Self-Attention Network for Skeleton-based Human Action Recognition

Cho, Sangwoo; Maqbool, M.H.; Liu, Fei; Foroosh, Hassan

doi:10.48550/arxiv.1912.08435

Cited by 2 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, Cho et al. [ 120 ] proposed a novel model called Self-Attention Network (SAN) that completely utilizes the self-attention mechanism to model spatial-temporal correlations. Shi et al.…”

Section: D Sar With Deep Learningmentioning

confidence: 99%

A Survey on 3D Skeleton-Based Action Recognition Using Learning Method

Ren,

Liu,

Ding

et al. 2024

Cyborg Bionic Syst

View full text Add to dashboard Cite

Three-dimensional skeleton-based action recognition (3D SAR) has gained important attention within the computer vision community, owing to the inherent advantages offered by skeleton data. As a result, a plethora of impressive works, including those based on conventional handcrafted features and learned feature extraction methods, have been conducted over the years. However, prior surveys on action recognition have primarily focused on video or red-green-blue (RGB) data-dominated approaches, with limited coverage of reviews related to skeleton data. Furthermore, despite the extensive application of deep learning methods in this field, there has been a notable absence of research that provides an introductory or comprehensive review from the perspective of deep learning architectures. To address these limitations, this survey first underscores the importance of action recognition and emphasizes the significance of 3-dimensional (3D) skeleton data as a valuable modality. Subsequently, we provide a comprehensive introduction to mainstream action recognition techniques based on 4 fundamental deep architectures, i.e., recurrent neural networks, convolutional neural networks, graph convolutional network, and Transformers. All methods with the corresponding architectures are then presented in a data-driven manner with detailed discussion. Finally, we offer insights into the current largest 3D skeleton dataset, NTU-RGB+D, and its new edition, NTU-RGB+D 120, along with an overview of several top-performing algorithms on these datasets. To the best of our knowledge, this research represents the first comprehensive discussion of deep learning-based action recognition using 3D skeleton data.

show abstract

Section: D Sar With Deep Learningmentioning

confidence: 99%

A Survey on 3D Skeleton-Based Action Recognition Using Learning Method

Ren,

Liu,

Ding

et al. 2024

Cyborg Bionic Syst

View full text Add to dashboard Cite

show abstract

“…SATD-GCN [21] utilized spatial attention pooling and temporal graph convolution module to acquire fine-grained information for action classification. Cho et al [22] proposed three variants of self-attention network. Tu et al [23] introduced a semi-supervised modality for skeleton-based action recognition.…”

Section: Human Skeleton Action Recognitionmentioning

confidence: 99%

Human Skeleton Action Recognition Based on Monocular Depth Estimation

Wang

Zhang

Gu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Human action recognition exhibits limited accuracy in video surveillance due to the 2D information captured with the monocular cameras. To address the problem, a monocular depth estimation (SARDE)-based human skeleton action recognition method is proposed in this study. The proposed method comprises two tasks, i.e., human skeleton action recognition and monocular depth estimation, with the aim of transforming 2D human action into 3D. The two tasks are integrated with multi-task manner in an end-to-end training to fully utilize the correlation between action 1 recognition and depth estimation by sharing learning data to learn the depth features of the human skeleton joints more effectively for human action recognition. In this study, the graph-structured depth estimations methods with inception blocks and skip connections are investigated. The experimental results verify the effectiveness and superiority of the proposed model in skeleton action recognition, the model reaches state-of-the-art on the datasets.

show abstract

Self-Attention Network for Skeleton-based Human Action Recognition

Cited by 2 publications

References 35 publications

A Survey on 3D Skeleton-Based Action Recognition Using Learning Method

A Survey on 3D Skeleton-Based Action Recognition Using Learning Method

Human Skeleton Action Recognition Based on Monocular Depth Estimation

Contact Info

Product

Resources

About