Virginia Tech

About: Virginia Tech is a education organization based out in Blacksburg, Virginia, United States. It is known for research contribution in the topics: Population & Poison control. The organization has 42053 authors who have published 95234 publications receiving 2905142 citations. The organization is also known as: VT & Virginia Polytechnic Institute and State University.

VQA: Visual Question Answering

Abstract: We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer. Mirroring real-world scenarios, such as helping the visually impaired, both the questions and answers are open-ended. Visual questions selectively target different areas of an image, including background details and underlying context. As a result, a system that succeeds at VQA typically needs a more detailed understanding of the image and complex reasoning than a system producing generic image captions. Moreover, VQA is amenable to automatic evaluation, since many open-ended answers contain only a few words or a closed set of answers that can be provided in a multiple-choice format. We provide a dataset containing ~0.25M images, ~0.76M questions, and ~10M answers (www.visualqa.org), and discuss the information it provides. Numerous baselines for VQA are provided and compared with human performance.

CIDEr: Consensus-based image description evaluation

Abstract: Automatically describing an image with a sentence is a long-standing challenge in computer vision and natural language processing. Due to recent progress in object detection, attribute classification, action recognition, etc., there is renewed interest in this area. However, evaluating the quality of descriptions has proven to be challenging. We propose a novel paradigm for evaluating image descriptions that uses human consensus. This paradigm consists of three main parts: a new triplet-based method of collecting human annotations to measure consensus, a new automated metric that captures consensus, and two new datasets: PASCAL-50S and ABSTRACT-50S that contain 50 sentences describing each image. Our simple metric captures human judgment of consensus better than existing metrics across sentences generated by various sources. We also evaluate five state-of-the-art image description approaches using this new protocol and provide a benchmark for future comparisons. A version of CIDEr named CIDEr-D is available as a part of MS COCO evaluation server to enable systematic evaluation and benchmarking.

A Simple Higher-Order Theory for Laminated Composite Plates

Abstract: A higher-order shear deformation theory of laminated composite plates is developed. The theory contains the same dependent unknowns as in the first-order shear deformation theory of Whitney and Pagano (1970), but accounts for parabolic distribution of the transverse shear strains through the thickness of the plate. Exact closed-form solutions of symmetric cross-ply laminates are obtained and the results are compared with three-dimensional elasticity solutions and first-order shear deformation theory solutions. The present theory predicts the deflections and stresses more accurately when compared to the first-order theory.

The SEED and the Rapid Annotation of microbial genomes using Subsystems Technology (RAST)

Abstract: In 2004, the SEED (http://pubseed.theseed.org/) was created to provide consistent and accurate genome annotations across thousands of genomes and as a platform for discovering and developing de novo annotations. The SEED is a constantly updated integration of genomic data with a genome database, web front end, API and server scripts. It is used by many scientists for predicting gene functions and discovering new pathways. In addition to being a powerful database for bioinformatics research, the SEED also houses subsystems (collections of functionally related protein families) and their derived FIGfams (protein families), which represent the core of the RAST annotation engine (http://rast.nmpdr.org/). When a new genome is submitted to RAST, genes are called and their annotations are made by comparison to the FIGfam collection. If the genome is made public, it is then housed within the SEED and its proteins populate the FIGfam collection. This annotation cycle has proven to be a robust and scalable solution to the problem of annotating the exponentially increasing number of genomes. To date, >12 000 users worldwide have annotated >60 000 distinct genomes using RAST. Here we describe the interconnectedness of the SEED database and RAST, the RAST annotation pipeline and updates to both resources.

Self-Concept in Consumer Behavior: A Critical Review

Abstract: The self-concept literature in consumer behavior can be characterized as fragmented, incoherent, and highly diffuse. This paper critically reviews self-concept theory and research in consumer behavior and provides recommendations for future research.