“DanceConv: Dance Motion Generation With Convolutional Networks” was published in IEEE Access and presents a convolutional approach to dance motion generation.
The work is relevant to the MediaLab profile in multimedia, movement analysis, human motion modelling and creative technologies, linking machine learning with embodied and cultural content.
- Authors: Kosmas Kritsis, Aggelos Gkiokas, Aggelos Pikrakis, Vassilis Katsouros
- Journal: IEEE Access, 10, 44982-45000
- Publication year: 2022
- DOI: 10.1109/ACCESS.2022.3169782
You may also like
-
TMLR 2026: prescriptive SVD-inspired attention via spectral energy retention
-
Towards Heritage World Models: from digital twins to predictive heritage systems
-
ICASSP 2026: representation-diverse self-supervision for bioacoustic learning
-
AISTATS 2026: process-tensor tomography of SGD and training memory
-
ICPRAM 2026: two-stage angular alignment for positive-unlabeled learning