Feature space data augmentation for viewpoint-robust action recognition in videos - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Feature space data augmentation for viewpoint-robust action recognition in videos

Résumé

The ongoing research on human action recognition models is achieving very promising results, and the existing models reach very high performances. However, they still suffer from one major challenge: their performance decreases on viewpoints not seen in the training step of the model. In this paper, we introduce a new approach based on virtual viewpoint augmentation in the feature space, in order to increase the robustness of the action recognition models to different camera viewpoints. This approach was evaluated on two action recognition datasets: DAHLIA and Toyota SmartHome. Our model shows promising results, with a significant performance increase on both datasets for viewpoints not seen during the training step.
Fichier principal
Vignette du fichier
ICIP_paper_final_NoteIEEE.pdf (671.3 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

cea-04484436 , version 1 (29-02-2024)

Identifiants

Citer

Carla Geara, Aleksandr Setkov, Astrid Orcesi, Bertrand Luvison. Feature space data augmentation for viewpoint-robust action recognition in videos. ICIP 2023 - IEEE International Conference on Image Processing, Oct 2023, Kuala Lumpur, Malaysia. pp.585-589, ⟨10.1109/ICIP49359.2023.10222026⟩. ⟨cea-04484436⟩
3 Consultations
8 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More