Irtiza Hasan

Senior Scientist

(ihasan085@gmail.com)

Google Scholar | GitHub


"We believe in: rough consensus and running code." - D. Clark

Research

Broadly, I like to work on problems related to visual perception, such as detection, classification, tracking, and time-series forecasting. Recently, I have been working mostly on trying to improve the robustness and generalization of algorithms in the visual perception domain.

About me

I am currently working as a senior computer vision researcher at Huawei Finland, in their cloud competence center. Previously, I worked as an AI researcher at Inception Institute of Artificial Intelligence (IIAI) and senior data scientist at AIQ. Prior to these appointments, I was a Marie Skłodowska-Curie fellow and finished my Ph.D. under the framework of Marie Skłodowska-Curie ITN SceneUnderLight from University of Verona, Italy and Osram Munich, Germany.

News

[SEP - 2022] Paper accepted @Pattern Recognition. IF=8.5.
[MAR - 2022] New paper on Transformer Networks for Time-Series Forecasting @ArXiv [pdf].
[JAN - 2022] New paper on Transformer Networks, Domain Generalization @ArXiv [pdf][code].
[AUG - 2021] Patent granted [pdf].
[MAR - 2021] Paper accepted @CVPR2021 [code].
[OCT - 2020] Paper accepted @ICPR 2020 [code].
[OCT - 2019] Paper accepted @TPAMI. IF=17.7.

Selected Publications and Patents

"Center and Scale Prediction: Anchor-free Approach for Face and Pedestrian Detection", Wei Liu*, Irtiza Hasan*, Shengcai Liao
Accepted in Pattern Recognition 2022. *Denotes equal contribution.
PDF Keras PyTorch
"Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond", Irtiza Hasan, Shengcai Liao, Jinpeng Li, Saad Ullah Akram, Ling Shao
Under review at IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2022
PDF code
"Generalizable Pedestrian Detection: The Elephant In The Room", Irtiza Hasan, Shengcai Liao, Jinpeng Li, Saad Ullah Akram, Ling Shao
In Proc. Computer Vision and Pattern Recognition (CVPR) 2021
PDF code
"Transformer Networks for Trajectory Forecasting", Francesco Giuliari, Irtiza Hasan, Marco Cristani and Fabio Galasso
In Proc. International Conference on Pattern Recognition (ICPR) 2020
PDF code
"Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets", Irtiza Hasan, Francesco Setti, Theodoros Tsesmelis, Vasileios Belagiannis, Sikandar Amin, Alessio Del Bue, Marco Cristani, Fabio Galasso
Accepted in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2019
PDF Annotations
"MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses", Irtiza Hasan, Francesco Setti, Theodoros Tsesmelis, Alessio Del Bue, Fabio Galasso, Marco Cristani,
In Proc. Computer Vision and Pattern Recognition (CVPR Spotlight Oral) 2018
PDF bibtex
"“Seeing is Believing”: Pedestrian Trajectory Forecasting Using Visual Frustum of Attention", Irtiza Hasan, Francesco Setti, Theodoros Tsesmelis, Alessio Del Bue, Marco Cristani, Fabio Galasso
In Proc. Winter Conf. on Applications of Computer Vision (WACV) 2018
PDF bibtex

Patents

November 2019, Patent disclosure on "A method of measuring illumination, corresponding system and computer program product", Theodoros Tsesmelis, Irtiza Hasan, Fabio Galasso, Herbert Kastle, Alessio Del Bue, Marco Cristani
WO/2018/069826, PDF
August 2016, Patent disclosure on "A method of view frustum detection, corresponding system and computer program product", Irtiza Hasan, Theodoros Tsesmelis, Fabio Galasso, Marco Cristani, Alessio Del Bue, Francesco Setti, Michael Eschey, Herbert Kastle
WO/2018/069826, PDF
August 2016, Patent disclosure on "A method of identifying light source, corresponding system and computer program product", Theodoros Tsesmelis, Irtiza Hasan, Fabio Galasso, Marco Cristani, Alessio Del Bue, Michael Eschey, Herbert Kastle
WO/2018/069827, PDF

Views

Flag Counter