My work is focused on Computer Vision and Machine Learning
I am currently a postdoctoral Research Associate at Bristol University's Machine Learning and Computer Vision Group (MaVi) working with prof. Dima Damen on video understanding. I obtained my PhD at Utrecht University's Department of Information and Computing Science. The topic of my thesis was on Machine Learning and Computer Vision for human action and interaction recognition in everyday social settings, supervised by dr. Ronald Poppe and prof. Remco C. Veltkamp. During my time in Utrecht I have also worked on improving the efficiency and explainabilty of spatio-temporal deep learning models, for scene understanding and classification of videos. I have completed my Masters and Bachelor degrees in (Advanced) Computer Science at the University of Essex. I have also worked shortly at the Institute for Analytics and Data Science (IADS) for a summer project on Neural Networks for structured population data with dr. Spyros Samothrakis.
A full list can be found in my GoogleScholar profile.
Stergiou A., and Damen D., Temporal Progressive Attention for Early Action Prediction, arXiv, 2022
@article{stergiou2022temporal, title={Temporal Progressive Attention for Early Action Prediction}, author={Stergiou, Alexandros and Damen, Dima}, journal={arXiv preprint arXiv:2204.13340}, year={2022}}
Stergiou A., and Poppe R., AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling, arXiv, 2021
@article{stergiou2021adapool, title={AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling}, author={Stergiou, Alexandros and Poppe, Ronald}, journal={arXiv preprint arXiv:2111.00772}, year={2021}}
Stergiou A., Poppe R., and Kalliatakis G., Refining activation downsampling with SoftPool, International Conference on Computer Vision (ICCV), 2021
@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}}
Stergiou A., The Mind's Eye: Visualizing Class Agnostic Features of CNNs, International Confernce on Image Procesing (ICIP), 2021
@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}}
Stergiou A., and Poppe R., Multi-Temporal Convolutions for Human ActionRecognition in Videos, International Joint Conference of Neural Networks (IJCNN), 2021
@article{stergiou2021multi,
title={Multi-Temporal Convolutions for Human Action Recognition in Videos},
author={Stergiou, Alexandros and Poppe, Ronald},
booktitle={International Joint Conference of Neural Networks (IJCNN)},
year={2021},
organization={IEEE}}
Stergiou A., Kapidis G., Kalliatakis G., Chrysoulas C., Poppe R., and Veltkamp R.C., Class Feature Pyramids for Video Explanation Intenrantional Conference on Computer Vision Workshop (ICCVW), 2019
@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}}
Stergiou A., and Poppe R., Spatio-Temporal FAST 3D Convolutions for Human Action Recognition, Intenrantional Conference on Machine Learning Applications (ICMLA), 2019
@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}}
Stergiou A., Kapidis G., Kalliatakis G., Chrysoulas C., Veltkamp R.C., and Poppe R., Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions, International Confernce on Image Procesing (ICIP), 2019
@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}}
Stergiou A., and Poppe R., Learn to cycle: Time-consistent feature discovery for action recognition, Pattern Recognition Letters, 2021
@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}}
Stergiou A., Poppe R., and Veltkamp R.C., Learning Class-Specific Features with Class Regularization for Videos, Applied Sciences, 2020
@article{stergiou2020learning,
title={Learning Class-Specific Features with Class Regularization for Videos},
author={Stergiou, Alexandros and Poppe, Ronald and Veltkamp, Remco C},
journal={Applied Sciences},
volume={10},
number={18},
pages={6241},
year={2020},
publisher={Multidisciplinary Digital Publishing Institute}}
Stergiou A., and Poppe R., Analyzing human-to-human interactions: a survey, Computer Vision and Image Understanding, 2019
@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}}
Stergiou A.G., Efficient Modelling Across Time of Human Actions and Interactions , Utrecht University 2021
@phdthesis{stergiou2021efficient, title={Efficient Modelling Across Time of Human Actions and Interactions}, author={Stergiou, Alexandros Georgios}, year={2021}, school={Utrecht University}}
© Alexandros Stergiou