We investigate methods of segmenting, visualizing, and indexing presentation videos by both audio and visual data. The audio track is segmented by speaker, and augmented with key ...
This paper presents a video-based motion modeling technique for generating physically realistic human motion from monocular video sequences. We formulate the video-based motion mo...
Recognizing players’ affective state while playing video games has been the focus of many recent research studies. In this paper we describe the process that has been followed t...
Noor Shaker, Stylianos Asteriadis, Georgios N. Yan...
Object detectors are typically trained on a large set of still images annotated by bounding-boxes. This paper introduces an approach for learning object detectors from realworld w...
Alessandro Prest, Christian Leistner, Javier Civer...
It is important to integrate contextual information in order to improve the inaccurate results of current approaches for automatic image annotation. Graph based representations all...
Vassilios Stathopoulos, Jana Urban, Joemon M. Jose