Over the recent years, there has been an increasing interest in large-scale classification of remote sensing images. In this context, the Inria Aerial Image Labeling Benchmark has been released online in December 2016. In this paper, we discuss the outcomes of the first year of the benchmark contest, which consisted in dense labeling of aerial images into building / not building classes, covering areas of five cities not present in the training set. We present four methods with the highest numerical accuracies, all four being convolutional neural network approaches. It is remarkable that three of these methods use the U-net architecture, which has thus proven to become a new standard in image dense labeling.
Online discussions forums, known as forums for short, are conversational social cyberspaces constituting rich repositories of content and an important source of collaborative knowledge. However, most of this knowledge is buried inside the forum infrastructure and its extraction is both complex and difficult. The ability to automatically rate postings in online discussion forums, based on the value of their contribution, enhances the ability of users to find knowledge within this content. Several key online discussion forums have utilized collaborative intelligence to rate the value of postings made by users. However, a large percentage of posts go unattended and hence lack appropriate rating.In this paper, we focus on automatic rating of postings in online discussion forums. A set of features derived from the posting content and the threaded discussion structure are generated for each posting. These features are grouped into five categories, namely (i) relevance, (ii) originality, (iii) forum-specific features, (iv) surface features, and (v) posting-component features. Using a non-linear SVM classifier, the value of each posting is categorized into one of three levels High, Medium, or Low. This rating represents a seed value for each posting that is leveraged in filtering forum content. Experimental results have shown promising performance on forum data.
The Aging process is a non-reversible process, causing human face characteristics to change over time as hair whitening, muscles drop and wrinkles. Recently, age estimation from facial images has emerged as a prominent research area. One of the most successful works is based on biologically inspired features (BIF). In this paper we extend BIF by incorporating fine detailed facial features, automatic initialization using active shape models and analyzing a more complete facial area by including the forehead details. Furthermore, we combine regression-based and classification-based models and test them experimentally on standard datasets showing the superiority of our proposed algorithm (extended BIF -EBIF) over the state-of-the-art methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.