Behavior Discovery and Alignment of Articulated Object Classes from Unstructured Video

We propose an automatic system for organizing the content of a collection of unstructured videos of an articulated object class (e.g., tiger, horse). By exploiting the recurring motion patterns of the class across videos, our system: (1) identifies its characteristic behaviors, and (2) recovers pixe...

Descripción completa

Detalles Bibliográficos
Autores principales: Del Pero, Luca, Ricco, Susanna, Sukthankar, Rahul, Ferrari, Vittorio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer US 2016
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7154839/
https://www.ncbi.nlm.nih.gov/pubmed/32336878
http://dx.doi.org/10.1007/s11263-016-0939-9

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7154839/
https://www.ncbi.nlm.nih.gov/pubmed/32336878
http://dx.doi.org/10.1007/s11263-016-0939-9

Ejemplares similares