Abstract. We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the propose...
We define a new “contour person” model of the human body that has the expressive power of a detailed 3D model and the computational benefits of a simple 2D part-based model....
Oren Freifeld, Alex Weiss, Silvia Zuffi, Michael B...
This paper proposes a novel volume-based motion capture method using a bottom-up analysis of volume data and an example topology database of the human body. By using a two-step gra...
Paraphrasing van Rijsbergen [37], the time is ripe for another attempt at using natural language processing (NLP) for information retrieval (IR). This paper introduces my disserta...
This paper proposes a novel approach for multi-view multi-pose object detection using discriminative shapebased exemplars. The key idea underlying this method is motivated by nume...
Ying Shan, Feng Han, Harpreet S. Sawhney, Rakesh K...