<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Zheng, Shuai</style></author><author><style face="normal" font="default" size="100%">Cheng, Ming Ming</style></author><author><style face="normal" font="default" size="100%">Warrell, Jonathan</style></author><author><style face="normal" font="default" size="100%">Sturgess, Paul</style></author><author><style face="normal" font="default" size="100%">Vineet, Vibhav</style></author><author><style face="normal" font="default" size="100%">Carsten Rother</style></author><author><style face="normal" font="default" size="100%">Torr, Philip H.S.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Dense semantic image segmentation with objects and attributes</style></title><secondary-title><style face="normal" font="default" size="100%">Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Attributes</style></keyword><keyword><style  face="normal" font="default" size="100%">Image segmentation</style></keyword><keyword><style  face="normal" font="default" size="100%">Object recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">Scene Understanding</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2014</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://www.robots.ox.ac.uk/˜tvg/http://tu-dresden.de/inf/cvld</style></url></web-urls></urls><pages><style face="normal" font="default" size="100%">3214–3221</style></pages><isbn><style face="normal" font="default" size="100%">9781479951178</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">The concepts of objects and attributes are both important for describing images precisely, since verbal descriptions often contain both adjectives and nouns (e.g. 'I see a shiny red chair'). In this paper, we formulate the problem of joint visual attribute and object class image segmentation as a dense multi-labelling problem, where each pixel in an image can be associated with both an object-class and a set of visual attributes labels. In order to learn the label correlations, we adopt a boosting-based piecewise training approach with respect to the visual appearance and co-occurrence cues. We use a filtering-based mean-field approximation approach for efficient joint inference. Further, we develop a hierarchical model to incorporate region-level object and attribute information. Experiments on the aPASCAL, CORE and attribute augmented NYU indoor scenes datasets show that the proposed approach is able to achieve state-of-the-art results.</style></abstract></record></records></xml>