolei Li, Jiawei Han, Sangkyum Kim, Hector Gonza...