Learn More
Computer vision algorithms for individual tasks such as object recognition , detection and segmentation have shown impressive results in the recent past. The next challenge is to integrate all these algorithms and address the problem of scene understanding. This paper is a step towards this goal. We present a probabilistic framework for reasoning about(More)
Recently, Krahenbuhl and Koltun proposed an efficient inference method for densely connected pairwise random fields using the mean-field approximation for a Conditional Random Field (CRF). However, they restrict their pairwise weights to take the form of a weighted combination of Gaussian kernels where each Gaussian component is allowed to take only zero(More)
With the introduction of applications such as Google Street View, Mi-crosoft Bing Maps, the problem of scene understanding has gained more importance than ever. Image sequences from such applications consist of complex scenarios involving multiple objects, such as people, buildings, cars, bikes. One may need to simultaneously segment and identify these(More)
— This paper describes a method for producing a semantic map from multi-view street-level imagery. We define a semantic map as an overhead, or bird's eye view of a region with associated semantic object labels, such as car, road and pavement. We formulate the problem using two conditional random fields. The first is used to model the semantic image(More)
The problems of dense stereo reconstruction and object class segmentation can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are mutually informative, no attempt has been made to jointly(More)
Linear SVMs are efficient in both training and testing, however the data in real applications is rarely linearly separable. Non-linear kernel SVMs are too computationally intensive for applications with large-scale data sets. Recently locally linear classifiers have gained popularity due to their efficiency whilst remaining competitive with kernel methods.(More)
The problems of object class segmentation [2], which assigns an object label such as road or building to every pixel in the image and dense stereo reconstruction, in which every pixel within an image is labelled with a disparity [1], are well suited for being solved jointly. Both approaches formulate the problem of providing a correct labelling of an image(More)
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 seg-mentation as a dense multi-labelling problem, where each pixel in an image(More)
Humans describe images in terms of nouns and adjectives while algorithms operate on images represented as sets of pixels. Bridging this gap between how humans would like to access images versus their typical representation is the goal of image parsing, which involves assigning object and attribute labels to pixels. In this article we propose treating nouns(More)