Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Khaertdinov, Bulat"'
Autor:
Ghaleb, Esam, Khaertdinov, Bulat, Pouw, Wim, Rasenberg, Marlou, Holler, Judith, Özyürek, Aslı, Fernández, Raquel
Publikováno v:
INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION (ICMI 2024)
In face-to-face dialogues, the form-meaning relationship of co-speech gestures varies depending on contextual factors such as what the gestures refer to and the individual characteristics of speakers. These factors make co-speech gesture representati
Externí odkaz:
http://arxiv.org/abs/2409.10535
Recent advancements in Deep and Self-Supervised Learning (SSL) have led to substantial improvements in Speech Emotion Recognition (SER) performance, reaching unprecedented levels. However, obtaining sufficient amounts of accurately labeled data for t
Externí odkaz:
http://arxiv.org/abs/2406.07900
Autor:
Krutikov, Sergei, Khaertdinov, Bulat, Kiriukhin, Rodion, Agrawal, Shubham, De Vries, Kees Jan
Transformer-based neural networks, empowered by Self-Supervised Learning (SSL), have demonstrated unprecedented performance across various domains. However, related literature suggests that tabular Transformers may struggle to outperform classical Ma
Externí odkaz:
http://arxiv.org/abs/2405.13692
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
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
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
The ever-changing world of wearable technologies makes it difficult for experts and practitioners to keep up with the most recent developments. This handbook provides a solid understanding of the significant role that AI plays in the design and devel