One of the main challenges for Content-Based Image Retrieval (CBIR) is to achieve meaningful mappings between the high-level semantic concepts and the low-level visual features in...
Haiying Guan, Sameer Antani, L. Rodney Long, Georg...
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...
Abstract. Traditional retrieval models assume that query terms are independent and rank documents primarily based on various term weighting strategies including TF-IDF and document...
We describe a new method to find and cluster recurrent keyplaces in a movie. It consists of an unsupervised classification of shots that are taking place in the same physical loca...
In this paper, we present a novel image representation that renders it possible to access natural scenes by local semantic description. Our work is motivated by the continuing effo...