-
Chapter and Conference Paper
C-volution: A Hybrid Operator for Visual Recognition
Convolution is a fundamental building block of modern neural networks, playing a critical role in the success of deep learning for vision tasks. However, convolutional neural networks exhibit limited spatial c...
-
Chapter and Conference Paper
Research on Experimental Teaching Reform of Computer Principles Course Based on Logisim Simulation Software
On the basis of analyzing the current existing problems in the experimental teaching of computer principles course, Logisim virtual simulation software is introduced to reform the experimental system. Four exp...
-
Chapter and Conference Paper
A New Augmented Method for Processing Video Datasets Based on Deep Neural Network
Large datasets are required for deep learning to achieve good performance. However, there is a lack of sufficient training datasets in many research fields, which may become a shortcoming of computer vision ap...
-
Article
Open AccessL2MXception: an improved Xception network for classification of peach diseases
Peach diseases can cause severe yield reduction and decreased quality for peach production. Rapid and accurate detection and identification of peach diseases is of great importance. Deep learning has been appl...
-
Chapter and Conference Paper
Classification of Tea Pests Based on Automatic Machine Learning
Tea pests, as one of the main threats in the tea gardens, cause considerable losses to the tea industry every year. In order to ensure the quality of the tea production process, it is of great importance to de...
-
Chapter and Conference Paper
MTFCN: Multi-task Fully Convolutional Network for Cow Face Detection
Automatic cow detection with computer vision is a hitting topic in recent years. Recent studies found that adding facial alignment task can improve the performance of the detection. Instead of using the cascad...
-
Article
Existence identifications of unobserved paths in graph-based social networks
In recent years, social networks have surged in popularity as one of the main applications of the Internet. One key aspect of social network research is exploring important unobserved network information which...
-
Chapter and Conference Paper
Localization and Recognition of Single Particle Image in Microscopy Micrographs Based on Region Based Convolutional Neural Networks
Single-particle Cryo-electron microscopy (Cryo-EM) is an important tool to study the structure and function of biological macromolecules. In order to acquire higher resolution macromolecular structure, large n...
-
Chapter and Conference Paper
Research on Evolution Mechanism in Different-Structure Module Redundancy Fault-Tolerant System
With the dramatic increase of circuit scale and the harsh environment, the reliability of the system has become the great hidden danger. Triple different-structure modular redundant system based on evolution m...
