-
Article
Improving deep learning-based image super-resolution with residual learning and perceptual loss using SRGAN model
This study introduces a new and inventive approach designed to address the complex challenges encountered in the domain of image super-resolution (SR) tasks based on deep learning. The super-resolution generat...
-
Article
DCANet: deep context attention network for automatic polyp segmentation
Automatic and accurate polyp segmentation is significant for diagnosis and treatment of colorectal cancer. This is a challenging task due to the polyp’s shape and size diversity. Recently, various deep convolu...
-
Article
Open AccessA novel dynamic reference point model for preference-based evolutionary multiobjective optimization
In the field of preference-based evolutionary multiobjective optimization, optimization algorithms are required to search for the Pareto optimal solutions preferred by the decision maker (DM). The reference po...
-
Chapter and Conference Paper
6D Object Pose Estimation with Mutual Attention Fusion
6D object pose estimation from RGB-D images has achieved excellent performance in recent years. Since RGB-D images contain both RGB data and depth data, how to learn a comprehensive representation from these t...
-
Chapter and Conference Paper
Tire X-ray Image Defects Detection Based on Adaptive Thresholding Method
Thin line defect is a common and critical kind of tire defect, which may result in serious accidents. This paper proposes a novel adaptive threshold based model for thin line defects detection in tire X-ray im...
-
Chapter and Conference Paper
Automatical Pulmonary Nodule Detection by Feature Contrast Learning
With regard to pulmonary nodule detection, due to the similar texture and shape as particular tissues, it is difficult for Computer-Aided Detection (CAD) system in detecting pulmonary nodule with both high acc...
-
Article
Detecting Deadlocks Involving Diverse Synchronization Mechanisms Using Extended Petri Nets
Synchronization mechanisms provide flexibility for concurrent programming. However, they also increase the difficulty of deadlock detection, since detection methods have to consider deadlocks caused by differe...
-
Article
MagicDetector: A Precise and Scalable Static Deadlock Detector for C/C++ Programs
Existing static deadlock detectors suffer from either lack of precise interprocedural path- and context-sensitive analysis or lack of scalability. In addition, they only take a few of synchronous events into a...
-
Article
Open AccessBLAS3 optimization for the Godson-3B1500
This paper proposes a performance model for general matrix multiplication (GEMM) on decoupled access/execute (DAE) architecture platforms, in order to guide improvements of the GEMM performance in the Godson-3...
-
Chapter and Conference Paper
Multi-GPU Based Recurrent Neural Network Language Model Training
Recurrent neural network language models (RNNLMs) have been applied in a wide range of research fields, including nature language processing and speech recognition. One challenge in training RNNLMs is the heav...
-
Article
Minimum cost service composition in service overlay networks
In service computing, it is often desirable to find the service composition solution for a given service composition request such that the total cost of the service composition solution is minimized. In this p...
-
Chapter and Conference Paper
Automated Recognition of Sequential Patterns in Captured Motion Streams
Motion capture data has been frequently used in computer animation and video games. Motions are often captured in a continuous manner such that a motion contains multiple patterns joined sequentially without o...
-
Chapter and Conference Paper
User Feedback for Improving Question Categorization in Web-Based Question Answering Systems
Question categorization, which automatically suggests a few categories to host a user’s question, is a useful technique in Web-based question answering systems. In this paper, we propose a question categorizat...
-
Chapter and Conference Paper
An Efficient Fibonacci Series Based Hierarchical Application-Layer Multicast Protocol
In this paper, an efficient Fibonacci series based hierarchical protocol-HFTM (Hierarchical Fibonacci Tree Multicast) is proposed for application-layer multicast. It adopts the idea of layer and cluster to con...
-
Article
Efficient indirect all-to-all personalized communication on rings and 2-D tori
All-to-All personalized communication is a basic communication operation in a parallel computing environment. There are a lot of results appearing in literature. All these communication algorithms can be divid...
