Human action recognition from various data modalities: A review

Z Sun, Q Ke, H Rahmani, M Bennamoun… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Human Action Recognition (HAR) aims to understand human behavior and assign a label to
each action. It has a wide range of applications, and therefore has been attracting increasing …

Deep learning-based human pose estimation: A survey

C Zheng, W Wu, C Chen, T Yang, S Zhu, J Shen… - ACM Computing …, 2023 - dl.acm.org
Human pose estimation aims to locate the human body parts and build human body
representation (eg, body skeleton) from input data such as images and videos. It has drawn …

Revisiting skeleton-based action recognition

H Duan, Y Zhao, K Chen, D Lin… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Human skeleton, as a compact representation of human action, has received increasing
attention in recent years. Many skeleton-based action recognition methods adopt GCNs to …

Star-transformer: a spatio-temporal cross attention transformer for human action recognition

D Ahn, S Kim, H Hong, BC Ko - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In action recognition, although the combination of spatio-temporal videos and skeleton
features can improve the recognition performance, a separate model and balancing feature …

Early, intermediate and late fusion strategies for robust deep learning-based multimodal action recognition

SY Boulahia, A Amamra, MR Madi, S Daikh - Machine Vision and …, 2021 - Springer
Multimodal action recognition techniques combine several image modalities (RGB, Depth,
Skeleton, and InfraRed) for a more robust recognition. According to the fusion level in the …

Mmnet: A model-based multimodal network for human action recognition in rgb-d videos

XB Bruce, Y Liu, X Zhang, S Zhong… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Human action recognition (HAR) in RGB-D videos has been widely investigated since the
release of affordable depth sensors. Currently, unimodal approaches (eg, skeleton-based …

Toward proactive human–robot collaborative assembly: A multimodal transfer-learning-enabled action prediction approach

S Li, P Zheng, J Fan, L Wang - IEEE Transactions on Industrial …, 2021 - ieeexplore.ieee.org
Human–robot collaborative assembly (HRCA) is vital for achieving high-level flexible
automation for mass personalization in today's smart factories. However, existing works in …

Multi-view action recognition using contrastive learning

K Shah, A Shah, CP Lau… - Proceedings of the …, 2023 - openaccess.thecvf.com
In this work, we present a method for RGB-based action recognition using multi-view videos.
We present a supervised contrastive learning framework to learn a feature embedding …

RGB-D data-based action recognition: a review

MB Shaikh, D Chai - Sensors, 2021 - mdpi.com
Classification of human actions is an ongoing research problem in computer vision. This
review is aimed to scope current literature on data fusion and action recognition techniques …

Multi-modal 3d human pose estimation with 2d weak supervision in autonomous driving

J Zheng, X Shi, A Gorban, J Mao… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract 3D human pose estimation (3D HPE) in autonomous vehicles (AV) differs from
other use cases in many factors, including the 3D resolution and range of data, absence of …