Fusion of multimedia streams for enhanced performance is a critical problem for retrieval. However, fusion performance tends to easily overfit the hillclimb set used to learn fus...
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
We present a method to automatically learn object categories from unlabeled images. Each image is represented by an unordered set of local features, and all sets are embedded into...
Image auto-annotation is an important open problem in
computer vision. For this task we propose TagProp, a discriminatively
trained nearest neighbor model. Tags of test
images a...
Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek...
Face verification has many potential applications including
filtering and ranking image/video search results on
celebrities. Since these images/videos are taken under uncontrolle...
Xiaogang Wang (MIT), Cha Zhang (Microsoft Research...