We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
Hierarchical models have been extensively studied in various domains. However, existing models assume fixed model structures or incorporate structural uncertainty generatively. In...
In this paper, we propose a novel approach of image annotation by constructing a hierarchical mapping between lowlevel visual features and text features utilizing the relations wi...
Area based triggers denote notifications being generated if a mobile client changes its spatial relation to a defined area, e.g. if it enters or leaves it. By these triggers, new ...
Text facilitated sports video analysis has achieved extensive success in video indexing, retrieval and summarization. A commonly adopted basis in previous work is the separate alig...
Chao Liang, Yi Zhang, Changsheng Xu, Jinqiao Wang,...