{"year":"2012","publisher":"IEEE","oa_version":"None","date_created":"2018-12-11T12:02:21Z","user_id":"4435EBFC-F248-11E8-B48F-1D18A9856A87","publist_id":"3382","quality_controlled":"1","title":"Image segmentation by figure-ground composition into maximal cliques","status":"public","month":"01","date_updated":"2021-01-12T07:42:15Z","type":"conference","author":[{"first_name":"Adrian","last_name":"Ion","id":"29F89302-F248-11E8-B48F-1D18A9856A87","full_name":"Ion, Adrian"},{"full_name":"Carreira, Joao","last_name":"Carreira","first_name":"Joao"},{"full_name":"Sminchisescu, Cristian","last_name":"Sminchisescu","first_name":"Cristian"}],"day":"12","doi":"10.1109/ICCV.2011.6126486","_id":"3265","article_number":"6126486","department":[{"_id":"HeEd"}],"language":[{"iso":"eng"}],"abstract":[{"lang":"eng","text":"We propose a mid-level statistical model for image segmentation that composes multiple figure-ground hypotheses (FG) obtained by applying constraints at different locations and scales, into larger interpretations (tilings) of the entire image. Inference is cast as optimization over sets of maximal cliques sampled from a graph connecting all non-overlapping figure-ground segment hypotheses. Potential functions over cliques combine unary, Gestalt-based figure qualities, and pairwise compatibilities among spatially neighboring segments, constrained by T-junctions and the boundary interface statistics of real scenes. Learning the model parameters is based on maximum likelihood, alternating between sampling image tilings and optimizing their potential function parameters. State of the art results are reported on the Berkeley and Stanford segmentation datasets, as well as VOC2009, where a 28% improvement was achieved."}],"publication_status":"published","conference":{"start_date":"2011-11-06","name":"ICCV: International Conference on Computer Vision","location":"Barcelona, Spain","end_date":"2011-11-13"},"citation":{"chicago":"Ion, Adrian, Joao Carreira, and Cristian Sminchisescu. “Image Segmentation by Figure-Ground Composition into Maximal Cliques.” IEEE, 2012. <a href=\"https://doi.org/10.1109/ICCV.2011.6126486\">https://doi.org/10.1109/ICCV.2011.6126486</a>.","apa":"Ion, A., Carreira, J., &#38; Sminchisescu, C. (2012). Image segmentation by figure-ground composition into maximal cliques. Presented at the ICCV: International Conference on Computer Vision, Barcelona, Spain: IEEE. <a href=\"https://doi.org/10.1109/ICCV.2011.6126486\">https://doi.org/10.1109/ICCV.2011.6126486</a>","ista":"Ion A, Carreira J, Sminchisescu C. 2012. Image segmentation by figure-ground composition into maximal cliques. ICCV: International Conference on Computer Vision, 6126486.","ama":"Ion A, Carreira J, Sminchisescu C. Image segmentation by figure-ground composition into maximal cliques. In: IEEE; 2012. doi:<a href=\"https://doi.org/10.1109/ICCV.2011.6126486\">10.1109/ICCV.2011.6126486</a>","short":"A. Ion, J. Carreira, C. Sminchisescu, in:, IEEE, 2012.","mla":"Ion, Adrian, et al. <i>Image Segmentation by Figure-Ground Composition into Maximal Cliques</i>. 6126486, IEEE, 2012, doi:<a href=\"https://doi.org/10.1109/ICCV.2011.6126486\">10.1109/ICCV.2011.6126486</a>.","ieee":"A. Ion, J. Carreira, and C. Sminchisescu, “Image segmentation by figure-ground composition into maximal cliques,” presented at the ICCV: International Conference on Computer Vision, Barcelona, Spain, 2012."},"date_published":"2012-01-12T00:00:00Z"}