Noureldien Hussein

Ph.D. Candidate in Computer Vision at the University of Amsterdam
Google ScholarLinkedInGitHubGoodReadsBlogResumeCV
Email: nhussein AT uva.nl



Summary

• Fourth-year Ph.D. candidate at Quva Lab, University of Amsterdam
• Supervised by Arnold Smeulders and Efstratios Gavves
• Helping in advancing methods for understanding human activities in videos at an industrial scale

Research

• Computer Vision: video analytics, action recognition, visual storytelling, event detection, temporal localization
• Applied Machine Learning: zero-shot recognition, generative models, graph-based representation, temporal modeling

Education

• 2016-2020 – Ph.D. Computer Vision – University of Amsterdam
• 2014-2015 – M.Sc. Artificial Intelligence – University of Southampton
• 2005-2012 – B.Sc. Computer and System Engineering – Ain Shams University

Publications


VideoGraph: Recognizing Minutes-Long Human Activities in VideosICCV Workshop, 2019
Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders

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 WM},
booktitle = {ICCV Workshop on Scene Graph Representation and Learning},
year      = {2019}
}

Timeception for Complex Action RecognitionCVPR, 2019Oral 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 WM},
booktitle = {CVPR},
year      = {2019}
}

Unified Embedding and Metric Learning for Zero-Exemplar Event DetectionCVPR, 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 WM},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
year      = {2017}
}

University of Amsterdam and Renmin University at TRECVID 2016: Searching Video, Detecting Events and Describing VideoTRECVID 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,
title     = {University of Amsterdam and Renmin University at TRECVID 2016: Searching Video, Detecting Events and Describing Video},
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.},
booktitle = {TRECVID 2016 Workshop. Gaithersburg, MD, USA},
year      = {2016},
url       = {https://ivi.fnwi.uva.nl/isis/publications/2016/SnoekPTRECVID2016},
}

Teaching & Supervision


Thesis Supervision

Multi-Modal Detection for Boats using Vision and Radar MSc Artifical Intelligence, 2019
Juan Buhagiar, Noureldien Hussein, Efstratios Gavves

The goal of this on-going research is to detect the surrounding boats using multi-modal sensori data from cameras and radars. This will help achieve the over-arching goal of autonomus water taxi.


Improving Word Embeddings for Zero-Shot Event Localisation by Combining Relational Knowledge with Distributional SemanticsMSc Artifical Intelligence, 2018
Joop L. Pascha, Efstratios Gavves, Noureldien Hussein

Using knownlege graphs as a priori for labels associated with event images or videos. Hence, improving the accuracy of zero-shot detection.


Real-Time Composing of Restaurant Label Classifiers Utilizing Semantic Word SimilarityBSc Artifical Intelligence, 2017
Tony Nguyen, Noureldien Hussein, Efstratios Gavves

An method to predict missing labels of restaurant images using semantic word similarities. The method makes use of dataset of Kaggle competition: "Yelp Restaurant Photo Classification".


Teaching Assistance

  • Autonomous Mobile Robots - BSc Computer Science / Artificial Intelligence, 2018
  • Information Visualization - BSc Computer Science, 2017
  • Autonomous Mobile Robots - BSc Computer Science / Artificial Intelligence, 2016

Miscellaneous


Patents

Unified Embedding with Metric Learning for Zero-Exemplar Event DetectionUS20180137360A1
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.


Peer Reviewing

Conferences: CVPR19, ICCV19, CVPR18, ECCV18, CVPR17, ICCV17, ACM-MM16
Journals: IEEE-ToM

Contact


Email: nhussein AT uva.nl
Office: +31-(0)20-525-8627

Address:

Quva Lab, Room C3.250a
Informatics Institute, University of Amsterdam
Science Park 904, 1098 XH Amsterdam, The Netherlands