M
Michalis Papakostas
Researcher at University of Michigan
Publications - 37
Citations - 342
Michalis Papakostas is an academic researcher from University of Michigan. The author has contributed to research in topics: Robot learning & Computer science. The author has an hindex of 9, co-authored 34 publications receiving 226 citations. Previous affiliations of Michalis Papakostas include University of Texas at Arlington.
Papers
More filters
Journal ArticleDOI
Deep Visual Attributes vs. Hand-Crafted Audio Features on Multidomain Speech Emotion Recognition
Michalis Papakostas,Evaggelos Spyrou,Theodoros Giannakopoulos,Giorgos Siantikos,Dimitrios Sgouropoulos,Phivos Mylonas,Fillia Makedon +6 more
TL;DR: This work presents an approach that uses a Convolutional Neural Network functioning as a visual feature extractor and trained using raw speech information, which does not require any linguistic model and is not specific to any particular language.
Journal ArticleDOI
Speech-music discrimination using deep visual feature extractors
TL;DR: This work investigates CNNs for the task of speech music discrimination and the first that exploits transfer learning across very different domains for audio modeling using deep-learning in general, and fine-tune a deep architecture originally trained for the Imagenet classification task.
Proceedings Article
Grounding the meaning of words through vision and interactive gameplay
Natalie Parde,Adam Hair,Michalis Papakostas,Konstantinos Tsiakas,Maria Dagioglou,Vangelis Karkaletsis,Rodney D. Nielsen +6 more
TL;DR: I Spy is an effective approach for teaching robots how to model new concepts using representations comprised of visual attributes, and a model evaluation showed that the system correctly understood the visual representations of its learned concepts with an average of 65% accuracy.
Proceedings ArticleDOI
CogniLearn: A Deep Learning-based Interface for Cognitive Behavior Assessment
TL;DR: The proposed system, CogniLearn, automates capturing and motion analysis of users performing the HTKS game and provides detailed evaluations using state-of-the-art computer vision and deep learning based techniques for activity recognition and evaluation.
Proceedings ArticleDOI
Physical fatigue detection through EMG wearables and subjective user reports: a machine learning approach towards adaptive rehabilitation
TL;DR: This work proposes a novel method based on objective EMG measurements and aims to identify the presence of physical fatigue based on subjective user-reports and discusses how machine learning based modeling can become useful towards understanding fatigue and designing adaptive rehabilitation scenarios.