Results 61 to 70 of about 282 (134)

Skräp in, skräp ut : En utredning av bruskänslighet i graf-baserad rörelseigenkänning

open access: yes, 2021
Human action recognition is the task of classifying human movement and actions from video data. To benchmark different algorithms within the action recognition field, a common benchmark dataset, called NTU-RGB+D is used.
Molén, Ricky, Rehn, Ruben
core   +2 more sources

2D human skeleton action recognition with spatial constraints

open access: yesIET Computer Vision, Volume 18, Issue 7, Page 968-981, October 2024.
(1) A novel 2D human skeleton action recognition model with spatial constraints, named 2D‐SCHAR, is introduced to address the ambiguity and uncertainty associated with human action recognition in 2D surveillance videos. (2) These issues stem from the absence of depth information in the action data, thus we concentrate on two main challenges: depth ...
Lei Wang   +4 more
wiley   +1 more source

Semantics-Enhanced Temporal Graph Networks for Content Caching and Energy Saving

open access: yes, 2023
The enormous amount of network equipment and users implies a tremendous growth of Internet traffic for multi-media services. To mitigate the traffic pressure, architectures with in-network storage have been proposed to cache popular content at devices in
Zhu, Jianhang   +5 more
core   +1 more source

GR‐Former: Graph‐reinforcement transformer for skeleton‐based driver action recognition

open access: yesIET Computer Vision, Volume 18, Issue 7, Page 982-991, October 2024.
By introducing graph structure information to directionally reinforce the effect of the self‐attention mechanism, dynamically learning and aggregating features between joints at multiple levels, the authors’ model constructs a richer feature vector space, enhancing its expressiveness and recognition accuracy, and has a simpler model structure ...
Zhuoyan Xu, Jingke Xu
wiley   +1 more source

Dynamic graph neural networks for UAV-based group activity recognition in structured team sports

open access: yesFrontiers in Neurorobotics
IntroductionUnderstanding group actions in real-world settings is essential for the advancement of applications in surveillance, robotics, and autonomous systems.
Ishrat Zahra   +10 more
doaj   +1 more source

A  substructure‐aware graph neural network incorporating relation features for drug–drug interaction prediction

open access: yesQuantitative Biology, Volume 12, Issue 3, Page 255-270, September 2024.
Abstract Identifying drug–drug interactions (DDIs) is an important aspect of drug design research, and predicting DDIs serves as a crucial guarantee for avoiding potential adverse effects. Current substructure‐based prediction methods still have some limitations: (i) The process of substructure extraction does not fully exploit the graph structure ...
Liangcheng Dong   +5 more
wiley   +1 more source

Temporal channel reconfiguration multi‐graph convolution network for skeleton‐based action recognition

open access: yesIET Computer Vision, Volume 18, Issue 6, Page 813-825, September 2024.
The authors introduce a novel Temporal Channel Reconfiguration Multi‐Graph Convolution Network (TRMGCN) that addresses limitations in existing methods for skeleton‐based action recognition by introducing the Temporal Channel Fusion with Guidance (TCFG) module for capturing crucial temporal information and the Top‐Down Attention Multi‐graph Independent ...
Siyue Lei   +5 more
wiley   +1 more source

AquaGraph and AGN-Net: A Biologically Inspired Framework for Scalable and Adaptive Graph Neural Networks

open access: yesIEEE Access
Graph Neural Networks (GNNs) are powerful tools for learning on relational data, but many real-world graphs evolve continuously, and existing Dynamic GNNs (DGNNs) often process large portions of the graph at every time step.
Md. Redwan Islam   +2 more
doaj   +1 more source

Hereditary cutaneous leiomyomatosis and low‐grade glioma due to a fumarate hydratase mutation

open access: yes
Journal of the European Academy of Dermatology and Venereology, Volume 39, Issue 2, Page e122-e124, February 2025.
Jörg Laske   +10 more
wiley   +1 more source

Fire emergency management of large shopping malls: IoT-based evacuee tracking and dynamic path optimization

open access: yesAlexandria Engineering Journal
As urbanization accelerates and buildings become more complex, fire emergency evacuation has become increasingly challenging. Traditional evacuation plans often struggle with slow response times and suboptimal path planning in real-time dynamic and ...
Ziyang Zhang   +2 more
doaj   +1 more source

Home - About - Disclaimer - Privacy