We describe and demonstrate CBGIR, a web-based system for performing content-based image retrieval in large sets of high-resolution overhead images. The system provides a familiar...
Shawn Newsam, Daniel Leung, Oscar Caballero, Justi...
Pictorial structure (PS) models are extensively used for part-based recognition of scenes, people, animals and multi-part objects. To achieve tractability, the structure and param...
The design and implementation of systems that combine both the utilities of the digital world as well as intrinsic affordances of traditional artifacts are challenging. In this pap...
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....
Abstract. We propose a methodology for recognizing actions at a distance by watching the human poses and deriving descriptors that capture the motion patterns of the poses. Human p...