检索结果-内蒙古大学图书馆

International Conference on Signal processing Proceedings (ICSP)

作者： Yingfeng Ou Xing Yang Jian Zhang Caiqing Jian Lihui Wang Engineering Research Center of Text Computing Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Few-shot learning based methods can address the reliance on large-scale labeled samples in current breast tumor segmentation. However, previous methods typically rely on a few support samples to extract abstract, coarse-grained semantic prototypes, without considering the interaction between support and query data. In this study, we aim to provide each query image with relevant and information-rich support information. By integrating the difficult point selection module and the multi-scale cyclical prototype refinement module, we progressively refine coarse-grained support prototypes into more informative, fine-grained class prototypes, thereby better matching the highly variable breast ultrasound query data. Experiments on two datasets demonstrate that our proposed multi-scale cyclical similarity prototype refinement network (CSPRNet) achieves remarkable improvements compared to previous state-of-the-art methods. Specifically, using ResNet50 as the backbone, we achieve 57.93%/57.92% and 57.58%/59.24% mIoU for 1-shot and 5-shot segmentation, respectively, on public and private datasets, outperforming the suboptimal method by 8.18%/2.55% and 2.77%/4.48%.

关键词： image segmentation Ultrasonic imaging Breast tumors Semantics Prototypes Signal processing data mining Few shot learning Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal-Aware Representation Learning with Syntactic Hypergraph Convolutional Network for VideoQA

Cross-Modal-Aware Representation Learning with Syntactic Hyp...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zenan Xu Wanjun Zhong Qinliang Su Fuwei Zhang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

A key challenge in video question answering (VideoQA) is how to align textual concepts with the cross-modal visual regions accurately. Existing methods mostly rely on the alignment between individual words and relevant video regions, but individual words are generally not able to capture the complete information of a textual concept, which is often represented by the composition of several words. To address this issue, we propose to build a syntactic dependency tree for each question with an off-the-shelf tool and use it to extract meaningful word compositions (i.e., textual concept). By viewing the words and compositions as nodes and hyperedges, respectively, a hypergraph convolutional network (HCN) is built to learn the representations of textual concepts. Then, to enable cross-modal interaction of relevant concepts from different modalities, an optimal transport (OT) based alignment method is developed to establish the connection between textual concepts and their relevant visual regions. Experimental results on three benchmarks show that our method outperforms all competing baselines. Further analyses demonstrate the effectiveness of each component, and show that our model is good at modeling different levels of semantic compositions and filtering out irrelevant information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ED-Pose++: Enhanced Explicit Box Detection for Conventional and Interactive Multi-Object keypoint Detection

引用

IEEE Transactions on Pattern analysis and Machine Intelligence 2025年第7期47卷 5636-5654页

作者： Jie Yang Ailing Zeng Tianhe Ren Shilong Liu Feng Li Ruimao Zhang Lei Zhang School of Electronics and Communication Engineering Sun Yat-sen University Shenzhen China Chinese University of Hong Kong Shenzhen China International Digital Economy Academy (IDEA) Shenzhen China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Detecting keypoints on diverse objects is essential for fine-grained visual understanding and analysis. This paper introduces Enhanced Explicit Box Detection (ED-Pose++), an end-to-end framework that leverages cascade box regression to realize both conventional and interactive multi-object keypoint detection. Unlike traditional one-stage methods, ED-Pose++ innovatively redefines multi-object keypoint detection as a dual-phase explicit box detection, achieving a unified representation and regression optimization process. Specifically, an object detection decoder first extracts each object’s position and global features, establishing a good initialization for subsequent keypoint detection. To bring in contextual information near keypoints, we also regard each keypoint as a small box to learn both positions and their related local contents. In practice, an object-to-keypoint detection decoder adopts a collaborative learning strategy between object and keypoint features, facilitating efficient information propagation between global and local perspectives. Rooted on the architecture, we further equip dual-phase box detection with an interactive mechanism that enables the model to refine its predictions based on limited user feedback. During training, we incorporate an error correction scheme to equip the model with an adept self-correction capability for use during inference. The comprehensive experiments demonstrate ED-Pose++’s superior performance in conventional multi-object keypoint detection tasks. For the first time, ED-Pose++ outperforms heatmap-based top-down approaches across various benchmarks, despite operating within a fully end-to-end architecture. The interactive variant also dramatically reduces more than 10 times the labeling effort of 2D keypoint annotation compared with manual-only annotation.

关键词： Annotations Manuals Detectors Decoding Training Pose estimation Predictive models Object detection Benchmark testing Accuracy

来源：评论

学校读者我要写书评

暂无评论

Learning analysis of Kernel Ridgeless Regression with Asymmetric Kernel Learning

arXiv

引用

arXiv 2024年

作者： He, Fan He, Mingzhen Shi, Lei Huang, Xiaolin Suykens, Johan A.K. STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Leuven Belgium MOE Key Laboratory of System Control and Information Processing Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai200433 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China MOE Key Laboratory of System Control and Information Processing Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

Ridgeless regression has garnered attention among researchers, particularly in light of the "Benign Overfitting" phenomenon, where models interpolating noisy samples demonstrate robust generalization. However, kernel ridgeless regression does not always perform well due to the lack of flexibility. This paper enhances kernel ridgeless regression with Locally-Adaptive-Bandwidths (LAB) RBF kernels, incorporating kernel learning techniques to improve performance in both experiments and theory. For the first time, we demonstrate that functions learned from LAB RBF kernels belong to an integral space of Reproducible Kernel Hilbert Spaces (RKHSs). Despite the absence of explicit regularization in the proposed model, its optimization is equivalent to solving an 0-regularized problem in the integral space of RKHSs, elucidating the origin of its generalization ability. Taking an approximation analysis viewpoint, we introduce an lq-norm analysis technique (with 0 © 2024, CC BY.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

LFD-RSNet: Lightweight Face Detection Network for Rainy Weather Scenes

LFD-RSNet: Lightweight Face Detection Network for Rainy Weat...

引用

Natural Language processing (ICNLP), International Conference on

作者： Xiaoying Pan Yamie Ding Nijuan Zhang Yaya Mu Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an China School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an China

ISBN: (数字)9798350349115

ISBN: (纸本)9798350349122

In response to the problem of low detection accuracy of lightweight models for face detection in complex rainy scenes, this paper proposes a face detection network FDL-RSNet for complex rainy scenes. This network integrates an adaptive image denoising module, an optimizer module, an HCA attention module, and a balanced branching strategy. The FDL-RSNet network can effectively address various challenges in complex rainy backgrounds, such as raindrop noise, differences in image lighting and contrast, and face detection challenges caused by low-quality images with dense targets. Experimental results on the UFDD Rain datasets show that FDL-RSNet has superior face detection capabilities in real-world unconstrained complex rainy scenes, Proved its effectiveness and reliability under such highly challenging conditions.

关键词： Adaptation models Rain Adaptive systems Noise Lighting Natural language processing Face detection Reliability Meteorology image denoising

来源：评论

学校读者我要写书评

暂无评论

Modeling of unsupervised knowledge graph of events based on mutual information among neighbor domains and sparse representation

引用

Defence Technology（防务技术） 2022年第12期18卷 2150-2159页

作者： Jing-Tao Sun Jing-Ming Li Qiu-Yu Zhang School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsXi'anShaanxi710121China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and TelecommunicationsXi'anShaanxi710121China School of Management Science and Engineering Anhui University of Finance and EconomicsBengbuAnhui230030China School of Computer and Communication Lanzhou University of TechnologyLanzhouGansu730050China

Text event mining,as an indispensable method of text mining processing,has attracted the extensive attention of researchers.A modeling method for knowledge graph of events based on mutual information among neighbor domains and sparse representation is proposed in this paper,***,UKGE-MS can improve the existing text mining technology's ability of understanding and discovering high-dimensional unmarked information,and solves the problems of traditional unsupervised feature selection methods,which only focus on selecting features from a global perspective and ignoring the impact of local connection of ***,considering the influence of local information of samples in feature correlation evaluation,a feature clustering algorithm based on average neighborhood mutual information is proposed,and the feature clusters with certain event correlation are obtained;Secondly,an unsupervised feature selection method based on the high-order correlation of multi-dimensional statistical data is designed by combining the dimension reduction advantage of local linear embedding algorithm and the feature selection ability of sparse representation,so as to enhance the generalization ability of the selected feature ***,the events knowledge graph is constructed by means of sparse representation and l1 *** experiments are carried out on five real datasets and synthetic datasets,and the UKGE-MS are compared with five corresponding *** experimental results show that UKGE-MS is better than the traditional method in event clustering and feature selection,and has some advantages over other methods in text event recognition and discovery.

关键词： Text event mining Knowledge graph of events Mutual information among neighbor domains Sparse representation

来源：评论

学校读者我要写书评

暂无评论

A Multi-Objective Evolutionary Stacking Integration Approach for Survival Prediction in GBM Patients

A Multi-Objective Evolutionary Stacking Integration Approach...

引用

Natural Language processing (ICNLP), International Conference on

作者： Fangyuan Du Hao Chen Kunjun Chen Xuelian Yang School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi’an China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi’an China

ISBN: (数字)9798350349115

ISBN: (纸本)9798350349122

To address the challenge of predicting survival rates for patients with Glioblastoma (GBM) after radiation therapy, we propose a two-stage integrated learning method that is based on Stacking and multi-objective differential evolution algorithm. Our aim is to achieve a balance between accuracy and interpretability. We have created a framework for survival prediction using radiomics features of gliomas that are imaged in subregions. Our method constructs a model for predicting GBM survival and visualizes decision rules that are easy to interpret. The method involves two primary steps: 1) Various combinations of MRI sequences and glioma subregions were evaluated to determine the optimal sequence, and the GBM long and short survival classification task in the first stage of the task was achieved by compressing features using spectral clustering. 2) An evolutionary integrated learning method based on Stacking was proposed. It uses a Random Forest classifier as the basic learning module of the integrated model and relies on the multi-objective optimization algorithm NSGA-II to continuously iterate with the aim of maximizing the regression accuracy while minimizing the model's integration complexity. We used 119 GBM patients in the BraTS2020 dataset as our study data. Based on the five-fold cross-validation, the survival classification Accuracy and Recall of our long- and short-term classification algorithm for GBM patients were 0.981 and 0.943, respectively; and the Mean-Square Error (MSE) of the survival prediction of GBM patients with the stack-based evolutionary integration method was 55713.08. The experimental results showed that our proposed method for GBM survival days prediction is significantly better than existing Machine Learning (ML) methods. This finding enables us to stratify patients more effectively and provides a more reliable basis for achieving personalized treatment for GBM patients.

关键词： Learning systems Accuracy Protocols Stacking Semantics Classification algorithms Radiation therapy Reliability Random forests Radiomics

来源：评论

学校读者我要写书评

暂无评论

Lightweight Transformer Network and Self-supervised Task for Kinship Verification 8

Lightweight Transformer Network and Self-supervised Task for...

引用

8th IEEE International Conference on Computer and Communications, ICCC 2022

作者： Zhu, Xiaoke Li, Yunwei Li, Danyang Dong, Lingyun Chen, Xiaopan School of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University China

ISBN: (纸本)9781665450515

Kinship verification is one of the interesting and critical problems in computer vision research, with significant progress in the past decades. Meanwhile, Vision Transformer (VIT) has recently achieved impressive success in many domains, including object detection, image recognition, and semantic segmentation, among others. Most of the previous work on kinship verification are based on convolutional or recurrent neural networks. Compared with the local processing of images like convolutions, transformers can effectively understand and process images globally. However, due to overuse, there are many Transformer layers of fully connected layers, and VIT speed is still an issue. Therefore, in this paper, inspired by the recent success of Transformer models in vision tasks, we propose a Transformer-based kinship verification for training and optimizing kinship verification models. We first train the basic vision transformer (VIT-B) with 12 transformer layers, then we reduce the transformer layers to 6 layers, namely VIT-S (Small Vit) and 4 layers, namely VIT-T (Tiny Vit), to make a tradeoff between optimization accuracy and efficiency. As the first attempt to apply Transformer to the kinship verification task, it provides a feasible strategy for kinship research topics and verifies the effectiveness of the method in terms of the accuracy of the experimental results. © 2022 IEEE.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

A compound fault diagnosis method based on Multi-task Learning with Multi-gate Mixture-of-Experts 14

A compound fault diagnosis method based on Multi-task Learni...

引用

14th International Conference on Measuring Technology and Mechatronics Automation, ICMTMA 2022

作者： Chen, Yanping Ren, Lele Xia, Hong Wang, Zhongmin Gao, Cong Wang, Fengwei School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China ZTE Corporation No.55 Hi-techRoadSouth Shenzhen518057 China

ISBN: (纸本)9781665499781

At present, the research object of fault diagnosis focuses on single fault diagnosis. This method of diagnosis does not consider the relationship between mechanical equipment faults, and cannot fully identify the type of fault. In the actual industrial process, mechanical equipment is mostly complex system, and compound fault diagnosis is more in line with industrial needs. In order to solve the problem of compound fault diagnosis of mechanical equipment and improve the accuracy of fault identification, this paper establishes a compound fault diagnosis model for gearbox by means of multi-task learning, uses multi-gated networks to extract features from the task sharing layer, and finally classifies the fault through the task specific *** experimental results show that, the compound fault diagnosis method based on Multi-task Learning with Multi-gate Mixture-of-Experts (ML-MMoE) can accurately identify compound fault types under different working conditions. © 2022 IEEE

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

A new double scrambling color image encryption algorithm based on multi chaotic systems and image segmentation

A new double scrambling color image encryption algorithm bas...

引用

Computer Science and Management Technology (ICCSMT), International Conference on

作者： Junfeng Tian Ke Wang Cheng Liu Key Laboratory of Big Data Analysis and Processing of Henan Province Henan University Kaifeng PR China

Aiming at low security of traditional encryption methods, this paper give a new encryption method by using multi chaotic systems and image segmentation. Firstly, use Arnold transform to perturb the RGB component matrices of the source image. Subsequently, the chaotic image chunking algorithm is applied to the mixed component matrix, and the chunked mixed matrix is perturbed by Hyperchaotic Chen system and Logistic mapping. Moreover, Diffusion of pixel transformations to the whole image by inverse transform operations. Finally, logistic system is applied to the secondary pixels scrambling, which achieves image encryption. The experimental data indicate that this encryption method encryption effect is good, and can effectively prevent ciphertext attack and noise attack.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：