Prajwal Gatti

I am a first year Ph.D. student at the University of Bristol advised by Prof. Dima Damen, in the Machine Learning and Computer Vision Group. My research interests are in AI for video understanding, specifically in the areas of long-term video understanding, egocentric video understanding and improving long-tailed performance of video recognition methods.

Prior to this, I was a Research Assistant at the Indian Institute of Technology Jodhpur advised by Prof. Anand Mishra where I explored the problems of vision-augemented table-to-text generation, cross-modal image retrieval among other vision-language problems.

I also briefly interned at the Center for Neuroscience, Indian Institute of Science where I worked on EEG Brain-Computer Interfaces under the advise of Prof. Sridharan Devarajan.

I received my B.E. in Information Science and Engineering at Dayananda Sagar College of Engineering in 2020.

Email  /  LinkedIn  /  Google Scholar  /  GitHub

News

Selected Publications
PontTuset Show Me the World in My Language: Establishing the First Baseline for Scene-Text to Scene-Text Translation
Shreyas Vaidya*, Arvind Kumar Sharma*, Prajwal Gatti, Anand Mishra
ICPR 2024
paper / project page

PontTuset Composite Sketch+Text Queries for Retrieving Objects with Elusive Names and Complex Interactions
Prajwal Gatti, Kshitij Parikh, Dhriti Paul, Manish Gupta, Anand Mishra
AAAI 2024
paper / poster / project page

PontTuset Towards Making Flowchart Images Machine Interpretable
Shreya Shukla, Prajwal Gatti, Yogesh Kumar, Vikash Yadav, Anand Mishra
ICDAR 2023
paper / pre-print / project page

PontTuset VisToT: Vision-Augmented Table-to-Text Generation
Prajwal Gatti, Anand Mishra, Manish Gupta, Mithun Das Gupta
EMNLP 2022
paper / poster / project page

PontTuset COFAR: Commonsense and Factual Reasoning in Image Search
Prajwal Gatti, Abhirama Penamakuri, Revant Teotia, Anand Mishra, Shubhashis Sengupta, Roshni Ramnani
AACL-IJCNLP 2022
paper / poster / project page

Template credits: this and this