I am a PhD student at Arizona State University, where I work on vision & language.
I am co-advised by Yezhou Yang and Chitta Baral.
In a previous life, I got my Masters from Carnegie Mellon University where I worked with Aswin Sankaranarayanan.
Even before that, I did my Bachelors at BITS Pilani India where I did a bunch of different things.
Google Scholar  /
I work on computer vision, and in order to "understand" the visual world, work at the intersection of vision and language.
Currently I'm working on question answering.
Light makes images, symbols make language, and certain advanced apes assign meaning to this seemingly arbitrary world.
I am investigating how we can get computers to do the same.
More specifically, I am investigating the following questions:
- How can we incorporate semantic concepts from language for assigning meaning to visible things ?
- Can we (and/or how can we) assign meaning without language?
- What are the underlying building blocks, necessary conditions, and annoying constraints that we can use for assigning meaning to the visual world ?
Cooking With Blocks : A Recipe for Visual Reasoning on Image-Pairs
CVPR 2019 Workshop, Vision Meets Cognition
Blocksworld Revisited: Learning and Reasoning to Generate Event-Sequences from Image Pairs
preprint, arxiv 2019
We introduce the BIRD dataset and the Image-based Event Sequencing, and propose a modular approach that possesses the capability of inductive generalization.
Vision beyond Pixels
IJCAI 2019, Doctoral Consortium
Awards & Honors
- IJCAI Doctoral Consortium Travel Award, (IJCAI 2019, Macao)
- CIDSE Travel Grant Award, (CVPR 2019, Long Beach CA)
- Inducted, Eta Kappa Nu Sigma Chapter (Carnegie Mellon University, 2017)
- National Talent Scholarship, (Govt. of India, 2007-2015)
- Mentor for Incoming PhD Students, Graduate Student Mentorship Program (GSMP), ASU
- Research Mentor: CSE485 Capstone (Cognitive Vision, Vision&Language)
ASU CSE310: Data Structures and Algorithms (Taught Recitations)
ASU CSE408: Multimedia Information Systems (TA)
ASU CSE110: Principles of Programming (Taught Labs)
ASU CSE576: Natural Language Processing (Mentored Class Projects)
BITS CTE: Advanced Image Processing (co-Instructor)
- Student Mentor:
BITS Goa Peer Mentorship Program (first installment), 2014
Collaborators, Friends, Cool People
- (MS Research): Shivakshit Patri (2019 Spring), Aadhavan Sadasivam (2019-20), Arnav Chakravarthy (2020 - )
- (BS Capstone): Jace Lord, Paul Butler, Sagarika Pannase, Aashwin Ranjan, William Tith (2019-20)
Kuldeep Kulkarni (now at Adobe),
|Arizona State University
|Carnegie Mellon University
|IEEE Eta Kappa Nu
- Summer 2020: I will be interning at Lawrence Livermore National Labs mentored by Rushil Anirudh
- Aug 2019: "Vision beyond Pixels", Talk at IJCAI 2019 Doctoral Consortium, Received IJCAI DC Travel Award
- July 2019: "Reasoning about Objects and Actions via Block-Play", Talk at Telluride 2019 Neuromorphic Cognition Engineering Workshop
- June 2019: "Cooking with Blocks", Workshop paper presented at CVPR 2019, Received CIDSE Travel Grant for attending
- May 2019: "Blocksworld Revisited" Preprint available on ARXIV. Webpage for "Blocksworld Image Reasoning Dataset" is now online
- Aug 2018: Joined ASU Active Perception Group as a PhD student with Yezhou Yang. Co-advised by Chitta Baral.
- May 2018: Research Internship at Snap Research, Seattle with Guru Krishnan and Shree Nayar
- Apr 2018: "Deep Learning Methods in Imaging and Computer Vision", Tutorial Talk at BITS Pilani - Goa Campus
- Dec 2017: Graduated with M.S. (ECE) from Carnegie Mellon University (with Eta Kappa Nu Honors)
- Jan 2017: Joined Image Sciences Lab at CMU as a Graduate Researcher with Aswin Sankaranarayanan.
Template stolen (with freedom) from this guy