Conference Paper

 

K. Schutte, H. Bouma, J. Schavemaker, L. Daniele, M. Sappelli, G. Koot, P. Eendebak, G. Azzopardi, M. Spitters, M. de Boer, M. Kruithof and Paul Brandt, “Interactive detection of incrementally learned concepts in images”, IEEE/ACM International Workshop on Content-Based Multimedia Indexing (CBMI), 2015.
[abstract] [pdf] [bib]

Abstract

The number of networked cameras is growing exponentially. Multiple applications in different domains result in an increasing need to search semantically over video sensor data. In this paper, we present the GOOSE demonstrator, which is a real-time general-purpose search engine that allows users to pose natural language queries to retrieve corresponding images. Top-down, this demonstrator interprets queries, which are presented as an intuitive graph to collect user feedback. Bottom-up, the system automatically recognizes and localizes concepts in images and it can incrementally learn novel concepts. A smart ranking combines both and allows effective retrieval of relevant images.

Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen, the Netherlands