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 …

A survey on deep learning for human activity recognition

F Gu, MH Chung, M Chignell, S Valaee… - ACM Computing …, 2021 - dl.acm.org
Human activity recognition is a key to a lot of applications such as healthcare and smart
home. In this study, we provide a comprehensive survey on recent advances and challenges …

Outlook on human-centric manufacturing towards Industry 5.0

Y Lu, H Zheng, S Chand, W **a, Z Liu, X Xu… - Journal of Manufacturing …, 2022 - Elsevier
The recent shift to wellbeing, sustainability, and resilience under Industry 5.0 has prompted
formal discussions that manufacturing should be human-centric–placing the wellbeing of …

Shunted self-attention via multi-scale token aggregation

S Ren, D Zhou, S He, J Feng… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Abstract Recent Vision Transformer (ViT) models have demonstrated encouraging results
across various computer vision tasks, thanks to its competence in modeling long-range …

Constructing stronger and faster baselines for skeleton-based action recognition

YF Song, Z Zhang, C Shan… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
One essential problem in skeleton-based action recognition is how to extract discriminative
features over all skeleton joints. However, the complexity of the recent State-Of-The-Art …

Multi-granularity anchor-contrastive representation learning for semi-supervised skeleton-based action recognition

X Shu, B Xu, L Zhang, J Tang - IEEE Transactions on Pattern …, 2022 - ieeexplore.ieee.org
In the semi-supervised skeleton-based action recognition task, obtaining more
discriminative information from both labeled and unlabeled data is a challenging problem …

Human activity recognition (har) using deep learning: Review, methodologies, progress and future research directions

P Kumar, S Chauhan, LK Awasthi - Archives of Computational Methods in …, 2024 - Springer
Human activity recognition is essential in many domains, including the medical and smart
home sectors. Using deep learning, we conduct a comprehensive survey of current state …

Molo: Motion-augmented long-short contrastive learning for few-shot action recognition

X Wang, S Zhang, Z Qing, C Gao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Current state-of-the-art approaches for few-shot action recognition achieve promising
performance by conducting frame-level matching on learned visual features. However, they …

Vision-based human activity recognition: a survey

DR Beddiar, B Nini, M Sabokrou, A Hadid - Multimedia Tools and …, 2020 - Springer
Human activity recognition (HAR) systems attempt to automatically identify and analyze
human activities using acquired information from various types of sensors. Although several …

A review of multimodal human activity recognition with special emphasis on classification, applications, challenges and future directions

SK Yadav, K Tiwari, HM Pandey, SA Akbar - Knowledge-Based Systems, 2021 - Elsevier
Human activity recognition (HAR) is one of the most important and challenging problems in
the computer vision. It has critical application in wide variety of tasks including gaming …