no code implementations • Findings (ACL) 2022 • Navita Goyal, Roodram Paneri, Ayush Agarwal, Udit Kalani, Abhilasha Sancheti, Niyati Chhaya
We leverage causal inference techniques to identify causally significant aspects of a text that lead to the target metric and then explicitly guide generative models towards these by a feedback mechanism.
no code implementations • 27 Feb 2024 • Mansi Goel, Ayush Agarwal, Shubham Agrawal, Janak Kapuriya, Akhil Vamshi Konam, Rishabh Gupta, Shrey Rastogi, Niharika, Ganesh Bagler
Simultaneously, we systematically cleaned and analyzed ingredient phrases from RecipeDB, the gold-standard recipe data repository, and annotated them using the Stanford NER.
no code implementations • 8 Mar 2021 • Anatoly Shusterman, Ayush Agarwal, Sioli O'Connell, Daniel Genkin, Yossi Oren, Yuval Yarom
To assess the effectiveness of this approach, in this work we seek to identify those JavaScript features which are essential for carrying out a cache-based attack.
Website Fingerprinting Attacks Cryptography and Security
no code implementations • 24 Oct 2020 • Navita Goyal, Roodram Paneri, Ayush Agarwal, Udit Kalani, Abhilasha Sancheti, Niyati Chhaya
We leverage causal inference techniques to identify causally significant aspects of a text that lead to the target metric and then explicitly guide generative models towards these by a feedback mechanism.
no code implementations • 14 Dec 2019 • Dhritimaan Das, Ayush Agarwal, Pratik Chattopadhyay, Lipo Wang
Over the past decade, several computer vision-based gait recognition approaches have been proposed in which walking information corresponding to a complete gait cycle has been used to construct gait features for person identification.
no code implementations • 25 Mar 2019 • Mansi Goel, Ayush Agarwal, Deepak Thukral, Tanmoy Chakraborty
This paper presents Fiducia, a food review system involving a pipeline which processes restaurant-related reviews obtained from Zomato (India's largest restaurant search and discovery service).
no code implementations • 13 Feb 2018 • Prerna Agarwal, Richa Verma, Ayush Agarwal, Tanmoy Chakraborty
In this paper, we propose DyPerm, the first dynamic community detection method which optimizes a novel community scoring metric, called permanence.
Social and Information Networks Physics and Society
no code implementations • 13 Dec 2017 • Le Hou, Ayush Agarwal, Dimitris Samaras, Tahsin M. Kurc, Rajarsi R. Gupta, Joel H. Saltz
We propose a unified pipeline that: a) generates a set of initial synthetic histopathology images with paired information about the nuclei such as segmentation masks; b) refines the initial synthetic images through a Generative Adversarial Network (GAN) to reference styles; c) trains a task-specific CNN and boosts the performance of the task-specific CNN with on-the-fly generated adversarial examples.