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.
Unsupervised Hyperbolic Action Recognition
Lect. Notes in Networks, Syst.
Iberian Robotics conference ; 2022 ; Zaragoza, Spain November 23, 2022 - November 25, 2022
2022-11-19
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Using a Product Manifold distance for unsupervised action recognition
British Library Online Contents | 2012
|Toward Human-Robot Cooperation: Unsupervised Domain Adaptation for Egocentric Action Recognition
Springer Verlag | 2023
|Bi-GRU-Attention Enhanced Unsupervised Network for Skeleton-Based Action Recognition
Springer Verlag | 2022
|Unsupervised action proposal ranking through proposal recombination
British Library Online Contents | 2017
|Tubelets: Unsupervised Action Proposals from Spatiotemporal Super-Voxels
British Library Online Contents | 2017
|