Active learning methods aim to select the most informative unlabeled instances to label first, and can help to focus image or video annotations on the examples that will most impr...
Relevance feedback (RF) is an iterative process, which refines the retrievals by utilizing the user's feedback on previously retrieved results. Traditional RF techniques solel...
Peng-Yeng Yin, Bir Bhanu, Kuang-Cheng Chang, Anlei...
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...
—Web-scale image search engines (e.g. Google Image Search, Bing Image Search) mostly rely on surrounding text features. It is difficult for them to interpret users’ search int...
Xiaoou Tang, Ke Liu, Jingyu Cui, Fang Wen, Xiaogan...
Our objective is to improve the performance of keyword based image search engines by re-ranking their baseline results. To this end, we address three limitations of existing searc...