Anurag Ghosh

I'm a Computer Vision, Imaging and Robotics PhD at Carnegie Mellon, advised by Srinivasa Narasimhan. I was co-advised by Srinivasa Narasimhan and Christoph Mertz when I got my Masters here.

I spent a few wonderful years at Microsoft Research working at the intersection of Computer Vision and Networked/Distributed Systems for Social Good. I worked with Venkat Padmanabhan, Akshay Nambi and Tanuja Ganu.

Even earlier, I studied at a vibrant and beautiful research-focused school, IIIT Hyderabad. I was advised by C. V. Jawahar and we worked on problems involving Computer Vision for Sports.

Here's my Resume.

Mentoring:If you would like to work with me, drop me an email with any specific finding you are excited by and why!

Email  /  GitHub  /  Google Scholar  /  LinkedIn

profile photo

Research

I draw inspiration from natural sciences, and my ideas revolve around computer vision, machine learning, robotics and, systems. I'm learning about the geometric and physical structure of our world to augment next generations of computational intelligence.

project image

Addressing Source Scale Bias via Image Warping for Domain Adaptation

Shen Zheng★, Anurag Ghosh★, Srinivasa Narasimhan
[Website][Paper]

Oversample salient object regions by warping source-domain images in-place during training while performing domain adaptation. Improve adaptation across geographies, lighting and weather conditions, is agnostic to the task, domain adaptation algorithm, saliency guidance, and underlying model architecture.

project image

Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection

Anurag Ghosh, N Dinesh Reddy, Christoph Mertz, Srinivasa Narasimhan
Computer Vision and Pattern Recognition Conference(CVPR), 2023 [Website][Paper]

A learnable geometry-guided prior that incorporates rough geometry of the 3D scene (a ground plane and a plane above) to resample the images for efficient object detection. This significantly improves small and far-away object detection performance while also being more efficient.

project image

Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception

Anurag Ghosh, Vaibhav Balloli, Akshay Nambi, Aditya Singh, Tanuja Ganu
Conference on Neural Information Processing Systems(NeurIPS), 2023 [Website][Paper]

Honorable Mention, Streaming Perception Challenge, CVPR 2021. [Presentation at WAD]

Learning optimal tradeoffs instead of handcrafting heuristic functions is a more natural way to design complex real-time perception systems operating within severe resource constraints.

project image

Streaming Video Analytics On The Edge With Asynchronous Cloud Support

Read about our work on Microsoft Research Blog!

Anurag Ghosh, Srinivasan Iyengar, Stephen Lee, Anuj Rathore, Venkat Padmanabhan
International Conference on Internet of Things Design and Implementation (IoTDI), 2023 [Paper]

Should we choose between offloading and on-device execution for Edge AI workloads? Our simple algorithm shows that a careful combination of the two approaches makes them complementary and achieve state-of-the-art performance.

project image

Holistic Energy Awareness for Intelligent Drones

Srinivasan Iyengar, Ravi Raj Saxena, Joydeep Pal, Bhawana Chhaglani, Anurag Ghosh, Venkat Padmanabhan, Prabhakar T. Venkata
International Conference on Systems for Energy-Efficient Built Environments (BuildSys), 2021 [Paper]
(Best Paper Runner-Up)

Holistically considering battery charecteristics and AI workload constraints for multi-drone flightpaths to develop an energy-aware scheduling system decreases energy consumed by 21.14% and mission times by 46.91% over state-of-the-art.

project image

Smartphone-based Driver License Testing

Watch Microsoft CEO Satya Nadella explain the project!

Read about our work on PM Awards Innovations Coffee Table Book! (Extracted here)

Deployed in multiple states/10+ cities in India, automatically testing hundreds of thousands of drivers at a low-cost with >99% accuracy (test verified by human operator). See Overview and Dashboard.

Instead of prohibitively expensive (>150,000$) overhead pole-mounted camera infrastructure to estimate car trajectories and judge driver manuevers, we use sub-500$ smartphones and additionally get driver state monitoring for free (face verification, mirror scanning, distraction and seatbelt checks).

Relevant Publications

[1] Smartphone-based Driver License Testing
Anurag Ghosh, Vijay Lingam, Ishit Mehta, Akshay Nambi, Venkat Padmanabhan, Satish Sangameswaran, Conference on Embedded Networked Sensor Systems (SenSys Demo), 2019 [Paper]

[2] ALT: Towards Automating Driver License Testing using Smartphones
Akshay Nambi, Ishit Mehta, Anurag Ghosh, Vijay Lingam, Venkat Padmanabhan, Conference on Embedded Networked Sensor Systems (SenSys), 2019 [Paper]
project image

Analyzing Racket Sports From Broadcast Videos

Piloted with ESPN/Star Sports at Premier Badminton League, watched by tens of millions in South East Asia.

Do we really need half a million dollars for HawkEye to understand players? Our End-to-end framework automatically tags broadcast sport videos in near-real time. Our analysis shows a single camera suffices for mining rich and actionable player data, instead of relying on existing cumbursome multi-camera setups or sensors. It is used for live broadcast visualizations.

Relevant Publications

[1] Analyzing Racket Sports From Broadcast Videos
Anurag Ghosh, IIIT Hyderabad (Master's Thesis), 2019 [Paper]

[2] Towards Structured Analysis of Broadcast Badminton Videos
Anurag Ghosh, Suriya Singh, C.V. Jawahar, Winter Conference On Applications of Computer Vision (WACV), 2018 [Paper]

[3] SmartTennisTV: An automatic indexing system for tennis
Anurag Ghosh, C.V. Jawahar, National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), 2017 [Paper]
(Best Paper Award)
project image

Signals Matter: Understanding Popularity and Impact on Stack Overflow

Arpit Merchant, Daksh Shah, Gurpreet Singh Bhatia, Anurag Ghosh, Ponnurangam Kumaraguru
The Web Conference (WWW), 2019 [Paper]

project image

Dynamic narratives for heritage tour

Anurag Ghosh ★, Yash Patel ★, Mohak Sukhwani, C.V. Jawahar
VisArt Workshop, Europen Conference on Computer Vision (ECCV), 2016 [Paper]

Press

Automated Driver License Testing

project image project image project image project image
project image project image project image project image

Badminton Analytics

project image project image project image project image



Interesting/Inspiring Links

Making computer vision systems that work: Boujou, Kinect, HoloLens, Andrew Fitzgibbon

A New Kind of Science - A 15 Year View, Stephen Wolfram

How I ran the length of every street in Pittsburgh: PAC TOM, Tom Murphy VII

Frugal Innovations for a Developing World, Bill Thies

Hints and Principles for Computer System Design, Butler Lampson

The Advent of Actionable Tennis Analytics, Jeff Sackmann

Automatic Pool Stick vs Strangers, Shane Wighton


If the universe has no principles, the only principles relevant are the ones we decide on.
If the universe has no purpose, then we get to dictate what its purpose is.



Design and source code from Jon Barron's website