Efficient Multi-stream Temporal Learning and Post-fusion Strategy for 3D Skeleton-based Hand Activity Recognition - Applications Domain, IRT b<>com Accéder directement au contenu
Communication Dans Un Congrès International Conference on Computer Vision Theory and Applications (VISAPP) Année : 2021

Efficient Multi-stream Temporal Learning and Post-fusion Strategy for 3D Skeleton-based Hand Activity Recognition

Stratégie efficace d'apprentissage temporel à plusieurs flux et de post-fusion pour la reconnaissance de l'activité des mains à partir d'un squelette 3D

Nam-Duong Duong
Amine Kacete
  • Fonction : Auteur
  • PersonId : 992925
Jérôme Royan
Renaud Seguier

Résumé

Recognizing first-person hand activity is a challenging task, especially when not enough data are available. In this paper, we tackle this challenge by proposing a new hybrid learning pipeline for skeleton-based hand activity recognition, which is composed of three blocks. First, for a given sequence of hand’s joint positions, the spatial features are extracted using a dedicated combination of local and global spatial hand-crafted features. Then, the temporal dependencies are learned using a multi-stream learning strategy. Finally, a hand activity sequence classifier is learned, via our Post-fusion strategy, applied to the previously learned temporal dependencies. The experiments, evaluated on two real-world data sets, show that our approach performs better than the state-of-the-art approaches. For more ablation studies, we compared our Post-fusion strategy with three traditional fusion baselines and showed an improvement above 2.4% of accuracy.
Fichier principal
Vignette du fichier
102327.pdf (893.65 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03145521 , version 1 (27-05-2021)

Identifiants

Citer

Yasser Mohamed Boutaleb, Catherine Soladie, Nam-Duong Duong, Amine Kacete, Jérôme Royan, et al.. Efficient Multi-stream Temporal Learning and Post-fusion Strategy for 3D Skeleton-based Hand Activity Recognition. 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP), Feb 2021, Online, France. pp.293-302, ⟨10.5220/0010232702930302⟩. ⟨hal-03145521⟩
227 Consultations
137 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More