Suman Saha

   I am a postdoctoral researcher at CVL (Computer Vision Lab) , ETH Zürich, Switzerland. My current research interests lie in Computer Vision, Machine Learning (ML) and of course Deep Learning (DL). I am interested in exploring ML algorithms for solving challenging Computer Vision tasks such as: human action detection and anticipation in realistic videos.    Before joining ETH Zürich, I was a Research Associate (RA) or a postdoctoral researcher at the Department of Computing and Communication Technologies, Oxford Brookes University, where I spent four wonderful years (included my PhD studies). I have received my PhD degree under the supervision of Professor Fabio Cuzzolin at Oxford Brookes University, United Kingdom. Professor Nigel Crook and Dr Tjeerd Olde Scheper where my PhD co-supervisors. I have completed my Master's study from the Department of Computer Science and Technology, University of Bedfordshire (UoB), United Kingdom. I received my Polytechnic Diploma Engineering degree in Computer Science from Siddaganga Polytechnic College, India. My CV can be viewed by clicking this link.    My email id is: Click here to read more about me.

Publications, PhD & MSc thesis


Unsupervised Deep Representations for Learning Audience Facial Behaviors,
Suman Saha, Rajitha Navarathna, Leonhard Helminger, Romann M. Weber,
CVPR 2018 Workshops.
[pdf] [arXiv] [Poster]

Predicting Action Tubes,
Gurkirt Singh, Suman Saha, Fabio Cuzzolin,
ECCV 2018 Workshops.
[arXiv] [ppt link will be updated soon]

Incremental Tube Construction for Human Action Detection,
Harkirat Singh Behl, Michael Sapienza, Gurkirt Singh, Suman Saha, Fabio Cuzzolin, Philip H. S. Torr,
BMVC 2018 (oral).
[pdf] [ppt link will be updated soon]

Spatio-temporal Human Action Detection and Instance Segmentation in Videos,
Suman Saha,
PhD thesis, Oxford Brookes University, United Kingdom, 2018.
[pdf] [ppt]

TraMNet - Transition Matrix Network for Efficient Action Tube Proposals,
Gurkirt Singh, Suman Saha, Fabio Cuzzolin,
arXiv 2018.

Action Detection from a Robot-Car Perspective,
Valentina Fontana, Manuele Di Maio, Stephen Akrigg, Gurkirt Singh, Suman Saha, Fabio Cuzzolin,
arXiv 2018.


AMTnet: Action-Micro-Tube regression by end-to-end trainable deep architecture,
Suman Saha, Gurkirt Singh, Fabio Cuzzolin,
ICCV 2017 .
[pdf] [supp] [arXiv] [Poster]

Online Real-time Multiple Spatiotemporal Action Localisation and Prediction,
Gurkirt Singh, Suman Saha, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin,
ICCV 2017 .
[pdf] [supp] [arXiv] [Poster]

Spatio-temporal human action localisation and instance segmentation in temporally untrimmed videos,
Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin,
arXiv, 2017 .
[project] [arXiv]

Metric learning for Parkinsonian identification from IMU gait measurements,
Fabio Cuzzolin, Michael Sapienza, Patrick Esser, Suman Saha, Miss Marloes Franssen, Johnny Collett, Helen Dawes,
Gait & Posture, Volume 54, May 2017, Pages 127-132 .
[online link]


Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos,
Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin,
BMVC 2016 .
[project] [arXiv] [pdf+supp] [code] [poster]


A real-time monocular vision-based frontal obstacle detection and avoidance for low cost UAVs in GPS denied environment,
Suman Saha, Ashutosh Natraj, Sonia Waharte,
Aerospace Electronics and Remote Sensing Technology (ICARES), 2014 IEEE International Conference on.
[pdf] [project]

Face Recognition using PCA and Multilayer Feedforward Neural Networks,
Suman Saha,
European Journal of Applied Sciences and Technology [EUJAST] Volume 1 (1), March 2014.

Parallelization of Genetic Algorithms using MapReduce,
Suman Saha,
European Journal of Applied Social Sciences Research (EJASSR), Vol-2, Issue 1, March 2014.

A Monocular Vision Approach for Obstacle Detection and Collision Avoidance for Low-cost Quadrocopters,
Suman Saha,
MSc thesis, University of Bedfordshire, Uited Kingdom. January 2014.
[pdf] [poster]

Technical Reports / Talks / Survey Reports