A
Ayush Chopra
Researcher at Massachusetts Institute of Technology
Publications - 38
Citations - 325
Ayush Chopra is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Computer science & Population. The author has an hindex of 7, co-authored 30 publications receiving 134 citations. Previous affiliations of Ayush Chopra include Adobe Systems & Delhi Technological University.
Papers
More filters
Journal ArticleDOI
Public health impact of delaying second dose of BNT162b2 or mRNA-1273 covid-19 vaccine: simulation agent based modeling study.
Santiago Romero-Brufau,Santiago Romero-Brufau,Ayush Chopra,Alex J Ryu,Esma S. Gel,Ramesh Raskar,Walter K. Kremers,Karen S. Anderson,Jayakumar Subramanian,Balaji Krishnamurthy,Abhishek Singh,Kalyan S. Pasupathy,Yue Dong,John C. O’Horo,Walter R. Wilson,Oscar J.L. Mitchell,Thomas Kingsley +16 more
TL;DR: In this paper, a simulation agent-based modeling study was conducted to estimate population health outcomes with delayed second dose versus standard schedule of SARS-CoV-2 mRNA vaccination.
Proceedings ArticleDOI
SieveNet: A Unified Framework for Robust Image-Based Virtual Try-On
TL;DR: This work introduces a multi-stage coarse-to-fine warping network to better model fine grained intricacies (while transforming the try-on cloth) and train it with a novel perceptual geometric matching loss to improve the texture transfer network.
Proceedings ArticleDOI
SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation
TL;DR: This work proposes to jointly predict the support and query masks to force the support features to share characteristics with the query features, and presents a framework - SimPropNet - to bridge gaps in the utilization of this similarity information in existing methods.
Proceedings ArticleDOI
Powering Robust Fashion Retrieval With Information Rich Feature Embeddings
TL;DR: A Grid Search Network (GSN) for learning feature embeddings for fashion retrieval significantly outperforms existing state-of-art methods on benchmark fashion datasets and extends the reinforcement learning based strategy to learn custom kernel functions for SVM based classification over FashionMNIST and MNIST datasets, showing improved performance.
Proceedings ArticleDOI
Powering Virtual Try-On via Auxiliary Human Segmentation Learning
TL;DR: This work proposes to use auxiliary learning to power an existing state-of-the-art virtual try-on network and leverage prediction of human semantic segmentation as an auxiliary task and shows that it allows the network to better model the bounds of the clothing item and human skin, thereby producing a better fit.