Learn More
Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as image classification and object detection. This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification (also called " semantic image segmentation "). We show(More)
In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or 'atrous convolution', as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly(More)
Recent years have witnessed a proliferation of large-scale knowledge bases, including Wikipedia, Freebase, YAGO, Microsoft's Satori, and Google's Knowledge Graph. To increase the scale even further, we need to explore automatic methods for constructing knowledge bases. Previous approaches have primarily focused on text-based extraction, which can be very(More)
AN IMPORTANT economic question is whether poor countries or regions tend to converge toward rich ones. We want to know, for example, whether the poor countries of Africa, South Asia, and Latin America will grow faster than the developed countries, whether the south of Italy will become like its north, whether and how fast the eastern regions of Germany will(More)
We propose a method that can generate an unambiguous description (known as a referring expression) of a specific object or region in an image, and which can also comprehend or interpret such an expression to infer which object is being described. We show that our method outperforms previous methods that generate descriptions of objects without taking into(More)
We present a system which can recognize the contents of your meal from a single image, and then predict its nutritional contents, such as calories. The simplest version assumes that the user is eating at a restaurant for which we know the menu. In this case, we can collect images offline to train a multi-label classifier. At run time, we apply the(More)
—Relational machine learning studies methods for the statistical analysis of relational, or graph-structured, data. In this paper, we provide a review of how such statistical models can be " trained " on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges in the graph). In particular, we(More)
—Relational machine learning studies methods for the statistical analysis of relational, or graph-structured, data. In this paper, we provide a review of how such statistical models can be " trained " on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges in the graph). In particular, we(More)