Image classification is a critical task for both humans and computers. One of the challenges lies in the large scale of the semantic space. In particular, humans can recognize tens...
Abstract. We propose the study of graphs that are defined by lowcomplexity distributed and deterministic agents. We suggest that this viewpoint may help introduce the element of in...
This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingl...
This workshop promotes ubiquitous computing research in authentic urban setting, with real users and with sufficient scale and time span. We first motivate why such research is im...
In this paper we propose an approach for action recognition based on a vocabulary forest of local motionappearance features. Large numbers of features with associated motion vecto...