76 citations · 176 across the 15 of their papers we have counts for
18 papers
Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
Masatoshi Tateno, Alexandros Stergiou, Risa Shinoda +2
Hand-object interaction (HOI) recognition requires capturing both hand manipulations and object transformations. However, existing video-language models often fall into shortcuts b…
About Time: Advances, Challenges, and Outlooks of Action Understanding
Alexandros Stergiou, Ronald Poppe
We have witnessed impressive advances in video action understanding. Increased dataset sizes, variability, and computation availability have enabled leaps in performance and task d…
Every Shot Counts: Using Exemplars for Repetition Counting in Videos
Saptarshi Sinha, Alexandros Stergiou, Dima Damen
Video repetition counting infers the number of repetitions of recurring actions or motion within a video. We propose an exemplar-based approach that discovers visual correspondence…
Holistic Representation Learning for Multitask Trajectory Anomaly Detection
Alexandros Stergiou, Brent De Weerdt, Nikos Deligiannis
Video anomaly detection deals with the recognition of abnormal events in videos. Apart from the visual signal, video anomaly detection has also been addressed with the use of skele…
Leaping Into Memories: Space-Time Deep Feature Synthesis
Alexandros Stergiou, Nikos Deligiannis
The success of deep learning models has led to their adaptation and adoption by prominent video understanding methods. The majority of these approaches encode features in a joint s…
Play It Back: Iterative Attention for Audio Recognition
Alexandros Stergiou, Dima Damen
A key function of auditory cognition is the association of characteristic sounds with their corresponding semantics over time. Humans attempting to discriminate between fine-graine…
The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction
Alexandros Stergiou, Dima Damen
Early action prediction deals with inferring the ongoing action from partially-observed videos, typically at the outset of the video. We propose a bottleneck-based attention model…
AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling
Alexandros Stergiou, Ronald Poppe
Pooling layers are essential building blocks of convolutional neural networks (CNNs), to reduce computational overhead and increase the receptive fields of proceeding convolutional…
Efficient Modelling Across Time of Human Actions and Interactions
Alexandros Stergiou
This thesis focuses on video understanding for human action and interaction recognition. We start by identifying the main challenges related to action recognition from videos and r…
The Mind's Eye: Visualizing Class-Agnostic Features of CNNs
Alexandros Stergiou
Visual interpretability of Convolutional Neural Networks (CNNs) has gained significant popularity because of the great challenges that CNN complexity imposes to understanding their…
Refining activation downsampling with SoftPool
Alexandros Stergiou, Ronald Poppe, Grigorios Kalliatakis
Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to reduce computational requi…
Multi-Temporal Convolutions for Human Action Recognition in Videos
Alexandros Stergiou, Ronald Poppe
Effective extraction of temporal patterns is crucial for the recognition of temporally varying actions in video. We argue that the fixed-sized spatio-temporal convolution kernels u…
Learn to cycle: Time-consistent feature discovery for action recognition
Alexandros Stergiou, Ronald Poppe
Generalizing over temporal variations is a prerequisite for effective action recognition in videos. Despite significant advances in deep neural networks, it remains a challenge to…
Learning Class Regularized Features for Action Recognition
Alexandros Stergiou, Ronald Poppe, Remco C. Veltkamp
Training Deep Convolutional Neural Networks (CNNs) is based on the notion of using multiple kernels and non-linearities in their subsequent activations to extract useful features.…
Spatio-Temporal FAST 3D Convolutions for Human Action Recognition
Alexandros Stergiou, Ronald Poppe
Effective processing of video input is essential for the recognition of temporally varying events such as human actions. Motivated by the often distinctive temporal characteristics…
Class Feature Pyramids for Video Explanation
Alexandros Stergiou, Georgios Kapidis, Grigorios Kalliatakis +3
Deep convolutional networks are widely used in video action recognition. 3D convolutions are one prominent approach to deal with the additional time dimension. While 3D convolution…
Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions
Alexandros Stergiou, Georgios Kapidis, Grigorios Kalliatakis +3
Deep learning approaches have been established as the main methodology for video classification and recognition. Recently, 3-dimensional convolutions have been used to achieve stat…
Analyzing Human-Human Interactions: A Survey
Alexandros Stergiou, Ronald Poppe
Many videos depict people, and it is their interactions that inform us of their activities, relation to one another and the cultural and social setting. With advances in human acti…