<div class="section abstract"><div class="htmlview paragraph">There is a recurring need for automatic Information Retrieval (IR) from quality documents, price tags, part markings, receipts, purchase orders and technical manuals - which are otherwise non-parsable. IR coupled with search functionalities has a wide range of applications from warehouses, marketplaces to even shop floors in the aviation sector. It helps in semi-automating workflows like document reviews, quality checks, collaborative Q&As and contextual extraction of information. These workflows make laborious tasks more intuitive and easier, thereby reducing the workload of the engineers using them. The paper describes an AI based IR platform which caters to the aforesaid scenarios in a scalable manner and integrates seamlessly with similar problems across different domains. It is the core to many different workflows that are currently used to detect paperwork mismatch for aviation parts, to auto-catalogue large amounts of documents, to detect the presence of sensitive information in documents, to digitize scanned documents, detecting presence of stamps in faceplates. Its capabilities can be extended beyond documents to other non-interactive and non-parsable contents as well. The intent of this paper is to describe different AI modules and services in this AI platform towards enabling Smart Factory and Industry 4.0.</div></div>
Sketching is a fundamental human cognitive ability. Deep Neural Networks (DNNs) have achieved the state-of-the-art performance in recognition tasks like image recognition, speech recognition etc. but have not made significant progress in generating stroke-based sketches a.k.a sketches in vector format. Though there are Variational Auto Encoders (VAEs) for generating sketches in vector format, there is no Generative Adversarial Network (GAN) architecture for the same. In this paper, we propose a standalone GAN architecture called SkeGAN and a hybrid VAE-GAN architecture called VASkeGAN, for sketch generation in vector format. SkeGAN is a stochastic policy in Reinforcement Learning (RL), capable of generating both multidimensional continuous and discrete outputs. VASkeGAN draws sketches by coupling the efficient representation of data by VAE with the powerful generating capabilities of GAN. We have validated that SkeGAN and VASkeGAN generate visually appealing sketches with minimal scribble effect and is comparable to a recent work titled Sketch-RNN.
CCS CONCEPTS• Computing methodologies → Sequential decision making; Image representations.
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.