UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition

Résumé

Action recognition based on skeleton data has recently witnessed increasing attention and progress. State-of-the-art approaches adopting Graph Convolutional networks (GCNs) can effectively extract features on human skeletons relying on the pre-defined human topology. Despite associated progress, GCN-based methods have difficulties to generalize across domains, especially with different human topological structures. In this context, we introduce UNIK, a novel skeleton-based action recognition method that is not only effective to learn spatio-temporal features on human skeleton sequences but also able to generalize across datasets. This is achieved by learning an optimal dependency matrix from the uniform distribution based on a multi-head attention mechanism. Subsequently, to study the cross-domain generalizability of skeleton-based action recognition in real-world videos, we re-evaluate state-of-the-art approaches as well as the proposed UNIK in light of a novel Posetics dataset. This dataset is created from Kinetics-400 videos by estimating, refining and filtering poses. We provide an analysis on how much performance improves on smaller benchmark datasets after pre-training on Posetics for the action classification task. Experimental results show that the proposed UNIK, with pre-training on Posetics, generalizes well and outperforms state-of-the-art when transferred onto four target action classification datasets: Toyota Smarthome, Penn Action, NTU-RGB+D 60 and NTU-RGB+D 120.
Fichier principal
Vignette du fichier
BMVC2021-0014.pdf (1.92 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03476581 , version 1 (13-12-2021)

Identifiants

Citer

Di Yang, Yaohui Wang, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca, et al.. UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition. BMVC 2021 - The British Machine Vision Conference, Nov 2021, Virtual, United Kingdom. ⟨hal-03476581⟩
100 Consultations
115 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More