Classical and modern face recognition approaches: a complete review

W Ali, W Tian, SU Din, D Iradukunda… - Multimedia tools and …, 2021 - Springer
Human face recognition have been an active research area for the last few decades.
Especially, during the last five years, it has gained significant research attention from …

RGB-D sensing based human action and interaction analysis: A survey

B Liu, H Cai, Z Ju, H Liu - Pattern Recognition, 2019 - Elsevier
Human activity recognition has been actively studied in the last three decades. Compared to
human action performed by a single person, human interaction is more complex due to the …

Interaction relational network for mutual action recognition

M Perez, J Liu, AC Kot - IEEE Transactions on Multimedia, 2021 - ieeexplore.ieee.org
Person-person mutual action recognition (also referred to as interaction recognition) is an
important research branch of human activity analysis. Current solutions in the field–mainly …

Dyadic relational graph convolutional networks for skeleton-based human interaction recognition

L Zhu, B Wan, C Li, G Tian, Y Hou, K Yuan - Pattern Recognition, 2021 - Elsevier
Skeleton-based human interaction recognition is a challenging task requiring all abilities to
recognize spatial, temporal, and interactive features. These abilities rarely co-exist in …

Content-based management of human motion data: survey and challenges

J Sedmidubsky, P Elias, P Budikova, P Zezula - IEEE Access, 2021 - ieeexplore.ieee.org
Digitization of human motion using skeleton representations offers exciting possibilities for a
large number of applications but, at the same time, requires innovative techniques for their …

Multi-localized sensitive autoencoder-attention-LSTM for skeleton-based action recognition

W Ng, M Zhang, T Wang - IEEE Transactions on Multimedia, 2021 - ieeexplore.ieee.org
One of key challenges of skeleton-based action recognition (SAR) tasks is the complex
nature of human motion patterns. Variations such as performers and viewpoints may impose …

Skeleton-based relational reasoning for group activity analysis

M Perez, J Liu, AC Kot - Pattern Recognition, 2022 - Elsevier
Research on group activity recognition mostly leans on the standard two-stream approach
(RGB and Optical Flow) as their input features. Few have explored explicit pose information …

Arbitrary-view human action recognition: A varying-view RGB-D action dataset

Y Ji, Y Yang, F Shen, HT Shen… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Current researches of action recognition which focus on single-view and multi-view
recognition can hardly satisfy the requirements of human-robot interaction (HRI) applications …

Two-person graph convolutional network for skeleton-based human interaction recognition

Z Li, Y Li, L Tang, T Zhang, J Su - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Graph convolutional networks (GCNs) have been the predominant methods in skeleton-
based human action recognition, including human-human interaction recognition. However …

Video Interaction Recognition using an Attention Augmented Relational Network and Skeleton Data

F Askari, C Yared, R Ramaprasad… - Proceedings of the …, 2024 - openaccess.thecvf.com
Recognizing interactions in multi-person videos known as Video Interaction Recognition
(VIR) is crucial for understanding video content. Often the human skeleton pose (skeleton for …