TY - JOUR
KW - Bi-directional analysis
KW - Convolution
KW - Cultural heritages
KW - Deep learning
KW - Intangible cultural heritage
KW - Intangible cultural heritages
KW - Learning systems
KW - Long short-term memory
KW - Low-cost sensors
KW - machine learning
KW - Monitoring capabilities
KW - Motion Primitives Classification
KW - Motion analysis
KW - Motion primitives
KW - Processing layer
KW - Serious Game
KW - Serious games
KW - Visual information
KW - dance
AU - Nikolaos Bakalos
AU - Ioannis Rallis
AU - Nikolaos Doulamis
AU - Anastasios Doulamis
AU - Athanasios Voulodimos
AU - Vassilios Vescoukis
AB - Serious games are receiving increasing attention in the field of cultural heritage (CH) applications. A special field of CH and education is intangible cultural heritage and particularly dance. Machine learning (ML) tools are necessary elements for the success of a serious game platform since they introduce intelligence in processing and analysis of users  interactivity. ML provides intelligent scoring and monitoring capabilities of the user s progress in a serious game platform. In this article, we introduce a deep learning model for motion primitive classification. The model combines a convolutional processing layer with a bidirectional analysis module. This way, RGB information is efficiently handled by the hierarchies of convolutions, while the bidirectional properties of a long short term memory (LSTM) model are retained. The resulting convolutionally enhanced bidirectional LSTM (CEBi-LSTM) architecture is less sensitive to skeleton errors, occurring using low-cost sensors, such as Kinect, while simultaneously handling the high amount of detail when using RGB visual information.
DO - 10.1109/MCG.2020.2985035
M1 - 4
N1 - Publisher: IEEE Computer Society
N2 - Serious games are receiving increasing attention in the field of cultural heritage (CH) applications. A special field of CH and education is intangible cultural heritage and particularly dance. Machine learning (ML) tools are necessary elements for the success of a serious game platform since they introduce intelligence in processing and analysis of users  interactivity. ML provides intelligent scoring and monitoring capabilities of the user s progress in a serious game platform. In this article, we introduce a deep learning model for motion primitive classification. The model combines a convolutional processing layer with a bidirectional analysis module. This way, RGB information is efficiently handled by the hierarchies of convolutions, while the bidirectional properties of a long short term memory (LSTM) model are retained. The resulting convolutionally enhanced bidirectional LSTM (CEBi-LSTM) architecture is less sensitive to skeleton errors, occurring using low-cost sensors, such as Kinect, while simultaneously handling the high amount of detail when using RGB visual information.
SP - 26
EP - 38
TI - Motion Primitives Classification Using Deep Learning Models for Serious Game Platforms
UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85084052185&doi=10.1109%2fMCG.2020.2985035&partnerID=40&md5=b5bfb5879e8524910a8ae112d1fe5daf
VL - 40
SN - 02721716 (ISSN)
ER -