Me

Alex Stergiou

I am an Assistant Professor at University of Twente's Data Management & Biometrics (DMB) group. Previously, I was a Postdoc at VUB and a Research Associate at the University of Bristol working with Dima Damen on video understanding. I obtained my PhD from Utrecht University where I was lucky to be supervised by Ronald Poppe and Remco C. Veltkamp. My thesis topic was on human action and interaction recognition in everyday social settings. During my time in Utrecht, I additionally worked on improving the efficiency and interpretability of spatiotemporal deep learning video classification models.

News

[03-2024]   Our preprint on video repetition counting is now available here alongside code and model checkpoints.
[11-2023]   I'll be joining University of Twente as an Assistant Professor in February.
[10-2023]   I'll present Holistic Representation Learning for Multi-Task Trajectory Anomaly Detection at WACV 2024.
[08-2023]   I am now a member of ELLIS .
[07-2023]   Leaping Into Memories: Space-Time Deep Feature Synthesis was accepted in ICCV 2023.
[02-2023]   I'll present Play It Back: Iterative Attention for Audio Recognition in ICASSP 2023.
[02-2023]   Our paper The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction was accepted in CVPR 2023.



PUBLICATIONS LIST

A full list can be found at my GoogleScholar.


anom_detect anom_detect-active

Sinha S., Stergiou A., and Damen D., Every Shot Counts: Using Exemplars for Repetition Counting in Videos
arXiv 2024
anom_detect anom_detect-active

Stergiou A., De Weerdt B., and Deligiannis N., Holistic Representation Learning for Multi-Task Trajectory Anomaly Detection
WACV 2024
leaps leaps-active

Stergiou A., and Deligiannis N., Leaping Into Memories: Space-Time Deep Feature Synthesis
ICCV 2023
tempr tempr-active

Stergiou A., and Damen D., The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction
CVPR 2023
playitback playitback-active

Stergiou A., and Damen D., Play It Back: Iterative Attention for Audio Recognition
ICASSP 2023
mindseye mindseye-active

Stergiou A., and Poppe R., AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling
IEEE Transactions on Image Processing, 2023
mindseye mindseye-active

Stergiou A., The Mind's Eye: Visualizing Class Agnostic Features of CNNs,
ICIP 2021
mindseye mindseye-active

Stergiou A., Poppe R., and Kalliatakis G., Refining activation downsampling with SoftPool
ICCV 2021
mtconv mtconv_active

Stergiou A., and Poppe R., Multi-Temporal Convolutions for Human ActionRecognition in Videos
IJCNN 2021
learn2cycle srtg-active

Stergiou A., and Poppe R., Learn to cycle: Time-consistent feature discovery for action recognition
Pattern Recognition Letters, 2021
feature-pyramids human-human-active
Stergiou A., Kapidis G., Kalliatakis G., Chrysoulas C., Poppe R., and Veltkamp R.C., Class Feature Pyramids for Video Explanation
ICCVw 2019
FAST_conv
Stergiou A., and Poppe R., Spatio-Temporal FAST 3D Convolutions for Human Action Recognition
ICMLA 2019 (Oral)
saliency-tubes human-human-active
Stergiou A., Kapidis G., Kalliatakis G., Chrysoulas C., Veltkamp R.C., and Poppe R., Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions
ICIP 2019 (Oral)
h2h_survey

Stergiou A., and Poppe R., Analyzing human-to-human interactions: a survey
Computer Vision and Image Understanding, 2019

DATASETS

Fig1
Inter4K



THESIS

thesis-static thesis-active

Stergiou A.G., Efficient Modelling Across Time of Human Actions and Interactions
Utrecht University 2021

ACTIVITIES

TEACHING

Fig1
REDI (Masters) 2023
Course administrator


Fig1
Deep Learning (Masters) 2023
Course administrator


Fig1
INFOMCV (Masters) 2018-2020
Guest Lecturer

REVIEWING

Journals: IJCV, TIP, TPAMI, Pattern Recognition
Conferences: CVPR 2022-now, ECCV 2022-now, ICCV 2023-now, BMVC (2018,2023), WACV 2024
Outstanding Reviewer: ECCV 2022

SUPERVISION

Master students
Ștefan Păun (UT, 2024)     Marjusa Elezi (VUB, 2023)

© Alexandros Stergiou