Dse-net: Deep simultaneous estimation network for low-light image enhancement

K Singh, AS Parihar - Journal of Visual Communication and Image …, 2023 - Elsevier
This paper presents a novel approach for low-light image enhancement. We propose a deep
simultaneous estimation network (DSE-Net), which simultaneously estimates the reflectance …

Data, language and graph-based reasoning methods for identification of human malicious behaviors in nuclear security

Z Li, X Song, S Chen, K Demachi - Expert Systems with Applications, 2024 - Elsevier
Identification of human malicious behaviors is a demanding problem in nuclear security due
to its potential to cause huge personnel and economic casualties. With the visibly rapid …

Human-object interaction detection based on cascade multi-scale transformer

L **a, X Ding - Applied Intelligence, 2024 - Springer
Human-object interaction (HOI) detection is an advanced computer vision task for detecting
the relationship between human and surrounding objects. Some methods have emerged to …

Integration of Feature and Decision Fusion With Deep Learning Architectures for Video Classification

RS Kiziltepe, JQ Gan, JJ Escobar - IEEE Access, 2024 - ieeexplore.ieee.org
Information fusion is frequently employed to integrate diverse inputs, including sensory data,
features, or decisions, in order to leverage the advantageous relationships among various …

Learning dynamic relationship between joints for 3D hand pose estimation from single depth map

H **ng, J Yang, Y **ao - Journal of Visual Communication and Image …, 2023 - Elsevier
Abstract 3D hand pose estimation from a single depth map is an essential topic in computer
vision. Most existing methods are devoted to designing a model to capture more spatial …

A novel multi-stream hand-object interaction network for assembly action recognition

L Shaochen, Z Liu, Y Huang, D Liu, G Duan… - Robotic Intelligence and …, 2024 - emerald.com
Purpose Assembly action recognition plays an important role in assembly process
monitoring and human-robot collaborative assembly. Previous works overlook the …

Data, language and graph-based reasoning methods for identification of human malicious behaviors in nuclear security

Z Li, X Song, S Chen, K Demachi - Language and Graph-Based …, 2023 - papers.ssrn.com
Identification of human malicious behaviors proves to be a demanding problem in nuclear
security, considering its potential to cause huge personnel and economic casualties. With …

Learning full context feature for human motion prediction

H **ng, Y Zhou, J Yang, Y **ao - Journal of Visual Communication and …, 2023 - Elsevier
Human motion prediction aims to predict the target poses given the previous poses. Most
existing methods are devoted to extracting richer motion features from only the given …

WPL-Based Constraint for 3D Human Pose Estimation from a Single Depth Image

H **ng, J Yang - Sensors, 2022 - mdpi.com
Three-dimensional human pose estimation from depth maps is a fast-growing research area
in computer vision. The distal joints of the human body are more flexible than the proximal …

Integration of Feature and Decision Fusion with Deep Learning Architectures for Video Classification

R Savran Kiziltepe, JQ Gan, JJ Escobar Pérez - 2024 - digibug.ugr.es
Information fusion is frequently employed to integrate diverse inputs, including sensory data,
features, or decisions, in order to leverage the advantageous relationships among various …