A review on action recognition for accident detection in smart city transportation systems

VA Adewopo, N Elsayed, Z ElSayed, M Ozer… - Journal of Electrical …, 2023 - Springer
Accident detection and public traffic safety is a crucial aspect of safe and better community.
Monitoring traffic flow in smart cities using different surveillance cameras plays a crucial role …

[HTML][HTML] Two-step domain adaptation for underwater image enhancement

Q Jiang, Y Zhang, F Bao, X Zhao, C Zhang, P Liu - Pattern Recognition, 2022 - Elsevier
In recent years, underwater image enhancement methods based on deep learning have
achieved remarkable results. Since the images obtained in complex underwater scenarios …

Continuous human action recognition for human-machine interaction: a review

H Gammulle, D Ahmedt-Aristizabal, S Denman… - ACM Computing …, 2023 - dl.acm.org
With advances in data-driven machine learning research, a wide variety of prediction
models have been proposed to capture spatio-temporal features for the analysis of video …

Relation-mining self-attention network for skeleton-based human action recognition

K Gedamu, Y Ji, LL Gao, Y Yang, HT Shen - Pattern Recognition, 2023 - Elsevier
Modeling spatiotemporal global dependencies and dynamics of body joints are crucial to
recognizing actions from 3D skeleton sequences. We propose a Relation-mining Self …

Lightweight semi-supervised network for single image rain removal

N Jiang, J Luo, J Lin, W Chen, T Zhao - Pattern Recognition, 2023 - Elsevier
Deep learning technologies have shown their advantages in Single Image Rain Removal
(SIRR) tasks. However, the derained results of most methods are limited to some …

Self-Relational Graph Convolution Network for Skeleton-Based Action Recognition

SB Yussif, N Xie, Y Yang, HT Shen - Proceedings of the 31st ACM …, 2023 - dl.acm.org
Using a Graph convolution network (GCN) for constructing and aggregating node features
has been helpful for skeleton-based action recognition. The strength of the nodes' relation of …

Global-local cross-view fisher discrimination for view-invariant action recognition

L Gao, Y Ji, Y Yang, HT Shen - … of the 30th ACM International Conference …, 2022 - dl.acm.org
View change brings a significant challenge to action representation and recognition due to
pose occlusion and deformation. We propose a Global-Local Cross-View Fisher …

Hybrid two-stream dynamic CNN for view adaptive human action recognition using ensemble learning

MH Javed, Z Yu, T Li, TM Rajeh, F Rafique… - International Journal of …, 2022 - Springer
Human actions are sequential, and structured patterns of the body parts and their
movements. In this paper, we present a hybrid two-stream convolutional neural network …

Affective action and interaction recognition by multi-view representation learning from handcrafted low-level skeleton features

D Avola, M Cascio, L Cinque, A Fagioli… - International journal of …, 2022 - World Scientific
Human feelings expressed through verbal (eg voice) and non-verbal communication
channels (eg face or body) can influence either human actions or interactions. In the …

Parallel disentangling network for human–object interaction detection

Y Cheng, H Duan, C Wang, Z Chen - Pattern Recognition, 2024 - Elsevier
Human–object interaction (HOI) detection aims to localize and classify triplets of human,
object and interaction from a given image. Earlier two-stage methods suffer both from …