Coding Kendall's Shape Trajectories for 3D Action Recognition

Tanfous, Amor Ben; Drira, Hassen; Amor, Boulbaba Ben

Document type :

Communication dans un congrès avec actes

DOI :

10.1109/CVPR.2018.00300

Title :

Coding Kendall's Shape Trajectories for 3D Action Recognition

Author(s) :

Tanfous, Amor Ben [Auteur]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Nord Europe]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Drira, Hassen [Auteur]

Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Amor, Boulbaba Ben [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Nord Europe]

Conference title :

IEEE/CVF Computer Vision and Pattern Recognition

City :

Salt Lake City

Country :

Etats-Unis d'Amérique

Start date of the conference :

2018-06-19

Publisher :

IEEE

HAL domain(s) :

Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]

English abstract : [en]

Suitable shape representations as well as their temporal evolution, termed trajectories, often lie to non-linear mani-folds. This puts an additional constraint (i.e., non-linearity) in using conventional machine learning ...
Show more >Suitable shape representations as well as their temporal evolution, termed trajectories, often lie to non-linear mani-folds. This puts an additional constraint (i.e., non-linearity) in using conventional machine learning techniques for the purpose of classification, event detection, prediction, etc. This paper accommodates the well-known Sparse Coding and Dictionary Learning to the Kendall's shape space and illustrates effective coding of 3D skeletal sequences for action recognition. Grounding on the Riemannian geometry of the shape space, an intrinsic sparse coding and dictionary learning formulation is proposed for static skeletal shapes to overcome the inherent non-linearity of the manifold. As a main result, initial trajectories give rise to sparse code functions with suitable computational properties, including sparsity and vector space representation. To achieve action recognition, two different classification schemes were adopted. A bi-directional LSTM is directly performed on sparse code functions, while a linear SVM is applied after representing sparse code functions using Fourier temporal pyramid. Experiments conducted on three publicly available datasets show the superiority of the proposed approach compared to existing Riemannian representations and its competitiveness with respect to other recently-proposed approaches. When the benefits of invariance are maintained from the Kendall's shape representation, our approach not only overcomes the problem of non-linearity but also yields to discriminative sparse code functions.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Files

https://hal.archives-ouvertes.fr/hal-01713295/document
Open access
Access the document

https://hal.archives-ouvertes.fr/hal-01713295/document
Open access
Access the document

https://hal.archives-ouvertes.fr/hal-01713295/document
Open access
Access the document

document
Open access
Access the document

3531.pdf
Open access
Access the document

Coding Kendall's Shape Trajectories for ... BibTeX CSV Excel RIS

Files

Coding Kendall's Shape Trajectories for ...

BibTeX

CSV

Excel

RIS