2014 · 69 citations · 35 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionImage LabelingImage SegmentationScene UnderstandingSemantic SegmentationVisual SemanticsCo-occurrence AnalysisLabelsMean-field ApproximationMean-field TheoryObject SegmentationSemantic Scene Understanding
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.
35
The Pascal Visual Object Classes (VOC) Challenge
Mark Everingham, Luc Van Gool, Christopher K. I. Williams et al. · International Journal of Computer Vision · 2009 · 19.5K citations · Full text
Selective Search for Object Recognition
Jasper Uijlings, Koen E. A. van de Sande, Theo Gevers et al. · International Journal of Computer Vision · 2013 · 6.1K citations · Full text
Carsten Rother, Vladimir Kolmogorov, Andrew Blake · ACM Transactions on Graphics · 2004 · 5.8K citations · Full text