avatar
I am a fifth year PhD student in the CS department at the Intelligent Visual Interfaces lab in Rutgers University . I work on Multi-modal A.I., under the supervision of Dr. Mubbasir Kapadia and Dr. Gerard De Melo. Particularly, I am interested in joint understanding of images/videos and abstract/narrative text with applications to multimodal story comprehension. More specifically, it involves developing neural network models to learn various factors that govern multimodal story comprehension and evaluating on tasks such as story illustration, visual storytelling, image captioning and text-to-image retreival/generation. I previously worked on authenticating visual media content such as videos and images using passive image analysis techniques and Machine Learning.

News

  • April 25, 2021: We received the Best Paper Award for our paper "Exploiting Image Text Synergy for Contextual Image Captioning", in LANTERN workshop associated with EACL 2021.
  • April 10, 2021: Code and Dataset for our paper "Exploiting Image Text Synergy for Contextual Image Captioning" is available here
  • April 01, 2021: Our paper "Exploiting Image Text Synergy for Contextual Image Captioning" is accepted in LANTERN workshop associated with EACL 2021.
  • Nov 10, 2020: Code for our arXiv paper "GitEvlove: Predicting the Evolution of GitHub Repositories" is available here.
  • Oct 10, 2020: Our arXiv paper on "GitEvlove: Predicting the Evolution of GitHub Repositories" is out here.
  • May 10, 2020: I will be a Computer Vision Research Intern at Adobe Research working on Visual Storytelling during summer 2020
  • ...