In this paper, we show how to reconstruct both 3D shape and 2D texture of a class of surfaces from a single perspective image. We consider the so-called the generalized cylindrica...
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...
Top-down visual saliency facilities object localization by providing a discriminative representation of target objects and a probability map for reducing the search space. In this...
— Since family members have their unique features when living in a smart home environment, user identifications are able to achieve without any tags. In this paper, we propose T...
Computer-Supported Collaborative Learning (CSCL) is a new learning method that is receiving an increasing amount of attention in Taiwan. With the rapid growth in learning resource...