A
Amit Goyal
Researcher at University of Maryland, College Park
Publications - 23
Citations - 1505
Amit Goyal is an academic researcher from University of Maryland, College Park. The author has contributed to research in topics: Sketch & Context (language use). The author has an hindex of 15, co-authored 23 publications receiving 1377 citations. Previous affiliations of Amit Goyal include International Institute of Information Technology, Hyderabad & Yahoo!.
Papers
More filters
Proceedings Article
Midge: Generating Image Descriptions From Computer Vision Detections
Margaret Mitchell,Jesse Dodge,Amit Goyal,Kota Yamaguchi,Karl Stratos,Xufeng Han,Alyssa Mensch,Alexander C. Berg,Tamara L. Berg,Hal Daumé +9 more
TL;DR: A novel generation system that composes humanlike descriptions of images from computer vision detections by leveraging syntactically informed word co-occurrence statistics and automatically generating some of the most natural image descriptions to date.
Proceedings ArticleDOI
Understanding and predicting importance in images
Alexander C. Berg,Tamara L. Berg,Hal Daumé,Jesse Dodge,Amit Goyal,Xufeng Han,Alyssa Mensch,Margaret Mitchell,Aneesh Sood,Karl Stratos,Kota Yamaguchi +10 more
TL;DR: This paper explores how a number of factors relate to human perception of importance using what people describe as a proxy for importance, and builds models to predict what will be described about an image given either known image content, or image content estimated automatically by recognition systems.
Journal ArticleDOI
A Comprehensive Profile of Clinical, Psychiatric, and Psychosocial Characteristics of Patients with Psychogenic Nonepileptic Seizures
TL;DR: To attain a comprehensive profile of clinical, psychiatric and psychosocial characteristics of patients with psychogenic nonepileptic seizures, and to assess the relation of these factors to NES outcome.
Proceedings Article
Automatically Producing Plot Unit Representations for Narrative Text
TL;DR: This research explores whether current NLP technology can be used to automatically produce plot unit representations for narrative text by creating a system called AESOP, which exploits a variety of existing resources to identify affect states and applies "projection rules" to map the affect states onto the characters in a story.
Proceedings Article
Sketch Algorithms for Estimating Point Queries in NLP
TL;DR: This work describes 10 sketch methods, including existing and novel variants, and evaluates several sketches on three important NLP problems, showing that one sketch performs best for all the three tasks.