Compared to Singular Value Decomposition (SVD), Generalized Low Rank Approximations of Matrices (GLRAM) can consume less computation time, obtain higher compression ratio, and yiel...
—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...
We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects....
This paper considers the problem of identifying on the Web compound documents (cDocs) ? groups of web pages that in aggregate constitute semantically coherent information entities...
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...