An extension of kernel learning methods using a modified Log-Euclidean distance for fast and accurate skeleton-based Human Action Recognition

Enjie Ghorbel (1) , Jacques Boonaert (2) , Rémi Boutteau (3) , Stéphane Lecoeuche (2) , Xavier Savatier (3, 4)

1 ITI - Département Image et Traitement Information
2 CERI SN - IMT Nord Europe - Centre for Digital Systems
3 Pôle Instrumentation, Informatique et Systèmes
4 IRSEEM - Institut de Recherche en Systèmes Electroniques Embarqués

Domaines: Intelligence artificielle [cs.AI]

Enjie Ghorbel, Jacques Boonaert, Rémi Boutteau, Stéphane Lecoeuche, Xavier Savatier. An extension of kernel learning methods using a modified Log-Euclidean distance for fast and accurate skeleton-based Human Action Recognition. Computer Vision and Image Understanding, 2018, 175, pp.32-43. ⟨10.1016/j.cviu.2018.09.004⟩. ⟨hal-01957644⟩