检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Su, Yawen Bai, Jing Lin, Gan School of Computer Science and Engineering North Minzu University Yinchuan China The Key Laboratory of Images & Graphics Intelligent Processing of State Ethnic Affairs Commission China

ISBN: (纸本)9798350368741

Sketch-based 3D shape retrieval has become a prominent area of research in computer vision, confronting challenges related to the inherent diversity and abstraction of sketches, as well as inter-domain discrepancies. This paper introduces a novel approach called Dual Knowledge Distillation Dynamic Learning (DKD2L) aimed at enhancing the extraction of spatio-temporal features for sketch-based 3D shape retrieval. We develop a temporal feature extraction network to effectively capture the dynamic temporal characteristics of sketches and improve retrieval efficiency through temporal knowledge distillation. Additionally, to tackle intra-class variation and inter-class imbalance, we apply semantic knowledge distillation, enabling the 3D shape network to guide the sketch network in capturing common semantic information. This approach facilitates precise cross-modal alignment and enhances retrieval accuracy. Extensive experiments on two benchmark datasets demonstrate that DKD2L surpasses existing state-of-the-art methods. © 2025 IEEE.

关键词： 3D Shape Retrieval Knowledge Distillation Sketch-based 3D Shape Retrieval Temporal Feature

来源：评论

学校读者我要写书评

暂无评论

MDT-Net: A Mask Decoder Tuning Strategy for CLIP-Based Zero-Shot 3D Classification 31st

MDT-Net: A Mask Decoder Tuning Strategy for CLIP-Based Zero...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Yan, Hao Bai, Jing The School of Computer Science and Engineering North Minzu University Ningxia Yinchuan750021 China The Key Laboratory of Images and Graphics Intelligent Processing of State Ethnic Affairs Commission Ningxia Yinchuan750021 China

ISBN: (纸本)9789819620609

PointCLIP shows that transferring 2D knowledge to zero-shot 3D shape classification tasks can be effective, even without incorporating 3D-specific knowledge. However, the absence of 3D knowledge limits the model’s performance, leading to efforts focused on improving 3D-to-2D projection algorithms. This work advances previous methods by introducing a learnable fine-tuning strategy, called MDT-Net, for Contrastive Language-Image Pre-training (CLIP) on 3D datasets. MDT-Net freezes the CLIP encoder to keep view features aligned with semantic information and incorporates a shape decoder with masked view consistency and attention-guided fusion, enabling more effective fine-tuning of CLIP for 3D tasks. The decoder receives both raw view features and masked view features. In the shallow layers, a mask consistency constraint is utilized between two types of view features to enhance the model’s generalization and robustness. In the deeper layers, attention-guided fusion is introduced to better capture the contextual information between views and compact all view features into one. MDT-Net is evaluated on different benchmarks of 5 datasets for zero-shot classification, achieving a competitive classification accuracy on ModelNet10, ModelNet40, McGill, and ZS3D datasets. These experiment results demonstrate the effectiveness of this approach. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Review of Knowledge Reasoning Methods Based on Graph Neural Networks

引用

computer Engineering and Applications 2025年第10期61卷 50-66页

作者： Liu, Xueyang Li, Weijun Liu, Shixia Ding, Jianping Su, Yilei School of Computer Science and Engineering North Minzu University Yinchuan750021 China Key Laboratory of Images Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu University Yinchuan750021 China

Knowledge reasoning is a fundamental task in knowledge graph completion. It has received widespread attention from the academic community. With the development of knowledge reasoning technology, applying graph neural networks to knowledge reasoning methods can fully consider the structural information of knowledge graphs, making them more interpretable and stronger in reasoning ability, which is currently one of the research hotspots. The basic concepts of knowledge graph and knowledge reasoning are described. Knowledge reasoning methods based on graph neural networks are categorized from the perspectives of closed-world and open-world settings. In the closed-world context, the emphasis is placed on two types of methods: graph convolutional networks and graph attention networks. In the open-world context, semi-inductive and fully-inductive methods are explored. The typical model frameworks of these methods are compared and analyzed, and their respective strengths and weaknesses are summarized. Finally, the applications of graph neural network reasoning in intelligent question answering, recommendation system and biomedicine are discussed, and the future research direction of graph neural network based knowledge reasoning is prospected. © 2025 Journal of computer Engineering and Applications Beijing Co., Ltd.;Science Press. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

DKD2L: Dual Knowledge Distillation Dynamic Learning for sketch-based 3D shape retrieval

DKD2L: Dual Knowledge Distillation Dynamic Learning for sket...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yawen Su Jing Bai Gan Lin School of Computer Science and Engineering North Minzu University Yinchuan China The Key Laboratory of Images & Graphics Intelligent Processing of State Ethnic Affairs Commission

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Sketch-based 3D shape retrieval has become a prominent area of research in computer vision, confronting challenges related to the inherent diversity and abstraction of sketches, as well as inter-domain discrepancies. This paper introduces a novel approach called Dual Knowledge Distillation Dynamic Learning (DKD 2 L) aimed at enhancing the extraction of spatio-temporal features for sketch-based 3D shape retrieval. We develop a temporal feature extraction network to effectively capture the dynamic temporal characteristics of sketches and improve retrieval efficiency through temporal knowledge distillation. Additionally, to tackle intra-class variation and inter-class imbalance, we apply semantic knowledge distillation, enabling the 3D shape network to guide the sketch network in capturing common semantic information. This approach facilitates precise cross-modal alignment and enhances retrieval accuracy. Extensive experiments on two benchmark datasets demonstrate that DKD 2 L surpasses existing state-of-the-art methods.

关键词： Knowledge engineering computer vision Three-dimensional displays Shape Semantics Signal processing Benchmark testing Feature extraction Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Mcnet: A Multi-Level Consistency Network for 3d Point Cloud Self-Supervised Learning

SSRN

引用

SSRN 2025年

作者： Liu, Hongshuo Bai, Jing Lin, Gan School of Computer Science and Engineering North Minzu University Yinchuan750021 China The Key Laboratory of Images and Graphics Intelligent Processing of State Ethnic Affairs Commission Yinchuan750021 China Liupanshan Laboratory Yinchuan750021 China

With the rapid advancement of computer vision and artificial intelligence, point clouds have become a pivotal representation of 3D data. However, practical applications of point clouds are hindered by challenges such as noise, structural sparsity, and information occlusion, which complicate computations and degrade the performance of high-precision analyses. While self-supervised learning has proven effective in reducing reliance on annotated data, existing methods predominantly focus on local features, often neglecting global structures and the balance between geometric and semantic information. This paper introduces the Multi-level Consistency Network (MCNet), a novel framework designed to comprehensively explore multi-level feature information in point clouds. MCNet integrates geometric, structural, and high-order semantic supervisory signals, fostering alignment and complementarity of features through self-supervised learning. We propose the Global-Local Synergistic Noise Module (GLSNM), which combines Principal Component Analysis-based Non-Local Noise Addition (PCA-NLNA) with Mask-based Local Noise Injection (Mask-LNI) to balance the preservation of global structures and local details. Additionally, we develop the Multi-level Information Reconstruction Module (MIRM), which employs an attention fusion mechanism to dynamically balance geometric and high-order semantic information, thereby enhancing the model's feature extraction capabilities in complex environments. Extensive experiments demonstrate that MCNet consistently outperforms existing methods across multiple tasks, including meta-classification, few-shot classification, real-world scene classification, fine-grained classification, and segmentation. These results validate the effectiveness of MCNet and its significant contribution to the field of point cloud processing. © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Spread-based elite opposite swarm optimizer for large scale optimization

引用

Cognitive Robotics 2022年 2卷 112-118页

作者： Zhang, Li Tan, Yu Guangxi Key Laboratory of Images and Graphics Intelligent Processing Guilin University of Electronic Technology Guilin541004 China

To prevent the traditional particle swarm optimizer (PSO) from inefficient search in complex problem spaces, this paper presents a novel spread-based elite opposite swarm optimizer (SEOSO) for large scale optimization. Inspired by the dandelion seeds in nature, the seeds can randomly spread by wind and grow better for the next generation. To achieve this, the spread learning and elite opposite learning are introduced in SEOSO. In spread learning, the particles are divided into some subswarms and these subswarms can exchange the particles to get more useful information that improves the diversity of the swarm. In elite opposite learning, the opposite position of the particle is used to exclude the worse direction. The experiments are conducted on 35 benchmark functions to evaluate the performance of SEOSO in comparison with several state-of-the-art algorithms. The comparative results show the effectiveness of SEOSO in solving large scale optimization problems. © 2022

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

An Improved Seq-Deepfake Detection Method 1st

An Improved Seq-Deepfake Detection Method

引用

1st International Conference on Applied Intelligence, ICAI 2023

作者： Deng, Zhenrong You, Kang Yang, Rui Hu, Xinru Chen, Yuren Guangxi Key Laboratory of Images and Graphics Intelligent Processing Guilin University of Electronic Technology Guilin541004 China Guangxi Construction Industry Mostly Guangxi China

ISBN: (纸本)9789819709021

Facial processing technology's ability to generate realistic human faces poses significant societal risks when exploited maliciously. Deep face fraud detection relies on deep learning to meticulously scrutinize the manipulation sequence of fake faces, uncovering deceptive traces. This study focuses on Detecting Sequential DeepFake Operations (Seq-DeepFake), transforming the face detection task into an image-to-sequence *** enhance detection accuracy, this paper introduces a Seq-DeepFake detection method. The Seq-DeepFake Transformer model's activation function is refined, incorporating the Rectified Randomized Leaky Unit (RReLU) to address learning rate challenges associated with negative input values. Furthermore, diverse attention mechanism modules are integrated into the backbone network, forming the innovative CLSP-Resnet-50 model. Experimental results demonstrate the efficacy of the enhanced Seq-DeepFake model, employing two evaluation metrics on a deepfake dataset, showcasing improved accuracy. Comparative analysis against other real and fake face detection methods substantiates the effectiveness of the Seq-DeepFake model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv8n Model for Detecting Helmets and License Plates on Electric Bicycles

引用

computers, Materials & Continua 2024年第7期80卷 449-466页

作者： Qunyue Mu Qiancheng Yu Chengchen Zhou Lei Liu Xulong Yu The College of Computer Science and Engineering North Minzu UniversityYinchuan750021China The Key Laboratory of Images and Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu UniversityYinchuan750021China

Wearing helmetswhile riding electric bicycles can significantly reduce head injuries resulting fromtraffic *** effectively monitor compliance,the utilization of target detection algorithms through traffic cameras plays a vital role in identifying helmet usage by electric bicycle riders and recognizing license plates on electric ***,manual enforcement by traffic police is time-consuming and *** methods face challenges in accurately identifying small targets such as helmets and license plates using deep learning *** paper proposes an enhanced model for detecting helmets and license plates on electric bicycles,addressing these *** proposedmodel improves uponYOLOv8n by deepening the network structure,incorporating weighted connections,and introducing lightweight convolutional *** modifications aim to enhance the precision of small target recognition while reducing the model’s parameters,making it suitable for deployment on low-performance devices in real traffic *** results demonstrate that the model achieves an mAP@0.5 of 91.8%,showing an 11.5%improvement over the baselinemodel,with a 16.2%reduction in ***,themodel achieves a frames per second(FPS)rate of 58,meeting the accuracy and speed requirements for detection in actual traffic scenarios.

关键词： YOLOv8 object detection electric bicycle helmet detection electric bicycle license plate detection

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Optimization Method for Federated Learning with Feature Alignment and Decision Fusion

引用

computers, Materials & Continua 2024年第10期81卷 1391-1407页

作者： Ke Li Xiaofeng Wang Hu Wang College of Computer Science and Engineering North Minzu UniversityYinchuan750021China The Key Laboratory of Images&Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu UniversityYinchuan750021China

In the realm of data privacy protection,federated learning aims to collaboratively train a global ***,heterogeneous data between clients presents challenges,often resulting in slow convergence and inadequate accuracy of the global *** shared feature representations alongside customized classifiers for individual clients emerges as a promising personalized ***,previous research has frequently neglected the integration of global knowledge into local representation learning and the synergy between global and local classifiers,thereby limiting model *** tackle these issues,this study proposes a hierarchical optimization method for federated learning with feature alignment and the fusion of classification decisions(FedFCD).FedFCD regularizes the relationship between global and local feature representations to achieve alignment and incorporates decision information from the global classifier,facilitating the late fusion of decision outputs from both global and local ***,FedFCD employs a hierarchical optimization strategy to flexibly optimize model *** experiments on the Fashion-MNIST,CIFAR-10 and CIFAR-100 datasets,we demonstrate the effectiveness and superiority of *** instance,on the CIFAR-100 dataset,FedFCD exhibited a significant improvement in average test accuracy by 6.83%compared to four outstanding personalized federated learning ***,extended experiments confirm the robustness of FedFCD across various hyperparameter values.

关键词： Federated learning data heterogeneity feature alignment decision fusion hierarchical optimization

来源：评论

学校读者我要写书评

暂无评论

PFMRC: A Unified MRC Framework for Chinese Named Entity Recognition via Semantic Feature Fusion 4

PFMRC: A Unified MRC Framework for Chinese Named Entity Reco...

引用

4th International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2024

作者： Deng, Zhenrong Zhang, Jinglin Xiao, Yannan Wei, Shiwei Guilin University of Electronic Technology Guangxi Key Laboratory of Images and Graphics Intelligent Processing Guilin China Nanning Research Institute Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Images and Graphics Intelligent Processing Guilin University of Electronic Technology Guilin China School of Computer Science and Engineering Guilin University of Aerospace Technology Guilin China

ISBN: (纸本)9798331531225

The landscape of natural language processing (NLP) has been revolutionized by advancements that enable the upstream training of knowledge-rich models for downstream tasks, particularly named entity recognition (NER). Traditional NER approaches, treating it as a sequence labeling problem, often fail to deeply understand the whole text and to capture syntactic nuances of text. To address these issues, we introduce PFMRC, a novel machine reading comprehension (MRC) framework that leverages the strengths of both contextual semantics and syntactic information for enhanced NER performance. PFMRC employs a dual-pronged feature extraction strategy, utilizing RoBERTa and BiGRU to encode text features for contextual semantic information and representing them as node features of the graph structure, and a weighted embedding representation to translate syntactic dependencies into graph-structured edge features. Our model further incorporates Graph Attention Networks (GAT) to harmonize node and edge features, facilitating a nuanced understanding of text. The integration of prior knowledge and the modeling of intricate syntactic relationships through Graph Attention Networks (GAT) not only improves entity recognition accuracy but also enriches the feature representation, leading to more robust NER outcomes. Extensive experiments on three Chinese datasets demonstrate PFMRC's superior performance over state-of-the-art models. © 2024 IEEE.

关键词： Semantics

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：