Methods based on Deep Geometric Learning allow the development of solutions with a geometric approximation in different applications. In particular, the curved feature of hyperbolic space has the ability to describe hierarchical structures in a better manner. In this paper, we aim to define an unsupervised learning model for action recognition. The curved feature space is intended to be used to describe a hierarchical relationship between the clips that compose a complete video sequence. These, in turn, are related to each other by means of a triplet loss function and a VAE (Variational Auto-Encoder) neural architecture, which establishes a similarity relationship between clips to identify actions from a set of unlabelled data.
CITATION STYLE
Castro-Vargas, J. A., Garcia-Garcia, A., Martinez-Gonzalez, P., Oprea, S., & Garcia-Rodriguez, J. (2023). Unsupervised Hyperbolic Action Recognition. In Lecture Notes in Networks and Systems (Vol. 590 LNNS, pp. 479–488). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-21062-4_39
Mendeley helps you to discover research relevant for your work.