whoami

Hi! If you are from the Deep Learning Summer School, please check out my CV here.

My current projects are:

  • Image Captioning:
    • Working towards developing captions for images using attention models, the results from MS COCO leaderboard will be shortly added.
  • Video Question Answering:
    • Implementing different language models to make the question answering more dynamic.
  • Intelligent and Proactive Dialog (Intelligent Chat Bot):
    • Which can carry context from one dialog exchange to another and can use this information to initiate a new dialog.
    • This is being developed using memory networks and is tested on an indigenous CMU corpus of dialogs also developed by me.
  • Repodoctor for the Mozilla Science Lab, to support open research.
  • The EESEN-Transcriber in which my work is:
    • To add the video indexing based on the words spoken in the video
    • To develop real time video summarization
    • To be able to write out the differences in text format between two video clusters or two videos.
    • Video Question Answering
    • This project will be added to the SpeechKitchen.org


blog comments powered by Disqus

Published

19 April 2016

Tags