In this paper, we approach the problem of understanding human actions from still images. Our method involves representing the pose with a spatial and orientational histogramming o...
Nazli Ikizler, Pinar Duygulu, Ramazan Gokberk Cinb...
In this work, we propose to use attributes and parts for recognizing human actions in still images. We define action attributes as the verbs that describe the properties of human...
Bangpeng Yao, Xiaoye Jiang, Aditya Khosla, Andy La...
This paper presents a graphical model for learning and recognizing human actions. Specifically, we propose to encode actions in a weighted directed graph, referred to as action gra...
This paper describes a general methodology for automated recognition of complex human activities. The methodology uses a context-free grammar (CFG) based representation scheme to ...
MuchattentionhasrecentlybeenpaidtoAugmented Reality (AR) systems, which can enhance a human's dailylife by blending multi-modalinformation with the real world. Most existing ...