Noureldien Hussein
PhD in Computer Vision - Interned @ Facebook AI, Microsoft, Qualcomm
Email: noureldien [at] live.com
Scholar
LinkedIn
GitHub
GoodReads
Blog
Résumé
C.V.
2021 – Research Intern – Facebook AI – Amsterdam, NL
2020 – Graduate Research Assistant – University of Amsterdam – Amsterdam, NL
2020 – Research Intern – Microsoft – Redmond, US
2019 – Research Intern – Qualcomm – Amsterdam, NL
2020 – PhD Computer Vision – University of Amsterdam
2015 – MSc Artificial Intelligence – University of Southampton
2012 – BSc Computer and System Engineering – Ain Shams University
Experience
• Research on semantic segmentation and video instance segmentation
• Technologies: SwinTransformer, SegFormer, Segmenter, MaskFormer, PyTorch
• Conduct world-class research published in top conferences and journals
• Co-supervise MSc/BSc thesis projects, and assist in teaching BSc subjects
• Reviewer for conferences and journals: CVPR, ICCV, ECCV, TPAMI, IEEE-ToM, ACM-MM
• Helped in organizing academic conferences: ECCV16, ACM-MM16, ICCV HVU
• Conduct research on lip movement manipulation in videos using generative models
• Technologies: DeepFake, Vid2Vid, GANs, OpticalFlow, Facial Keypoint Prediction
• Conducted research on efficient recognition of minutes-long human activities in videos
• Technologies: Temporal Sampling, PyTorch, TensorFlow
• Designed/developed web and mobile solutions using C#, ASP.Net, MVC, Xamarin
• Developed educational, augmented reality app for iPad using C#, Unity3D
• Saved 60% of server monitoring time by developing an automated-monitoring tool
• Proof of concept and investigation for integrating different technologies
Education
• Research: action recognition, temporal modeling, video description, visual storytelling
• Advisors: Arnold Smeulders, Efstratios Gavves
• Thesis: Aspects of Time for Recognizing Human Activities
@inproceedings{hussein2020aspects, title = {Aspects of Time for Recognizing Human Activities}, author = {Hussein, Noureldien}, booktitle = {Ph.D. Thesis, University of Amsterdam}, year = {2020} }
• Computer Vision • Machine Learning • Intelligent Agents • Computational Finance
• Advisor: Jonathon Hare
• Thesis: Hierarchical ConvNets for Large-Scale Traffic Sign Detection and Recognition
@inproceedings{hussein2015hierarchical, title = {Hierarchical ConvNets for Large-Scale Traffic Sign Detection and Recognition}, author = {Hussein, Noureldien}, booktitle = {M.Sc. Thesis, University of Southampton}, year = {2015} }
• Software Engineering • Neural Networks • Operating Systems • Computer Networks
• Data Structures and Algorithms • Computer Security • Computer Architecture
• Advisor: Hazem Abbas
• Thesis: Arabic Sign Language Recognition in Real Time (Distinction, Award-winning)
@inproceedings{hussein2012arabic, title = {Arabic Sign Language Recognition in Real Time}, author = {Hussein, Noureldien; Hefny, Walid; Fawzy, Fady; Moustafa, Mohamed}, booktitle = {B.Sc. Thesis, Ain Shams University}, year = {2012} }
Research
Publications
arXiv, 2020
Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders
A novel convolutional block named Permutation Invariant Convolution (PIC) is proposed. It is permissible in many ways that a long-range activity can take place over time. The result is improvements in the accuracy of recognizing the long-range activities of Breakfast, Charades, and MultiThumos.
@inproceedings{hussein2020pic, title = {PIC: Permutation Invariant Convolution for Recognizing Long-range Activities}, author = {Hussein, Noureldien and Gavves, Efstratios and Smeulders, Arnold W.M.}, booktitle = {arXiv}, year = {2020} }
arXiv, 2020
Noureldien Hussein, Mihir Jain, Babak Ehteshami Bejnordi
A conditional gating mechanism is proposed to select the most relevant segments from a video of long-range activity. The selection is conditioned on both the segment and its context, i.e. the video itself. The result is extreme efficiency in classifying long-range activities without compromising the performance.
@inproceedings{hussein2020timegate, title = {TimeGate: Conditional Gating of Segments in Long-range Activities}, author = {Hussein, Noureldien and Jain, Mihir and Bejnordi, Babak Ehteshami}, booktitle = {arXiv}, year = {2020} }
ICPR, 2020
Mert Kilickaya, Noureldien Hussein, Efstratios Gavves, Arnold Smeulders
For recognizing human-object interaction from single image, we propose new sources of contexts. In addition, we propose a conditional gating model for fusing the context features. The result is a substantial improvement on three benchmarks: HICO, V-COCO and CINT.
@inproceedings{kilickaya2020self, title = {Self-Selective Context for Interaction Recognition}, author = {Kilickaya, Mert; Hussein, Noureldien; Gavves, Efstratios; Smeulders, Arnold W.M.}, booktitle = {ICPR}, year = {2020} }
ICCV Workshop, 2019
Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders
A method to represent a long-range action as a graph. A soft version of the graph is reconstructed, where both the graph nodes and graph edges are learned entirely from data. The result is recognizing minutes-long human activities in videos.
@inproceedings{hussein2019videograph, title = {VideoGraph: Recognizing Minutes-Long Human Activities in Videos}, author = {Hussein, Noureldien and Gavves, Efstratios and Smeulders, Arnold W.M.}, booktitle = {ICCV Workshop on Scene Graph Representation and Learning}, year = {2019} }
CVPR, 2019 – Oral Presentation
Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders
A novel temporal layer for 3D CNNs with multi-scale temporal convolutions and much reduced computation. The result is a CNN for modeling minute-long complex actions, 8 times longer than best related method.
@inproceedings{hussein2018timeception, title = {Timeception for Complex Action Recognition}, author = {Hussein, Noureldien and Gavves, Efstratios and Smeulders, Arnold W.M.}, booktitle = {CVPR}, year = {2019} }
CVPR, 2017
Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders
A manifold is learned using contrastive loss, in which there is a joint embedding of videos of human events and their related articles. The result is end-to-end model with best results on TRECVID MED dataset.
@inproceedings{hussein2017unified, title = {Unified Embedding and Metric Learning for Zero-Exemplar Event Detection}, author = {Hussein, Noureldien and Gavves, Efstratios and Smeulders, Arnold W.M.}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, year = {2017} }
TRECVID Workshop, 2016
Cees G. M. Snoek, Jianfeng Dong, Xirong Li, Xiaoxu Wang, Qijie Wei, Weiyu Lan, Efstratios Gavves, Noureldien Hussein, Dennis C. Koelma, Arnold W. M. Smeulders
Summary for our method used in the annual competition for zero-shot event recognition TRECVID MED 2016.
@inproceedings{snoek2016trecvid, author = {Snoek, Cees G. M. and Dong, Jianfeng and Li, Xirong and Wei, Qijie and Wang, Xiaoxu and Lan, Weiyu and Gavves, Efstratios and Hussein, Noureldien and Koelma, Dennis C. and Smeulders, Arnold W.M.}, title = {University of Amsterdam and Renmin University at TRECVID 2016: Searching Video, Detecting Events and Describing Video}, booktitle = {TRECVID Workshop}, year = {2016}, url = {https://ivi.fnwi.uva.nl/isis/publications/2016/SnoekPTRECVID2016}, }
Patents
WO2021097359A1
Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders
WO2021097378A1
Mert Kilickaya, Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders
US20200302185A1
Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders
US20180137360A1
Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders
Peer Reviewing
Conferences
- Conference on Neural Information Processing Systems (NeurIPS): 2020, 2019, 2018
- Conference on Computer Vision and Pattern Recognition (CVPR): 2022, 2020, 2019, 2018, 2017
- International Conference on Computer Vision (ICCV): 2021, 2019, 2017
- European Conference on Computer Vision (ECCV): 2022, 2020, 2018
- The British Machine Vision Conference (BMVC): 2021, 2020, 2019, 2018
- ACM International Conference on Multimedia (ACM MM): 2016
Journals
- IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI): 2021, 2020
- IEEE Transactions on Multimedia (IEEE ToMM): 2016
Teaching & Supervision
Thesis Supervision
Juan Buhagiar, Noureldien Hussein, Efstratios Gavves
MSc Artifical Intelligence, 2019
Joop L. Pascha, Efstratios Gavves, Noureldien Hussein
MSc Artifical Intelligence, 2018
Tony Nguyen, Noureldien Hussein, Efstratios Gavves
BSc Artifical Intelligence, 2017
Teaching Assistance
Autonomous Mobile RobotsBSc Artificial Intelligence, 2018
Information VisualizationBSc Computer Science, 2017
Autonomous Mobile RobotsBSc Artificial Intelligence, 2016
Talks
03.2020 – Invited by Prof. Dr. Mubarak Shah, University of Central Florida (Online, Covid-19)
01.2020 – Qualcomm AI Research
10.2019 – Qualcomm AI Research
10.2019 – Guest Lecturer, University of Amsterdam
05.2019 – Qualcomm AI Research
03.2019 – Guest Lecturer, University of Amsterdam
10.2018 – Qualcomm AI Research
03.2018 – Qualcomm AI Research
02.2017 – Qualcomm AI Research
04.2016 – Qualcomm AI Research
12.2012 – Social Innovation Summit, US
10.2012 – Microsoft Middle East Annual Meeting, Turkey
About
Biography
Noureldien Hussein is a computer scientist, specialized in computer vision and applied machine learning. He is interested in teaching computer machines on how to understand videos. This overarching goal can be broken down into several tasks, such as action recognition, video retrieval, video representation learning, temporal modeling, video captioning, and many more.
Speaking of his educational background, he did his Ph.D. in video understanding at the University of Amsterdam. During his Ph.D. studies, he conducted a few industrial internships at Microsoft and Qualcomm. Earlier on, he studied his M.Sc. in artificial intelligence at the University of Southampton in Southampton, the UK, and his B.Sc. in computer and system engineering at Ain Shams University in Cairo, Egypt.
During his Ph.D. studies, he gained industrial experience throughout research internships. In 2020, he conducted a research internship at Microsoft in Redmond, U.S., where he devised a generative model to manipulate human face landmarks in videos. While in 2019, he proposed a method for the efficient recognition of human actions in videos using contextual conditional gating. Before his postgraduate studies, and for almost two years, he worked as a software development engineer at Breeze IT in Nottingham, U.K, and at ITWorx in Cairo, Egypt.
He is known for his competitiveness. During his undergraduate studies, he competed in Imagine Cup, a software development competition for students, run by Microsoft. In mid 2012, he and his team won the first place in the mobile development contents at Microsoft Imagine Cup competition in Sydney, Australia. While in late 2012, he and his team won the third place in Imagine Cup Grant, with an angel funding of fifty thousand USD.
Awards
- 3rd Place – TRECVID Multimedia Event Detection (MED) Challenge, 2016 – Online
- 3rd Place – Kaggle In-class Competition for Recommender Systems, 2015 – Online
- 3rd Place – Microsoft Imagine Cup Grant, 2012 – Seattle, US
- 1st Place – Microsoft Imagine Cup, Windows Phone Challenge, 2012 – Sydney, AU
- 3rd Place – BSc Thesis Project, ebTIECar Challenge, 2012 – Cairo, Egypt
- 1st Place – Microsoft Imagine Cup, Egypt Local Finals, Software Design, 2010 – Warsaw, PL
Media Coverage
Third Place Worldwide, Microsoft Imagine Cup Grant, 2012 – Seattle, US
- Wired.com Microsoft Announces Imagine Cup Finalists 2012
- TechCrunch Microsoft Awards Imagine Cup Grants to 5 Innovative Student Teams>
- Microsoft News Microsoft Awards Imagine Cup Grants to Jumpstart Student Startups That Address Social Issues
- Stanford Social Innovation Review Mirrors to Windows, and Youth Innovation
- Microsoft News Microsoft awards US $75,000 Imagine Cup Grant to Australian students
- Microsoft Tech Announcing the Imagine Cup 2012 Grant Finalists
- PR Newswire Microsoft Awards Imagine Cup Grants to Jumpstart Student Startups That Address Social Issues
- Innovation Village Imagine Cup 2012: Microsoft Awards Grants To Student Winners
First Place Worldwide, Windows Phone Challenge, Microsoft Imagine Cup, 2012– Sydney, Australia, 2012
- ZDNet Microsoft announces Imagine Cup 2012 winners
- PC Magazine Microsoft's Imagine Cup 2012 Winners
- Microsoft News Microsoft Announces Imagine Cup 2012 Winners
- Windows Azure Windows Azure Powers Imagine Cup Experience
- Windows Blog Microsoft Imagine Cup 2012 Yearbook
- Image Cup News Exclusive: Meet team Vivid, a 1st place winner in Imagine Cup 2012
- BizTech Africa Imagine Cup grant finalists named
- YouTube Announcing First Place Winner of Windows Phone Development
- Flickr Announcing Winners of Windows Phone Development, Microsoft Imagine Cup