Fast action detection via discriminative random forest voting and top-K subvolume search

Multiclass action detection in complex scenes is a challenging problem because of cluttered backgrounds and the large intra-class variations in each type of actions. To achieve efficient and robust action detection, we characterize a video as a collection of spatio-temporal interest points, and loca...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yu, G., Goussies, N.A., Yuan, J., Liu, Z.
Formato: JOUR
Materias:
Action detection
branch and bound
random forest
top-K search
Complex scenes
Data sets
Detection methods
Interest points
Intra-class variation
Multi-class
Mutual informations
Orders of magnitude
Random forests
Search Algorithms
Spatio-temporal
Subvolumes
Linear programming
Decision trees
Acceso en línea:http://hdl.handle.net/20.500.12110/paper_15209210_v13_n3_p507_Yu
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires

Ejemplares similares

Ejemplares similares