We present a novel method for analyzing social behavior. Continuous videos are segmented into action ‘bouts’ by building a temporal context model that combines features from s...
In this paper we propose a novel approach for the spatial segmentation of video sequences containing multiple temporal textures. This work is based on the notion that a single tem...
Abstract. We propose a novel method for action detection based on a new action descriptor called a shape flow that represents both the shape and movement of an object in a holistic...
Human activity recognition has potential to impact a wide range of applications from surveillance to human computer interfaces to content based video retrieval. Recently, the rapi...
Kiwon Yun, Jean Honorio, Debaleena Chattopadhyay, ...
We introduce a novel local image descriptor designed for dense wide-baseline matching purposes. We feed our descriptors to a graph-cuts based dense depth map estimation algorithm ...