July 2019: Excited to present our paper on event detection using multi-aspect attention at the DLRL Summer School in Edmonton, Canada!
July 2019: Featured in DAC News!
May 2019: I'll be spending another wonderful summer at Netflix working on Neural Machine Translation. Stay tuned for our paper!
Jan 2019: 1 paper accepted to The Web Conference 2019 !
Jan 2019: Best paper award at IUI 2019 !
May 2018: I'll be spending the summer at Netflix working on Neural Machine Translation hosted by Ritwik Kumar, Boris Chen and Vinith Misra.
Aug 2017: Our submission for automatic narrative generation from a large collection of documents selected for the final round of ODNI Xpress Challenge !
April 2017: I'll be joining Discovery Analytics Centre as a PhD student in summer !
April 2017: The undergraduate students that I supervised and worked with on the PhotoSleuth project won 1st place at VTURCS Spring Symposium.
Nov 2016: Presented our paper and poster on understanding human performance in image geolocation at the GroupSight workshop at HCOMP 2016 !
June 2016: Student Volunteer at CVPR 2016 at Las Vegas, Nevada.

I am a PhD student in the Computer Science department at Virginia Tech's College of Engineering, working with Prof. Naren Ramakrishnan.
My research falls under the umbrella of Natural Language Processing, Deep Learning and Data Mining. I'm interested in developing AI systems for natural language understanding and generation. I also love developing Django webapps.

I am affiliated with Discovery Analytics Centre (DAC) . Before joining DAC, I have worked at the Crowd Intelligence Lab at Virginia Tech.

Prior to joining grad school, I double majored in Computer Science and Mathematics from Birla Institute of Technology and Science (BITS), Pilani. After graduating I worked at Dreamworks Animation as an R&D Engineer. Some of the places I have interned at during my undergrad include Dreamworks Animation, Global Logic and Harish Chandra Research Institute. I was a recipient of the MITACS Globalink Research Internship Grant in summer 2013.

My research is graciously supported by DARPA and NSF.


Event Detection Using Hierarchical Multi-Aspect Attention
Event encoding can be viewed as a hierarchical task where the coarser level task is event detection and the fine-grained task is one of event encoding. In this work we present a novel attention mechanism and show its effectivenes on the event detection task when plugged into hierarchical attention models.
Sneha Mehta, M. Raihanul, Huzefa Rangwala, Naren Ramakrishnan
The Web Conference 2019
(Acceptance Rate: 16%)
PhotoSleuth: Combining Human Expertise and Face Recognition to Identify Historical Portraits
We created Photo Sleuth, a web-based platform that combines crowdsourced human expertise and automated face recognition to support Civil War portrait identification.
Vikram Mohanty, David Thames, Sneha Mehta, Kurt Luther
ACM IUI 2019
An Exploratory Study of Human Performance in Image Geolocation
We perform an exploratory study of image geolocation tasks performed by novice and expert humans on a diverse image dataset we developed. Our findings include a model of sensemaking strategies, a taxonomy of image clues, and key challenges and design ideas for image sensemaking and crowdsourcing.
Sneha Mehta, Chris North, Kurt Luther
GroupSight workshop at HCOMP 2016


Siamese Network for binary VQA
We study the performance of a siamese network based deep neural architecture on the task of binary(Yes/No) visual question answering. Comparing the performance of a siamese network based VQA model to a non-siamese VQA model we find that having a pairwise loss helps perform better than a loss from a non-siamese VQA network.
Sneha Mehta, Yash Goyal (Project advisor: Prof. Devi Parikh).
Extracting Topics from Tweets and Webpages
We develop the topic analysis component of a robust Information Retrieval system for search and retrieval of large-scale tweets and webpages built on top of Solr, a general purpose open-source search engine. Our contribution enables semantic search and retrieval of tweets and webpages based on topics.
Sneha Mehta, Radha Krishnan Vinayagam (Project advisor: Prof. Edward Fox).
Birds in a forest
We employ a random forest approach for bird species identification. First we train 25 SVMs to predict 25 bird features for our dataset images. Then we train a random-forest to identify the specific bird species. We used the CUB-200-2011 bird dataset for this task.
Sneha Mehta, Aditya Pratapa, Phillip Summers (Project advisor: Prof. Bert Huang).
Automatic image geolocation
Automatic estimation of geographic coordinates from an image using computer vision. We use pre-deep learning era feature detectors such as SIFT, GIST and RGB features. We extract these features followed by a nearest neighbour retrieval. The implementation is based on im2gps. SIFT(SURF) and Color features computed using OpenCV 3.0. GIST descriptor computed using computer vision feature extraction toolbox.
Sneha Mehta (Project advisor: Prof. Devi Parikh)

Short Projects

Seam Carving
Seam-carving is a dynamic programming based algorithm for content-aware image resizing developed by Ariel Shamir. In the above example, the algorithm reduces the width of the image by removing vertical seams of pixels between the girl and the cliff edges. > Code
Image Warping
Creating image panorama by image warping based on homographies. In the first example (left), the image on the bottom is the panorama created by warping (by computing a homography matrix) and stitching together the three images above. In the second example(right), a photo of mine (a really embarrasing one now I realize) was warped and merged onto a billboard in a Times Square image. Find code and more examples > Code


Presenting at GroupSight (Workshop on Human Computation for Image and Video Analysis), HCOMP 2016 at Austin, Texas.


An interview summarizing my early life as an athlete.
Copyright © Sneha Mehta (Me) 2015. All rights reserved.