检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

25 篇 会议

馆藏范围

25 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

23 篇 工学
- 14 篇 电气工程
- 9 篇 计算机科学与技术...
- 3 篇 光学工程
- 3 篇 软件工程
- 1 篇 电子科学与技术（可...
- 1 篇 信息与通信工程
- 1 篇 化学工程与技术
- 1 篇 生物医学工程（可授...
- 1 篇 生物工程
13 篇 医学
- 13 篇 临床医学
3 篇 理学
- 3 篇 物理学
- 1 篇 化学
- 1 篇 生物学
1 篇 法学
- 1 篇 社会学

主题

3 篇 image enhancemen...
3 篇 deep learning
3 篇 image processing
2 篇 object detection
1 篇 fuzzy logic
1 篇 proactive traffi...
1 篇 movenet
1 篇 sinelayer
1 篇 multi-view image...
1 篇 semantic segment...
1 篇 ensemble learnin...
1 篇 modeling
1 篇 indexes
1 篇 self-attention
1 篇 visual processin...
1 篇 image segmentati...
1 篇 optical characte...
1 篇 prompt-tuning
1 篇 temporal coheren...
1 篇 3d human pose es...

机构

2 篇 dalian univ tech...
2 篇 dalian univ sch ...
1 篇 vels inst sci te...
1 篇 department of co...
1 篇 ural fed univ ek...
1 篇 engn univ pap xi...
1 篇 xiaomi inc peopl...
1 篇 saveetha school ...
1 篇 univ haute alsac...
1 篇 xd prod bry sur ...
1 篇 sun yat sen univ...
1 篇 inst appl phys &...
1 篇 maharashtra lava...
1 篇 beijing inst tec...
1 篇 univ chinese aca...
1 篇 univ ghent dept ...
1 篇 pondicherry engi...
1 篇 state key labora...
1 篇 univ elect sci &...
1 篇 shanghai jiao to...

作者

2 篇 yi pengfei
2 篇 dong jing
2 篇 liu rui
2 篇 zhou dongsheng
2 篇 guo yujie
1 篇 rudro rifat al m...
1 篇 agalya d.
1 篇 palahan sirinda
1 篇 poovayar priya m...
1 篇 chen shengru
1 篇 li yang
1 篇 pang junbiao
1 篇 arunthari santip...
1 篇 nachtegael m.
1 篇 zhao yifei
1 篇 yang shangyu
1 篇 christy s.
1 篇 mangileva daria
1 篇 fan shuhuan
1 篇 wilser nicola

语言

25 篇 英文

检索条件"任意字段=2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition, CVIPPR 2024"

共 25 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

cvippr 2024 - 2nd asia conference on computer vision, image processing and pattern recognition

CVIPPR 2024 - 2nd Asia Conference on Computer Vision, Image ...

引用

2nd asia conference on computer vision, image processing and pattern recognition, cvippr 2024

ISBN: (纸本)9798400716607

The proceedings contain 59 papers. The topics discussed include: 3D point clouds simplification based on low-dimensional contour feature extraction;3D human pose estimation using pressure images on a smart chair;combining doses from internal and external radiotherapies for cervical cancer with successive image registration;attention mechanism-based feature fusion generative network for infrared-visible person re-identification;a vision-based remote assistance method and its application in object transfer;research on model-free 6D object pose estimation based on vision 3D matching;active exploration of modality complementarity for multimodal sentiment analysis;self-attention-based multi-scale feature fusion network for road ponding segmentation;and low light image enhancement algorithm based on edge and color information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Innovating Tourism: Personalized Recommendations through AI 2

Innovating Tourism: Personalized Recommendations through AI

引用

2nd asia conference on computer vision, image processing and pattern recognition (cvippr)

作者： Palahan, Sirinda Arunthari, Santipat Univ Thai Chamber Commerce Sch Sci & Technol Bangkok Thailand

ISBN: (纸本)9798400716607

This paper delves into the development and deployment of an AI-powered chatbot aimed at enhancing tourism experiences. By integrating advanced natural language processing and machine learning techniques, the chatbot offers personalized travel recommendations and information, serving as a versatile tool for tourists. Through experimental evaluation involving intent classification and user satisfaction, the chatbot demonstrates significant accuracy in understanding user queries and a positive impact on user satisfaction. Intent classification using DistilBERT achieved a high F1-score, indicating superior understanding capabilities. User feedback highlighted satisfaction and likelihood of reuse, pointing to areas for further refinement in response relevance.

关键词： Chatbot Tourism Natural Language processing Intent Classification

来源：评论

学校读者我要写书评

暂无评论

Ensemble of Distinct Students for SSL 2D Pose Estimation 24

Ensemble of Distinct Students for SSL 2D Pose Estimation

引用

2nd asia conference on computer vision, image processing and pattern recognition (cvippr)

作者： Wu, Jiaqi Pang, Junbiao Huang, Qingming Beijing Univ Technol Chaoyang Beijing Peoples R China Univ Chinese Acad Sci Haidian Beijing Peoples R China

ISBN: (纸本)9798400716607

Semi-supervised pose estimation poses a significant challenge in computer vision. Although numerous semi-supervised classification techniques have been developed, they often rely on confidence scores to assess the quality of pseudo-labels, a feat that is challenging to achieve in pose estimation tasks. In pose estimation, for instance, confidence merely indicates the likelihood of a specific location on the heatmap being a keypoint, rather than the overall prediction quality. To address this issue, this paper introduces an ensemble framework leveraging diverse student models to evaluate the credibility of pseudo-labels by assessing their consistency across multiple models. Specifically, within a double-mean-teacher framework, we create two distinct student models (DS) to encourage two teacher models to generate distinct decision boundaries for the same sample. Experimental results demonstrate the effectiveness of our approach in enhancing semi-supervised pose estimation performance across three datasets.

关键词： Semi-supervised Learning Ensemble Learning 2D Pose Estimation

来源：评论

学校读者我要写书评

暂无评论

Pixel Power: Harnessing image processing for Optimizing Few-Shot Malicious Traffic Detection 2

Pixel Power: Harnessing Image Processing for Optimizing Few-...

引用

2nd asia conference on computer vision, image processing and pattern recognition (cvippr)

作者： Wang, Yihan Yan, Ruiyi Beijing Inst Technol Beijing Peoples R China

ISBN: (纸本)9798400716607

The rapid proliferation of cyber threats in an increasingly digitized world presents a formidable challenge to existing cybersecurity mechanisms of which malicious traffic is a noticeable issue. However, feature extraction of malicious traffic is often hindered by insufficient data, and thus training effectiveness and efficiency are compromised. To address the challenge of detecting malicious traffic with small sample sizes, we introduce a meta regularization network, MRN. Our method leverages meta-learning techniques alongside convolutional neural networks to capture intricate traffic patterns, so as to classify processed encrypted traffic data. Within MRN, we introduce a novel meta-learning regularization strategy that adjusts the training process's loss based on network parameters, in order to improve computing efficiency. Our comprehensive experimental evaluations reveal the model's exceptional capability in malicious traffic classification, achieving 95.11% accuracy averagely, which is higher than the baseline methods under various experimental setup. This underscores our framework's potential in advancing the field of cybersecurity through image-based analysis and small-sample classification techniques.

关键词： few-shot meta learning deep learning network traffic

来源：评论

学校读者我要写书评

暂无评论

ELiFormer: A hierarchical Transformer based Model with Efficient Encoder and Lightweight Decoder for Semantic Segmentation 2

ELiFormer: A hierarchical Transformer based Model with Effic...

引用

2nd asia conference on computer vision, image processing and pattern recognition (cvippr)

作者： Wu, Zixuan Zhou, Yue Shanghai Jiao Tong Univ Shanghai Peoples R China

ISBN: (纸本)9798400716607

Fully-convolutional networks have limited global information modeling, while Transformers can be computationally demanding. This paper introduces ELiFormer, a lightweight model combining Transformer and CNN components for semantic segmentation tasks. We start by using a lightweight inverted residual module to extract initial features, aiming to reduce computational complexity and improve model efficiency. Within encoder module, we adopt depth-wise separable convolution for flexible position embedding, notably improving segmentation accuracy for small objects. We also employs two self-attention mechanisms: local window multi-head self-attention and global window multi-head self-attention, which generate multi-scale feature maps, enhancing the encoder's ability to capture complex relationships. Dropout layers are introduced to reduce computational demand during training. To address semantic disparity between CNN and visual Transformer, we introduce fusion block. Finally, we utilize a lightweight MLP decoder to streamline the model and ensure robust segmentation performance. Our extensive ablation study shows that ELiFormer attains significant results for semantic segmentation, which is competitive on Cityscapes datasets.

关键词： Semantic segmentation Hierarchical vision Transformer Lightweight

来源：评论

学校读者我要写书评

暂无评论

Real-Time 3D Skeleton Reconstruction: A Comprehensive Approach from Multiple Views 24

Real-Time 3D Skeleton Reconstruction: A Comprehensive Approa...

引用

2nd asia conference on computer vision, image processing and pattern recognition (cvippr)

作者： Wilser, Nicola Cordier, Frederic Maillot, Yvan Souchet, Philippe Univ Haute Alsace Bry Sur Marnes France XD Prod Bry Sur Marnes France Univ Haute Alsace Mulhouse France

ISBN: (纸本)9798400716607

This paper presents a comprehensive method for real-time 3D human skeleton reconstruction from calibrated camera sets, addressing challenges in scenes with multiple individuals. Accurate 3D pose estimation is crucial for various applications such as 3D model animation, augmented reality, and human-computer interaction. The approach involves initial 2D skeleton estimation, followed by skeleton identification through a matching algorithm and reconstruction via triangulation. Three key enhancements were implemented: refining the matching algorithm using 3D reconstruction reprojection, accelerating execution with skeleton tracking, and validation on a diverse dataset with over 9,000 frames. The method achieves accurate 3D reconstruction and robust performance in multi-individual scenarios, making it suitable for real-world applications. Project page: https://instant- ***.

关键词： 3D Human Pose Estimation Temporal Coherence in 3D Reconstruction Real-time 3D Skeleton Reconstruction Multi-view image processing

来源：评论

学校读者我要写书评

暂无评论

Sitting Posture recognition Based on the computer's Camera 2

Sitting Posture Recognition Based on the Computer's Camera

引用

2nd asia conference on computer vision, image processing and pattern recognition (cvippr)

作者： Zhao, Songyin Su, Yang Engn Univ PAP Xian Peoples R China

ISBN: (纸本)9798400716607

The popularity of computers has made sitting a normal part of people's lives. Since unhealthy sitting postures not only harm the eyes but also increase the risk of various musculoskeletal diseases, sitting posture detecting and warning is very necessary to help people develop healthy sitting habits. Thus, a cheaper and more convenient method using an ordinary camera is proposed in this paper for 8 kinds of sitting posture. Restricted by the view of camera, the positions of nose, eyes, ears and shoulders are extracted using MoveNet, as the input of a Multi-layer Perceptron (MLP) classifier. To train the classifier, the user needs to record a video for each sitting posture. In the process of recording, guidelines are provided to improve the quality of training data. For this study, a small dataset including 12 groups of videos recorded using 2 sets of table and chair was collected. The relatively good MLP with (64,64) as hidden layer sizes and 0.162378 as alpha are found by GridSearchCV, using Leave P Group(s) Out cross-validator as the cross-validation splitting strategy. Overall, the average accuracy of this method for the dataset is 95.8%, while 97.3% for the same set of table and chair and 94.1% for the different set. These results mean that is feasible to recognize the sitting postures using ordinary camera, which implies a more easily available sitting posture warning technology.

关键词： Posture detection image classification MoveNet Multi-layer Perceptron

来源：评论

学校读者我要写书评

暂无评论

NanoTrack: An Enhanced MOT Method by Recycling Low-score Detections from Light-weight Object Detector 2

NanoTrack: An Enhanced MOT Method by Recycling Low-score Det...

引用

2nd asia conference on computer vision, image processing and pattern recognition (cvippr)

作者： Li, WeiJia Chen, LiYuan Cai, JunZhi Tong, Lihan Chen, ErKang Huang, Bin Jimei Univ Xiamen Fujian Peoples R China

ISBN: (纸本)9798400716607

In this paper, we introduced NanoTrack, a novel multi-object tracking (MOT) method that leverages light-weight object detectors to enhance tracking performance in real-time applications where computational resources are scarce. While light-weight detectors are efficient, they often produce an imbalance in detection quality, generating a significant number of low-scoring detections that pose challenges for tracking algorithms. Our approach innovatively utilizes these low-scoring detections for track initialization and maintenance, addressing the shortcomings observed in existing tracking by two-stage tracking methods like ByteTrack, which struggle with the abundance of low-scoring detections. By integrating two new light-weight modules, Refind High Detection (RHD) and Duplicate Track Checking (DTC), NanoTrack effectively incorporates low-scoring detections into the tracking process. Additionally, we enhance the pseudo-depth estimation technique for improved handling in dense target environments, mitigating issues like ID Switching. Our comprehensive experiments demonstrate that NanoTrack surpasses state-of-the-art two-stage TBD methods, including ByteTrack and SparseTrack, on benchmark datasets such as MOT16, MOT17, and MOT20, thereby establishing a new standard for MOT performance using light-weight detectors. The code is open source in https://***/VjiaLi/NanoTrack

关键词： multi-object tracking computer vision light-weight object detector

来源：评论

学校读者我要写书评

暂无评论

Judicial Text Relation Extraction Based on Prompt Tuning 24

Judicial Text Relation Extraction Based on Prompt Tuning

引用

2nd asia conference on computer vision, image processing and pattern recognition (cvippr)

作者： Chen, Xue Li, Yi Fan, Shuhuan Hou, Mengshu Univ Elect Sci & Technol China Chengdu Peoples R China

ISBN: (纸本)9798400716607

With the acceleration of the digital transformation in the judicial field, the need for automated processing and analysis of voluminous legal documents becomes increasingly imperative. Relationship extraction, a pivotal step in comprehending these documents, is crucial for automated case analysis, discovery of legal facts, and prediction of judgments. However, the idiosyncrasies of judicial texts, such as their intricate linguistic structures, specialized terminology, and implicit semantic relationships, present significant challenges to the efficacy of traditional text analysis methods. Traditional relation extraction techniques often fail to adapt well to professional terms, intricate linguistic structures and implicit semantics in judicial texts. Moreover, the general lack of training data tailored to the specific context of the legal domain hampers the ability of models to learn effectively and accurately extract relationships from judicial texts. This paper introduces a novel approach utilizing pre-trained models for prompt-based fine-tuning to achieve relationship extraction in judicial texts. Leveraging the robust language comprehension capabilities of large-scale pre-trained models, we have designed domain-specific prompt templates to guide the model in more effectively capturing and understanding key information within legal texts. This method not only enhances the accuracy of relationship extraction but also significantly reduces reliance on extensive annotated data. The effectiveness and superiority of our approach are corroborated by test results on a judicial text dataset.

关键词： relation extraction pre-training model prompt-tuning judicial text processing

来源：评论

学校读者我要写书评

暂无评论

A vision-based Remote Assistance Method and it's Application in Object Transfer 2

A Vision-based Remote Assistance Method and it's Application...

引用

2nd asia conference on computer vision, image processing and pattern recognition (cvippr)

作者： Cheng, Mingkai Yi, Pengfei Guo, Yujie Liu, Rui Dong, Jing Zhou, Dongsheng Dalian Univ Sch Software Engn Key Lab Adv Design & Intelligent Comp Minist Educ Dalian Liao Ning Peoples R China Dalian Univ Technol Sch Comp Sci & Technol Dalian Liao Ning Peoples R China

ISBN: (纸本)9798400716607

Remote assistance by users is a common means in current robot applications, which can improve the efficiency of transfer tasks. However, the current mainstream methods are costly, relying on auxiliary equipment, and result in a significant workload for users throughout the task. To reduce the cost and workload of remote assistance and improve user interaction with robots. This paper has undertaken the following work using available visual image information. Firstly, proposing a remote guidance method based on facial information, which is derived from analyzing user facial information for gaze estimation and combined with image detection. Secondly, proposing an autonomous transfer method based on position inference, which combines target information in images with the real-time state of the robot. Finally, by integrating the above methods, proposing a vision-based remote assistance method and applyingit in real-world experiments of object transfer tasks.

关键词： Visual processing Gaze Estimation Position Inference Object Transfer Remote Assistance

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共3页 << < 1 2 3 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：