Suman Saha
Suman Saha
Postdoc
Verified email at vision.ee.ethz.ch - Homepage
Title
Cited by
Cited by
Year
Online real-time multiple spatiotemporal action localisation and prediction
G Singh, S Saha, M Sapienza, PHS Torr, F Cuzzolin
Proceedings of the IEEE International Conference on Computer Vision, 3637-3646, 2017
1512017
Online real-time multiple spatiotemporal action localisation and prediction
G Singh, S Saha, M Sapienza, PHS Torr, F Cuzzolin
Proceedings of the IEEE International Conference on Computer Vision, 3637-3646, 2017
1512017
Deep learning for detecting multiple space-time action tubes in videos
S Saha, G Singh, M Sapienza, PHS Torr, F Cuzzolin
arXiv preprint arXiv:1608.01529, 2016
1302016
Amtnet: Action-micro-tube regression by end-to-end trainable deep architecture
S Saha, G Singh, F Cuzzolin
Proceedings of the IEEE International Conference on Computer Vision, 4414-4423, 2017
442017
A real-time monocular vision-based frontal obstacle detection and avoidance for low cost UAVs in GPS denied environment
S Saha, A Natraj, S Waharte
2014 IEEE International Conference on Aerospace Electronics and Remote …, 2014
442014
Metric learning for Parkinsonian identification from IMU gait measurements
F Cuzzolin, M Sapienza, P Esser, S Saha, MM Franssen, J Collett, ...
Gait & posture 54, 127-132, 2017
172017
Predicting Action Tubes
G Singh, S Saha, F Cuzzoli
https://arxiv.org/pdf/1808.07712.pdf, 2018
82018
Incremental Tube Construction for Human Action Detection
HS Behl, M Sapienza, G Singh, S Saha, F Cuzzolin, PHS Torr
arXiv preprint arXiv:1704.01358, 2017
82017
Unsupervised deep representations for learning audience facial behaviors
S Saha, R Navarathna, L Helminger, RM Weber
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018
42018
Spatio-temporal human action localisation and instance segmentation in temporally untrimmed videos
S Saha, G Singh, M Sapienza, PHS Torr, F Cuzzolin
arXiv preprint arXiv:1707.07213, 2017
42017
Parallelization of Genetic Algorithms using MapReduce
S Saha
European Journal of Applied Social Sciences Research (EJASSR) 2 (1), 20-35, 2014
42014
Tramnet-transition matrix network for efficient action tube proposals
G Singh, S Saha, F Cuzzolin
Asian Conference on Computer Vision, 420-437, 2018
32018
Action Detection from a Robot-Car Perspective
V Fontana, G Singh, S Akrigg, M Di Maio, S Saha, F Cuzzolin
arXiv preprint arXiv:1807.11332, 2018
22018
Spatio-temporal Human Action Detection and Instance Segmentation in Videos
S Saha
https://drive.google.com/open?id=1YzJkjLjrIDCOEgEsZm_vSxlY4be97oeA, 2018
12018
Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference
M Kanakis, D Bruggemann, S Saha, S Georgoulis, A Obukhov, ...
arXiv preprint arXiv:2007.12540, 2020
2020
Two-Stream AMTnet for Action Detection
S Saha, G Singh, F Cuzzolin
arXiv preprint arXiv:2004.01494, 2020
2020
Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing
S Saha, W Xu, M Kanakis, S Georgoulis, Y Chen, D Pani Paudel, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
2020
Face Recognition using PCA and Multilayer Feedforward Neural Networks
S Saha
European Journal of Applied Sciences and Technology [EUJAST] Volume 1 (1), 2014
2014
Supplementary Material AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture
S Saha, G Singh, F Cuzzolin
Supplementary Material: Incremental Tube Construction for Human Action Detection
HS Behl, M Sapienza, G Singh, S Saha, F Cuzzolin, PHS Torr, TT Team
The system can't perform the operation now. Try again later.
Articles 1–20