![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
Open AccessTime Series Classification Based on Forward Echo State Convolution Network
The Echo state network (ESN) is an efficient recurrent neural network that has achieved good results in time series prediction tasks. Still, its application in time series classification tasks has yet to devel...
-
Article
Multi-style image generation based on semantic image
Image generation has always been one of the important research directions in the field of computer vision. It has rich applications in virtual reality, image design, and video synthesis. Our experiments proved...
-
Article
Semi-supervised clustering ensemble based on genetic algorithm model
Clustering ensemble can be regarded as a mathematical optimization problem, and the genetic algorithm has been widely used as a powerful tool for solving such optimization problems. However, the existing resea...
-
Article
Open AccessDeep Embedding Clustering Based on Residual Autoencoder
Clustering algorithm is one of the most widely used and influential analysis techniques. With the advent of deep learning, deep embedding clustering algorithms have rapidly evolved and yield promising results....
-
Chapter and Conference Paper
A Summary of Research on China Basic Education Evaluation with the Help of Intelligent Technology
Under the background of China Education Modernization 2035 and Education 4.0, promoting the integration and innovation of intelligent technology and basic education evaluation is the necessary path for educati...
-
Chapter and Conference Paper
A Summary Research of the Current Status, Hot Spots and Trends in STEM Education
In the context of the publication of the “Thirteenth Five-Year Plan for Educational Informationization,” and China’s entry into the era of education informatization, the integration of information technology a...
-
Chapter and Conference Paper
Exploration and Practice of Operating System Curriculum Reform Based on the Integration of Science and Education
Operating system (OS) is the core control of a computer, which serves as the command and management center of a computer, often referred to as the brain of a computer. Currently, operating systems are an impor...
-
Chapter and Conference Paper
Research on the Teaching Model of Interdisciplinary Computational Thinking Cultivating from the Perspective of Problem-Solving
Computational thinking is a thinking process related to formal problems and their solutions, and the development of students’ computational thinking skills is one of the important objectives of basic IT teachi...
-
Chapter and Conference Paper
DSAM-GN: Graph Network Based on Dynamic Similarity Adjacency Matrices for Vehicle Re-identification
In recent years, vehicle re-identification (Re-ID) has gained increasing importance in various applications such as assisted driving systems, traffic flow management, and vehicle tracking, due to the growth of...
-
Article
Dense-scale dynamic network with filter-varying atrous convolution for semantic segmentation
Deep convolution neural networks (DCNNs) in deep learning have been widely used in semantic segmentation. However, the filters of most regular convolutions in DCNNs are spatially invariant to local transformat...
-
Article
FASS-pruner: customizing a fine-grained CNN accelerator-aware pruning framework via intra-filter splitting and inter-filter shuffling
Nowadays, with the increasing depth of CNNs, the number of computation and storage requirements with weights expands significantly, preventing their wide deployment on resource-constrained application scenario...
-
Article
An algorithm of non-negative matrix factorization with the nearest neighbor after per-treatments
Clustering is a hot topic in machine learning. For high dimension data, nonnegative matrix factorization (NMF) is a crucial technology in clustering. However, NMF has some disadvantages. First, NMF clusters da...
-
Article
Correction to: Embedded mutual learning: a novel online distillation method integrating diverse knowledge sources
-
Article
Embedded mutual learning: A novel online distillation method integrating diverse knowledge sources
Knowledge distillation (KD) is a feasible and effective way to obtain small networks with outstanding properties that can be deployed on hardware-constrained devices. Earlier KD methods were primarily implemen...
-
Article
An algorithm of nonnegative matrix factorization under structure constraints for image clustering
Nonnegative matrix factorization (NMF) is a crucial method for image clustering. However, NMF may obtain low accurate clustering results because the factorization results contain no data structure information....
-
Chapter and Conference Paper
A Quantitative Spectra Analysis Framework Combining Mixup and Band Attention for Predicting Soluble Solid Content of Blueberries
Hyperspectral imaging can rapid and non-destructive monitor physical characteristics and intrinsic chemical information of food. In recent years, many studies have applied hyperspectral imaging to evaluate the...
-
Chapter and Conference Paper
IoU-Enhanced Attention for End-to-End Task Specific Object Detection
Without densely tiled anchor boxes or grid points in the image, sparse R-CNN achieves promising results through a set of object queries and proposal boxes updated in the cascaded training manner. However, due ...
-
Chapter and Conference Paper
Factor Space and Spectrum for Medical Hyperspectral Image Segmentation
Medical Hyperspectral Imaging (MHSI) brings opportunities for computational pathology and precision medicine. Since MHSI is a 3D hypercube, building a 3D segmentation network is the most intuitive way for MHSI...
-
Chapter and Conference Paper
Deep Mutual Distillation for Semi-supervised Medical Image Segmentation
In this paper, we focus on semi-supervised medical image segmentation. Consistency regularization methods such as initialization perturbation on two networks combined with entropy minimization are widely used ...
-
Chapter and Conference Paper
Gene-Induced Multimodal Pre-training for Image-Omic Classification
Histology analysis of the tumor micro-environment integrated with genomic assays is the gold standard for most cancers in modern medicine. This paper proposes a Gene-induced Multimodal Pre-training (GiMP) fram...