Výsledky vyhledávání - "Asteriadis, Stylianos"

Report

Explaining, Analyzing, and Probing Representations of Self-Supervised Learning Models for Sensor-based Human Activity Recognition

Autor: Khaertdinov, Bulat, Asteriadis, Stylianos

In recent years, self-supervised learning (SSL) frameworks have been extensively applied to sensor-based Human Activity Recognition (HAR) in order to learn deep representations without data annotations. While SSL frameworks reach performance almost c

Externí odkaz: http://arxiv.org/abs/2304.07304

Zobrazit plný text záznamu

Report

Unsupervised Interpretable Basis Extraction for Concept-Based Visual Explanations

Autor: Doumanoglou, Alexandros, Asteriadis, Stylianos, Zarpalas, Dimitrios

An important line of research attempts to explain CNN image classifier predictions and intermediate layer representations in terms of human understandable concepts. In this work, we expand on previous works in the literature that use annotated concep

Externí odkaz: http://arxiv.org/abs/2303.10523

Zobrazit plný text záznamu

Report

Temporal Feature Alignment in Contrastive Self-Supervised Learning for Human Activity Recognition

Autor: Khaertdinov, Bulat, Asteriadis, Stylianos

Automated Human Activity Recognition has long been a problem of great interest in human-centered and ubiquitous computing. In the last years, a plethora of supervised learning algorithms based on deep neural networks has been suggested to address thi

Externí odkaz: http://arxiv.org/abs/2210.03382

Zobrazit plný text záznamu

Report

Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition

Autor: Brinzea, Razvan, Khaertdinov, Bulat, Asteriadis, Stylianos

Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. We explore the hypothesis that

Externí odkaz: http://arxiv.org/abs/2205.10071

Zobrazit plný text záznamu

Report

Being the center of attention: A Person-Context CNN framework for Personality Recognition

Autor: Dotti, Dario, Popa, Mirela, Asteriadis, Stylianos

This paper proposes a novel study on personality recognition using video data from different scenarios. Our goal is to jointly model nonverbal behavioral cues with contextual information for a robust, multi-scenario, personality recognition system. T

Externí odkaz: http://arxiv.org/abs/1910.06690

Zobrazit plný text záznamu