Traditional architectures for solving computer vision problems and the degree of success they enjoyed have been heavily reliant on hand-crafted features. However, of late, deep learning techniques have offered a compelling alternative -that of automatically learning problem-specific features. With this new paradigm, every problem in computer vision is now being re-examined from a deep learning perspective. Therefore, it has become important to understand what kind of deep networks are suitable for a given problem. Although general surveys of this fast-moving paradigm (i.e., deep-networks) exist, a survey specific to computer vision is missing. We specifically consider one form of deep networks widely used in computer vision -convolutional neural networks (CNNs). We start with "AlexNet" as our base CNN and then examine the broad variations proposed over time to suit different applications. We hope that our recipe-style survey will serve as a guide, particularly for novice practitioners intending to use deep-learning techniques for computer vision.
We propose a novel image representation, termed Attribute-Graph, to rank images by their semantic similarity to a given query image. An Attribute-Graph is an undirected fully connected graph, incorporating both local and global image characteristics. The graph nodes characterise objects as well as the overall scene context using mid-level semantic attributes, while the edges capture the object topology. We demonstrate the effectiveness of Attribute-Graphs by applying them to the problem of image ranking. We benchmark the performance of our algorithm on the 'rPascal' and 'rImageNet' datasets, which we have created in order to evaluate the ranking performance on complex queries containing multiple objects. Our experimental evaluation shows that modelling images as Attribute-Graphs results in improved ranking performance over existing techniques.
An earthquake of moment magnitude M w 5.7 shook the northeastern region of India on 3 January 2017 at 14 h:39 min:0.5 s local time. The duration of the tremor lasted for about 5-6 s and had its epicenter in Dhalai District, Tripura, India. Even though the earthquake was of moderate magnitude, it caused damage to several masonry dwellings in Tripura and triggered soil liquefaction, lateral spreading, and landslides near the epicentral area. The sand boils containing appreciable amount of silts were ejected to the ground surface at the Kanchanbari and Kumarghat area due to the liquefaction-induced upward ground water flow. This is possibly the first liquefaction evidence in India induced due to a moderate earthquake magnitude of M w 5.7. This paper reports the field reconnaissance observations of geotechnical effects and damage to buildings following a shallow, strike-slip earthquake in northeast India on 3 January 2017. In addition, the distribution of surface peak ground acceleration of the earthquake estimated from the empirical equations based on the available data is evaluated and discussed.
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.