Automatic scene generation using voice and text offers a unique multimedia approach to classic storytelling and human computer interaction with 3D graphics. In this paper, we pre...
We present algorithms for recognizing human motion in monocular video sequences, based on discriminative Conditional Random Field (CRF) and Maximum Entropy Markov Models (MEMM). E...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
Generation of ground-truths is of great importance for unbiased performance evaluation of document layout analysis methods. This is especially necessary because many methods are c...
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human...
Abhinav Gupta, Trista Chen, Francine Chen, Don Kim...
: Acquisition of various human body models is useful in many cases. In this paper, we present some of our recent work on body creation tools. Our goal is to enable rapid creation o...
Hyewon Seo, Frederic Cordier, Laurent Philippon, N...