Saurav Sharma

I am a data science practitioner with background in computer vision having worked in multitude of projects and collaborations both academic and professional.

In mid 2019, I got the oppurtunity to do a research internship at INRIA Sophia-Antipolis where I worked on activity recognition and detection. Prior to internship, I was Senior Data Analyst at Kantar. I've done my masters from NIT Rourkela and bachelors from Tezpur University.

Email  /  CV  /  Google Scholar  /  ResearchGate  /  LinkedIn  /  GitHub

profile photo

I'm interested in deep learning methods for computer vision problems such as activity understanding and holistic scene understanding. My research goal is to comprehend how spatio-temporal scene context can help in better understanding of action dynamics. I am also curious about complex interplay and mutual learning of tasks related to different modalities.


  • Nov 2021 - Started as d'ingénieur de recherche at Camma Research Lab
  • Oct 2020 - Pre-print Toyota Smarthomes Untrimmed Dataset For Action Detection. (Work done at INRIA)
  • Jul 2020 - One Paper accepted at ECCV2020 for the work done at INRIA
  • Mar 2020 - Joined as Decision Scientist at Inference Labs, Bengaluru, India
  • Jul 2019 - Joined STARS Lab at INRIA-Sophia Antipolis, France as a research intern.
  • Apr 2019 - Left Kantar, Bengaluru, India as Senior Data Analyst.
  • Jun 2017 - Joined Kantar, Bengaluru, India as Data Analyst.
  • May 2017 - Completed Masters in Computer Science from NIT, Rourkela, India.

Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection
Rui Dai, Srijan Das, Saurav Sharma, Luca Minciullo, Lorenzo Garattoni, Francois Bremond, Gianpiero Francesca.
(Arxiv Pre-print), October 2020

Project Link

Untrimmed daily-living action detection dataset with dense annotations and features several real world challenges

VPN: Learning Video-Pose Embedding for Activities of Daily Living
Srijan Das, Saurav Sharma, Rui Dai, Francois Bremond, Monique Thonnat.
16th European Conference on Computer Vision (ECCV'20 ONLINE), 2020

Project Link

Temporal Activity Recognition using RGB videos guided by Human Pose based Attention Network

DenseNet with pre-activated deconvolution for estimating depth map from single image
Saurav Sharma, Ram Prasad Padhy, Suman Choudhury, Nabarun Goswami, Pankaj Sa.
5th Activity monitoring by multiple distributed sensing (AMMDS) Workshop under BMVC, London, 2017

Master's Thesis

Monocular depth estimation with state of the art DenseNet CNN with custom deconvolution modules.

A Framework for Pixel Intensity Modulation Based Image Steganography
Srijan Das, Saurav Sharma, Sambit Bakshi, Imon Mukherjee.
1st International Conference on Advanced Computing and Intelligent Engineering (ICACIE), India, 2016

Novel steganographic algorithm in the spatial domain using the concept of pixel modulation.

A Comparative Analysis of a novel Anomaly Detection algorithm with Neural Networks
Srijan Das, Arpita Dutta, Saurav Sharma, Sangharatna Godboley.
International Journal of Rough Sets and Data Analysis (IJRSDA) by IGI Global, 2017

Supervised anomaly detection using classical criterion functions.

Workshops Attended


  • Jan 2017 - Apr 2017    Teaching Assistant for CS 172 Computing Laboratory-II at NIT Rourkela.
  • Aug 2016 - Nov 2016   Teaching Assistant for CS 171 Computing Laboratory-I at NIT Rourkela.

Take a look at this website