108 Result(s)
within
English
Computer Science
Chunxia **g
-
Article
Open AccessIlluminator: Image-based illumination editing for indoor scene harmonization
Illumination harmonization is an important but challenging task that aims to achieve illumination compatibility between the foreground and background under different illumination conditions. Most current studi...
-
Article
Virtual reality technologies to provide performance feedback for motor and imagery training
The key research objective is to explore the key functions of virtual reality technology used by educators to improve motor and imagery training in athletes. The sample was 160 students from Shandong Sport Uni...
-
Article
Comparing competency-oriented student activities between expert and novice teachers in China: Insights from an epistemic network analysis (ENA)
Competency-oriented student activities are an important means of enabling teachers to move from teaching fundamental knowledge to develo** students' subject competencies. To examine mathematics teacher novic...
-
Chapter and Conference Paper
RGB-D Road Segmentation Based on Geometric Prior Information
Deep data can provide rich spatial structure information, which can effectively exclude the interference of lighting and road texture in road segmentation. This paper proposes a road segmentation model based o...
-
Chapter and Conference Paper
Multi-Scale Implicit Surface Reconstruction for Outdoor Scenes
The images used to reconstruct 3D models in outdoor scenes are generally captured at different scales. Accurately reconstructing geometry from multi-scale images has not been extensively addressed. This work p...
-
Article
Towards High-Resolution Specular Highlight Detection
Specular highlight detection is an essential task with various applications in computer vision. This paper aims to detect specular highlights in single high-resolution images using deep learning while avoiding...
-
Article
CRD-CGAN: category-consistent and relativistic constraints for diverse text-to-image generation
Generating photo-realistic images from a text description is a challenging problem in computer vision. Previous works have shown promising performance to generate synthetic images conditional on text by Genera...
-
Article
Monocular human depth estimation with 3D motion flow and surface normals
We propose a novel monocular human depth estimation method using video sequences as training data. We jointly train the depth and 3D motion flow networks with photometric and 3D geometric consistency constrain...
-
Article
Long Short-Term Memory Networks with Multiple Variables for Stock Market Prediction
Long short-term memory (LSTM) networks have been successfully applied to many fields including finance. However, when the input contains multiple variables, a conventional LSTM does not distinguish the contrib...
-
Article
No-reference image quality assessment of multi-level residual feature augmentation
No-reference image quality assessment (NR-IQA) has a wide range of application scenarios and occupies an important position in the field of digital image processing. In this paper, we propose a multi-level fea...
-
Article
Effects of Boletus Poisoning on Estrogen Receptors and Neurotransmitters in Rats Based on ERk1/2 Pathway
Estrogen is primarily an endocrine hormone produced by the ovaries and, to a lesser degree, glands of the adrenal cortex's zona reticularis layer. However, it can be synthesized from other tissues and can poss...
-
Chapter and Conference Paper
GERNS: A Graph Embedding with Repeat-Free Neighborhood Structure for Subgraph Matching Optimization
Subgraph matching is used to determine whether a query graph exists within a target graph, and appears in a lot applications of domains including social sciences, chemistry, biology and database systems. Exist...
-
Chapter and Conference Paper
Research on Cross-Domain Heterogeneous Information Interaction System in Complex Environment Based on Blockchain Technology
In the field of information interaction, when a project involves a large amount of cross-domain heterogeneous information, it is difficult to transmit and update the required information in a timely, accurate,...
-
Chapter and Conference Paper
Generating Network Security Defense Strategy Based on Cyber Threat Intelligence Knowledge Graph
Network systems are composed of thousands of devices connected in complex network topologies. The diversity and complexity of these devices increase the security risks of network systems. Cyber Threat Intellig...
-
Article
Open AccessSelf-supervised coarse-to-fine monocular depth estimation using a lightweight attention module
Self-supervised monocular depth estimation has been widely investigated and applied in previous works. However, existing methods suffer from texture-copy, depth drift, and incomplete structure. It is difficult...
-
Article
A Novel Data Augmentation Method for Chinese Character Spatial Structure Recognition by Normalized Deformable Convolutional Networks
In this paper, we propose a novel data augmentation method and a normalized deformable convolutional network for natural image classification and handwritten Chinese character structure recognition. The spatia...
-
Chapter and Conference Paper
Deep Relevant Feature Focusing for Out-of-Distribution Generalization
Convolution Neural Networks (CNNs) often fail to maintain their performance when they confront new test domains. Unlike human’s strong ability of abstraction and connection, CNNs learn everything relevant and ...
-
Chapter and Conference Paper
Sports Video Moving Object Detection and Tracking Technology Based on Hybrid Algorithm
With the improvement of the level of sports competition, the requirements of sports training are also increasing. In the past, only relying on the intuitive training of coaches can not meet the needs of sports...
-
Chapter and Conference Paper
Foreground-Background Collaboration Network for Salient Object Detection
Saliency object detection has become an active topic in both computer vision and multimedia fields. Though much remarkable progress has been achieved, it is still challenging to predicted saliency maps correct...
-
Article
CondenseNet with exclusive lasso regularization
Group convolution has been widely used in deep learning community to achieve computation efficiency. In this paper, we develop CondenseNet-elasso to eliminate feature correlation among different convolution gr...
