Sudhir Yarram

I am a PhD candidate in Computer Science Department at the University at Buffalo advised by Prof. Junsong Yuan. My research focuses on designing video perception and forecasting models for autonomous systems that will enable autonomous systems to perceive and forecast in the real world just as humans are able, and ultimately surpass humans ability to forecast. My research spans three core directions: Video Perception, where I develop efficient and domain-adaptable models; Future Forecasting, leveraging video perception to accurately predict future scenes; and Controllable Future Forecasting, integrating vision with agent intentions expressed through language to enhance forecasting controllability.

I've had the opportunity to intern at Amazon (with Tian Lan and Hui Liang). Before that, I worked at Adobe. I received my Bachelor's degree in Computer Science from IIIT Hyderabad in 2015. In my free time, I enjoy reading, running, and cricket.

🚨🚨 I'm on the job market for industry positions starting Jan 2025! Please reach out (sudhirya at buffalo dot edu) if you think I might be a good fit for your team.


2011-2015
2019-2024
2015-2017
Summer 2021, 2022

News


  • [July '22] Our journal paper accepted to MVA.


Publications (Google Scholar)


Forecasting Future Videos from Novel Views via Disentangled 3D Scene Representation

ECCV 2024

Sudhir Yarram, Junsong Yuan

Project Page

Adversarial Structured Prediction for Domain-Adaptive Semantic Segmentation

MVA 2022

Sudhir Yarram, Junsong Yuan, Ming Yang

Efficient Video Instance Segmentation via Tracklet Query and Proposal

CVPR 2022

Jialian Wu, Sudhir Yarram, Hui Liang, Tian Lan, Junsong Yuan, Jayan Eledath, Gerard Medioni

Deformable vistr: Spatio temporal deformable attention for video instance segmentation

ICASSP 2022

Sudhir Yarram, Jialian Wu, Pan Ji, Yi Xu, Junsong Yuan

Joint Global-Local Alignment for Domain Adaptive Semantic Segmentation

ICASSP 2022

Sudhir Yarram, Ming Yang, Junsong Yuan, Chunming Qiao

Semantic segmentation datasets for resource constrained training

NCVPRIPG 2019

Ashutosh Mishra*, Sudhir Kumar*, Tarun Kalluri*, Girish Varma, Anbumani Subramaian, Manmohan Chandraker, CV Jawahar

City-Scale Road Audit System using Deep Learning

IROS 2018

Sudhir Yarram, Girish Varma, CV Jawahar