Anurag Ghosh

I'm a Research Fellow at Microsoft Research. I'm part of the Systems Lab, and I work at the intersection of Computer Vision and Systems for Driver Safety, with Venkat Padmanabhan and Akshay Nambi.

I previously obtained my Bachelors and Masters in Computer Science from IIIT Hyderabad. I was a Research Assistant at Centre for Visual Information Technology, where I was advised by C. V. Jawahar as I worked on problems involving Computer Vision and Sports.

Here's my Resume.

Email / GitHub / Google Scholar / LinkedIn

Research

I'm interested in problems involving computer vision, machine learning, robotics and systems with real world applications. I'm specially interested in developing algorithms in these domains keeping resource constraints (computational efficiency, infrastructural efficiency, label efficiency, minimal supervision) in mind.

	Smartphone-based Driver License Testing Watch Microsoft CEO Satya Nadella Explain the project in 2 sentences! Deployed with Maruti-Suzuki, Govt. Of Uttarakhand and Ministry of Road Transport, Govt. of India. Can a smartphone administer a driver license test? We demonstrate a low-cost, smartphone-based system for automating key aspects of the driver license test. A windshield-mounted smartphone serves as the sole sensing platform, with the front camera being used to monitor driver’s gaze, and the rear camera being used to evaluate driving maneuvers via a novel fiducial marker informed SLAM system. Relevant Publications [1] ALT: Towards Automating Driver License Testing using Smartphones Akshay Nambi, Ishit Mehta, Anurag Ghosh, Vijay Lingam, Venkat Padmanabhan, ACM Conference on Embedded Networked Sensor Systems (ACM SenSys), 2019 [Paper] [2] Smartphone-based Driver License Testing Anurag Ghosh, Vijay Lingam, Ishit Mehta, Akshay Nambi, Venkat Padmanabhan, Satish Sangameswaran, ACM Conference on Embedded Networked Sensor Systems (ACM SenSys Demo), 2019 [Paper]
	Analyzing Racket Sports From Broadcast Videos Framework piloted with ESPN/Star Sports at Premier Badminton League 2019. Sports video data is recorded for nearly every major tournament but remains archived and inaccessible to large scale data mining and analytics. We propose an end-to-end framework for automatic tagging and analysis of broadcast sport videos. Unlike previous approaches, we do not rely on special camera setups or additional sensors. Lastly, we adapt our proposed framework for tennis games to mine spatiotemporal and event data from large set of broadcast videos. We demonstrate that we can infer the playing styles between Roger Federer, Rafael Nadal and Novac Djokovic from their Grand Slam matches. 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, IEEE 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 Recipient)
	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] Stack Overflow, a Q&A site on programming, awards reputation points and badges (game elements) to users on performing various actions. Situating our work in Digital Signaling Theory, we investigate the role of these game elements in characterizing social qualities (specifically, popularity and impact) of its users. We present evidence that certain non-trivial badges, reputation scores and age of the user on the site positively correlate with popularity and impact.
	Dynamic narratives for heritage tour Anurag Ghosh , Yash Patel , Mohak Sukhwani, C.V. Jawahar VisArt Workshop, Europen Conference on Computer Vision (ECCV), 2016 [Paper] We present a dynamic story generation approach for the egocentric videos from the heritage sites. The narrative is optimised over length, relevance, cohesion and information simultaneously.