 |
Conference papers
Sparse Shift-Invariant Representation of Local 2D Patterns and Sequence Learning for Human Action Recognition
Abstract : Most existing methods for action recognition mainly rely on manually engineered features which, despite their good performances, are highly problem dependent. We propose in this paper a fully automated model, which learns to classify human actions without using any prior knowledge. A convolutional sparse auto- encoder learns to extract sparse shift-invariant representations of the 2D local patterns present in each video frame. The evolution of these mid-level features is learned by a Recurrent Neural Network trained to classify each sequence. Experimental results on the KTH dataset show that the proposed approach outperforms existing models which rely on learned-features, and gives comparable results with the best related works.
https://hal.archives-ouvertes.fr/hal-01353014
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Wednesday, August 10, 2016 - 4:19:04 PM
Last modification on : Wednesday, November 20, 2019 - 3:01:33 AM
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Wednesday, August 10, 2016 - 4:19:04 PM
Last modification on : Wednesday, November 20, 2019 - 3:01:33 AM
