My main research focus is on Computer Vision and Machine Learning
I am a Postdoc Researcher at Vrije Universiteit Brussel (VUB) working on explainability methods for video models. I was previously a Research Associate at the University of Bristol working with Dima Damen on video understanding. I obtained my PhD from Utrecht University's Department of Information and Computing Science where I was lucky to be supervised by Ronald Poppe and Remco C. Veltkamp. The topic of my thesis was based on human action and interaction recognition in everyday social settings. During my time in Utrecht, I also worked on improving the efficiency and explainability of spatiotemporal deep learning models, for scene understanding and classification of videos. I completed my Master's and Bachelor's degrees in Computer Science at the University of Essex.
A full list can be found at my GoogleScholar profile.
@article{stergiou2023leaping, title={Leaping Into Memories: Space-Time Deep Feature Synthesis}, author={Stergiou, Alexandros and Deligiannis, Nikos}, journal={arXiv preprint arXiv:2303.09941}, year={2023}}
@article{stergiou2022temporal, title={Temporal Progressive Attention for Early Action Prediction}, author={Stergiou, Alexandros and Damen, Dima}, journal={arXiv preprint arXiv:2204.13340}, year={2022}}
@article{stergiou2022playitback, title={Play It Back: Iterative Attention for Audio Recognition}, author={Stergiou, Alexandros and Damen, Dima}, journal={arXiv preprint arXiv:2210.11328}, year={2022}}
@article{stergiou2021refining,
title={Refining activation downsampling with SoftPool},
author={Stergiou, Alexandros and Poppe, Ronald and Kalliatakis, Grigorios},
booktitle={IEEE International Conference on Computer Vision (ICCV)},
year={2021},
organization={IEEE}}
@article{stergiou2021mind,
title = {The Mind's Eye: Visualizing Class-Agnostic Features of CNNs},
author={Stergiou, Alexandros},
booktitle={IEEE International Conference on Image Processing (ICIP)},
year={2021},
organization={IEEE}}
@article{stergiou2021multi,
title={Multi-Temporal Convolutions for Human Action Recognition in Videos},
author={Stergiou, Alexandros and Poppe, Ronald},
booktitle={IEEE International Joint Conference of Neural Networks (IJCNN)},
year={2021},
organization={IEEE}}
@article{stergiou2019class,
title={Class Feature Pyramids for Video Explanation},
author={Stergiou, Alexandros and Kapidis, Georgios and Kalliatakis, Grigorios and
Chrysoulas, Christos Poppe, Ronald and Veltkamp, Remco},
booktitle={IEEE Intenrantional Conference on Computer Vision Workshops (ICCVW)},
year={2019},
organization={IEEE}}
@article{stergiou2019fast,
title={Spatio-Temporal FAST 3D Convolutions for Human Action Recognition},
author={Stergiou, Alexandros and Poppe, Ronald},
booktitle={IEEE Intenrantional Conference on Machine Learning Applications (ICMLA)},
year={2019},
organization={IEEE}}
@article{stergiou2019saliency,
title={Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions},
author={Stergiou, Alexandros and Kapidis, Georgios and Kalliatakis, Grigorios and
Chrysoulas, Christos and Veltkamp, Remco and Poppe, Ronald},
booktitle={IEEE International Conference on Image Processing (ICIP)},
year={2019},
organization={IEEE}}
@article{stergiou2023adapool,
author={Stergiou, Alexandros and Poppe, Ronald},
journal={IEEE Transactions on Image Processing},
title={AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling},
year={2023},
volume={32},
pages={251-266},
doi={10.1109/TIP.2022.3227503}}
@article{stergiou2020learn,
title = {Learn to cycle: Time-consistent feature discovery for action recognition},
author={Stergiou, Alexandros and Poppe, Ronald},
journal = {Pattern Recognition Letters},
volume ={141},
pages ={1--7},
year ={2021},
issn ={0167-8655}}
@article{stergiou2019analyzing,
author = {Stergiou, Alexandros and Poppe, Ronald},
title = {Analyzing human-human interactions: a survey},
journal = {Computer Vision and Image Understanding},
volume = {188},
pages = {102799},
year = {2019},
issn = {1077-3142}}
@phdthesis{stergiou2021efficient, title={Efficient Modelling Across Time of Human Actions and Interactions}, author={Stergiou, Alexandros Georgios}, year={2021}, school={Utrecht University}}