Multi-label learning is useful in visual object recognition when several objects are present in an image. Conventional approaches implement multi-label learning as a set of binary...
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....
In this paper we report on our experiments on aligning names and faces as found in images and captions of online news websites. Developing accurate technologies for linking names a...
Phi The Pham, Marie-Francine Moens, Tinne Tuytelaa...
Various interfaces for video browsing and retrieval have been proposed that provide improved usability, better retrieval performance, and richer user experience compared to simple ...
The explosive growth in image sharing via social networks has produced exciting opportunities for the computer vision community in areas including face, text, product and scene re...
Ana C. Murillo, Iljung S. Kwak, Lubomir Bourdev, D...