ECCV 2012 Workshop on Information Fusion in Computer Vision for Concept Recognition Print
Written by University of Reading   
Thursday, 28 June 2012 07:31

VideoSense is co-organizing the 2012 International Workshop on Information Fusion in Computer Vision for Concept Recognition (IFCVCR 2012), to be held in conjunction with the 12th European Conference on Computer Vision (ECCV 2012), on Oct 13, 2012, in Firenze, Italy. The workshop will bring together researchers working on wide range of topics related to:

  • Feature (early) fusion for visual content description;
  • Kernel fusion methods;
  • Classifier (late) fusion methods, stacking;
  • Bagging and boosting methods;
  • Multimodal fusion for multimedia tagging ;
  • Feature fusion for object detection, recognition and object tracking
  • Geo-tags and other sensor?based social information fusion
  • Normalisation for fusion;
  • Fusion and dimensionality reduction, PCA, LDA;
  • Contextual fusion, metadata;
  • Hierarchical and community?based fusion;
  • Social media fusion and mining
  • Metric spaces.
  • Legal, ethical and social concepts fusion

The fusion of multiple cues in the whole task of concept recognition in vision and content understanding seems to be promising to increase the performance of concept recognition. The large international community around both, the TRECVID challenge and the MediaEval challenge, has been intensively exploring this subject for many years. The target audience is a mix of these two benchmarking communities and other researchers working in fields of “Computer Vision” and “Multimedia Tagging and Retrieval”.

More details about the workshop can be found on the ECCV website ( and on the workshop website (

Important dates:

  • Paper submission due: July 1st, 2012
  • Notification of acceptance: July 31st, 2012
  • Camera-ready paper due: August 8th, 2012
  • Workshop date: October 13th, 2012
Last Updated on Thursday, 28 June 2012 15:43