Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Human action recognition by means of subtensor projections and dense trajectories

Autor
Carmona, J. M.; Climent, J.
Tipus d'activitat
Article en revista
Revista
Pattern recognition
Data de publicació
2018-09
Volum
81
Pàgina inicial
443
Pàgina final
455
DOI
https://doi.org/10.1016/j.patcog.2018.04.015 Obrir en finestra nova
Projecte finançador
Colaboración robots-humanos para el transporte de productos en zonas urbanas
Repositori
http://hdl.handle.net/2117/118301 Obrir en finestra nova
URL
https://www.sciencedirect.com/science/article/pii/S0031320318301493 Obrir en finestra nova
Resum
In last years, most human action recognition works have used dense trajectories features, to achieve state-of-the-art results. Histograms of Oriented Gradients (HOG), Histogram of Optical Flow (HOF) and Motion Boundary Histograms (MBH) features are extracted from regions and being tracked across the frames. The goal of this paper is to improve the performance obtained by means of Improved Dense Trajectories (IDTs), adding new features based on temporal templates. We construct these templates co...
Paraules clau
Action recognition, Dense trajectories, Keypoint descriptors, Subtensors, Temporal template
Grup de recerca
VIS - Visió Artificial i Sistemes Intel.ligents

Participants