Dense Semantic Image Segmentation with Objects and Attributes.
CVPR(2014)
摘要
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.
更多查看译文
关键词
materials,approximation theory,visual appearance,visualization,object recognition,image segmentation,correlation,hierarchical model,semantics
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要