Many computer vision algorithms require searching a set of images for similar patches, which is a very expensive operation. In this work, we compare and evaluate a number of neares...
This paper addresses action spotting, the spatiotemporal detection and localization of human actions in video. A novel compact local descriptor of video dynamics in the context of...
Konstantinos Derpanis, Mikhail Sizintsev, Kevin Ca...
We investigate the problem of how to evaluate, fast and efficiently, classes of optimal route queries on a massive graph in a unified framework. To evaluate a route query effectiv...
This paper compares the efficacy and efficiency of different clustering approaches for selecting a set of exemplar images, to present in the context of a semantic concept. We eval...
This paper addresses the problem of estimating human body pose in static images. This problem is challenging due to the high dimensional state space of body poses, the presence of...