Abstract. This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database1 intermediate abstra...
In recent years, with the rapid proliferation of digital images, the need to search and retrieve the images accurately, efficiently, and conveniently is becoming more acute. Automa...
Abstract. This paper presents an architecture that enables the recognizer to learn incrementally and, thereby adapt to document image collections for performance improvement. We ar...
In this paper, an evaluation is presented of a framework that supports flexible content repurposing. Unlike the usual practice where content components, such as slides, images, def...
This paper describes an approach to optimize query by visual example results, by combining visual features and implicit user feedback in interactive video retrieval. To this end, ...
Stefanos Vrochidis, Ioannis Kompatsiaris, Ioannis ...