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 …

Convolutional neural networks or vision transformers: Who will win the race for action recognitions in visual data?

O Moutik, H Sekkat, S Tigani, A Chehri, R Saadane… - Sensors, 2023 - mdpi.com
Understanding actions in videos remains a significant challenge in computer vision, which
has been the subject of several pieces of research in the last decades. Convolutional neural …

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 …

Hierarchically decomposed graph convolutional networks for skeleton-based action recognition

J Lee, M Lee, D Lee, S Lee - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Graph convolutional networks (GCNs) are the most commonly used methods for skeleton-
based action recognition and have achieved remarkable performance. Generating …

Masked motion predictors are strong 3d action representation learners

Y Mao, J Deng, W Zhou, Y Fang… - Proceedings of the …, 2023 - openaccess.thecvf.com
In 3D human action recognition, limited supervised data makes it challenging to fully tap into
the modeling potential of powerful networks such as transformers. As a result, researchers …

Generative action description prompts for skeleton-based action recognition

W **ang, C Li, Y Zhou, B Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Skeleton-based action recognition has recently received considerable attention. Current
approaches to skeleton-based action recognition are typically formulated as one-hot …

3mformer: Multi-order multi-mode transformer for skeletal action recognition

L Wang, P Koniusz - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Many skeletal action recognition models use GCNs to represent the human body by 3D
body joints connected body parts. GCNs aggregate one-or few-hop graph neighbourhoods …

Unified pose sequence modeling

LG Foo, T Li, H Rahmani, Q Ke… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Abstract We propose a Unified Pose Sequence Modeling approach to unify heterogeneous
human behavior understanding tasks based on pose data, eg, action recognition, 3D pose …

Pyramid self-attention polymerization learning for semi-supervised skeleton-based action recognition

B Xu, X Shu - arxiv preprint arxiv:2302.02327, 2023 - arxiv.org
Most semi-supervised skeleton-based action recognition approaches aim to learn the
skeleton action representations only at the joint level, but neglect the crucial motion …

Skateformer: skeletal-temporal transformer for human action recognition

J Do, M Kim - European Conference on Computer Vision, 2024 - Springer
Skeleton-based action recognition, which classifies human actions based on the
coordinates of joints and their connectivity within skeleton data, is widely utilized in various …