Sparse Coding of Shape Trajectories for ...
Type de document :
Compte-rendu et recension critique d'ouvrage
Titre :
Sparse Coding of Shape Trajectories for Facial Expression and Action Recognition
Auteur(s) :
Tanfous, Amor [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Drira, Hassen [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Ben Amor, Boulbaba [Auteur]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Inception Institute of Artificial Intelligence [Abu Dhabi] [IIAI]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Drira, Hassen [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Ben Amor, Boulbaba [Auteur]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Inception Institute of Artificial Intelligence [Abu Dhabi] [IIAI]
Titre de la revue :
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pagination :
1-1
Éditeur :
Institute of Electrical and Electronics Engineers
Date de publication :
2019-08-05
ISSN :
0162-8828
Mot(s)-clé(s) en anglais :
Kendall's shape space
Shape trajectories
Sparse Coding and Dictionary Learning
Action recognition
Facial expression recognition !
Shape trajectories
Sparse Coding and Dictionary Learning
Action recognition
Facial expression recognition !
Discipline(s) HAL :
Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Intelligence artificielle [cs.AI]
Résumé en anglais : [en]
The detection and tracking of human landmarks in video streams has gained in reliability partly due to the availability of affordable RGB-D sensors. The analysis of such time-varying geometric data is playing an important ...
Lire la suite >The detection and tracking of human landmarks in video streams has gained in reliability partly due to the availability of affordable RGB-D sensors. The analysis of such time-varying geometric data is playing an important role in the automatic human behavior understanding. However, suitable shape representations as well as their temporal evolution, termed trajectories, often lie to nonlinear manifolds. This puts an additional constraint (i.e., nonlinearity) in using conventional Machine Learning techniques. As a solution, this paper accommodates the well-known Sparse Coding and Dictionary Learning approach to study time-varying shapes on the Kendall shape spaces of 2D and 3D landmarks. We illustrate effective coding of 3D skeletal sequences for action recognition and 2D facial landmark sequences for macro-and micro-expression recognition. To overcome the inherent nonlinearity of the shape spaces, intrinsic and extrinsic solutions were explored. As main results, shape trajectories give rise to more discriminative time-series with suitable computational properties, including sparsity and vector space structure. Extensive experiments conducted on commonly-used datasets demonstrate the competitiveness of the proposed approaches with respect to state-of-the-art.Lire moins >
Lire la suite >The detection and tracking of human landmarks in video streams has gained in reliability partly due to the availability of affordable RGB-D sensors. The analysis of such time-varying geometric data is playing an important role in the automatic human behavior understanding. However, suitable shape representations as well as their temporal evolution, termed trajectories, often lie to nonlinear manifolds. This puts an additional constraint (i.e., nonlinearity) in using conventional Machine Learning techniques. As a solution, this paper accommodates the well-known Sparse Coding and Dictionary Learning approach to study time-varying shapes on the Kendall shape spaces of 2D and 3D landmarks. We illustrate effective coding of 3D skeletal sequences for action recognition and 2D facial landmark sequences for macro-and micro-expression recognition. To overcome the inherent nonlinearity of the shape spaces, intrinsic and extrinsic solutions were explored. As main results, shape trajectories give rise to more discriminative time-series with suitable computational properties, including sparsity and vector space structure. Extensive experiments conducted on commonly-used datasets demonstrate the competitiveness of the proposed approaches with respect to state-of-the-art.Lire moins >
Langue :
Anglais
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.archives-ouvertes.fr/hal-02398951/document
- Accès libre
- Accéder au document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-02398951/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-02398951/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- Preprint_Amor_TPAMIISI_2019.pdf
- Accès libre
- Accéder au document
- d06b1a14518dca257835a7da9cd866aaa9fe.pdf
- Accès libre
- Accéder au document