Interactive detection of incrementally learned concepts in images with ranking and semantic query interpretation

Kl. Schutte, H. Bouma, J. Schavemaker, L. Daniele, M. Sappelli, G. Koot, P. Eendebak, G. Azzopardi, M. Spitters, M. de Boer, P. Brandt

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

7 Citations (Scopus)

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.
Original languageEnglish
Title of host publication13th International Workshop on Content-Based Multimedia Indexing (CBMI), 2015, 10-12 June 2015, Prague, Czech Republic
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages1-4
Number of pages4
DOIs
Publication statusPublished - 12 Jun 2015
Event13th International Workshop on Content-Based Multimedia Indexing (CBMI 2015), June 10-12, 2015, Prague, Czech Republic - Prague, Czech Republic
Duration: 10 Jun 201512 Jun 2015
http://siret.ms.mff.cuni.cz/cbmi2015/

Workshop

Workshop13th International Workshop on Content-Based Multimedia Indexing (CBMI 2015), June 10-12, 2015, Prague, Czech Republic
Abbreviated titleCBMI 2015
Country/TerritoryCzech Republic
CityPrague
Period10/06/1512/06/15
Internet address

Keywords

  • semantic reasoning
  • concept detection
  • incremental learning

Fingerprint

Dive into the research topics of 'Interactive detection of incrementally learned concepts in images with ranking and semantic query interpretation'. Together they form a unique fingerprint.

Cite this