Action recognition based on skeleton data has recently witnessed increasing attention and progress. State-of-the-art approaches adopting Graph Convolutional networks (GCNs) can …
F Zhang, M Xu, C Xu - IEEE Transactions on Multimedia, 2021 - ieeexplore.ieee.org
Facial expression recognition (FER) has attracted much attention in recent years due to its wide applications. While some progress has been achieved thanks to the emergence of …
D Chen, G Wen, H Li, R Chen… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Facial expression recognition (FER) becomes more challenging in the wild due to unconstrained conditions, such as the different illumination, pose changes, and occlusion of …
W Huang, S Zhang, P Zhang, Y Zha… - IEEE Transactions …, 2021 - ieeexplore.ieee.org
Person-dependent facial expression recognition has received considerable research attention in recent years. Unfortunately, different identities can adversely influence …
Human tends to locate the facial landmarks with heavy occlusion by their relative position to the easily identified landmarks. The clue is defined as the landmark inherent relation while it …
M Liao, X Fan, Y Li, M Gao - Information Sciences, 2023 - Elsevier
The existing single dictionary learning algorithms are applied to face recognition and achieve satisfactory results. However, their performance is poor when dealing with noisy …
X Liu, G Zhao - IEEE Transactions on Multimedia, 2020 - ieeexplore.ieee.org
Learning 3D skeleton-based representation for gesture recognition has progressively stood out because of its invariance to the viewpoint and background dynamics of video. Typically …
G Yang, W Zou - Multimedia Tools and Applications, 2022 - Springer
In view of the problem that the current deep learning network does not fully extract and fuse spatio-temporal information in the action recognition task, resulting in low recognition …
R Friji, H Drira, F Chaieb, H Kchok… - Proceedings of the …, 2021 - openaccess.thecvf.com
Deep Learning architectures, albeit successful in mostcomputer vision tasks, were designed for data with an un-derlying Euclidean structure, which is not usually fulfilledsince pre …