Elastic Functional Coding of Riemannian Trajectories

Visual observations of dynamic phenomena, such as human actions, are often represented as sequences of smoothly-varying features. In cases where the feature spaces can be structured as Riemannian manifolds, the corresponding representations become trajectories on manifolds. Analysis of these traject...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2017-05, Vol.39 (5), p.922-936
Hauptverfasser:	Anirudh, Rushil, Turaga, Pavan, Jingyong Su, Srivastava, Anuj
Format:	Artikel
Sprache:	eng
Schlagworte:	activity recognition Clustering Coding dimensionality reduction Embedding Encoding Euclidean geometry Euclidean space Linearity Machine learning Manifolds Manifolds (mathematics) Measurement Nonlinearity Principal component analysis Rehabilitation Representations Riemann manifold Riemannian geometry Speech recognition State of the art Trajectory Trajectory analysis Velocity distribution Visual observation Visualization
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!