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

17,699 篇 会议
260 册 图书
190 篇 期刊文献
1 篇 学位论文

馆藏范围

18,149 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

10,551 篇 工学
- 6,241 篇 计算机科学与技术...
- 4,017 篇 电气工程
- 3,839 篇 控制科学与工程
- 2,914 篇 软件工程
- 1,926 篇 信息与通信工程
- 1,556 篇 光学工程
- 1,409 篇 机械工程
- 998 篇 仪器科学与技术
- 583 篇 电子科学与技术（可...
- 550 篇 生物医学工程（可授...
- 434 篇 生物工程
- 232 篇 材料科学与工程（可...
- 196 篇 交通运输工程
- 164 篇 安全科学与工程
- 154 篇 化学工程与技术
- 139 篇 力学（可授工学、理...
- 117 篇 建筑学
- 112 篇 土木工程
- 105 篇 航空宇航科学与技...
3,403 篇 理学
- 2,549 篇 物理学
- 806 篇 数学
- 487 篇 生物学
- 295 篇 系统科学
- 210 篇 统计学（可授理学、...
- 134 篇 化学
1,654 篇 医学
- 1,577 篇 临床医学
- 185 篇 基础医学(可授医学...
764 篇 管理学
- 584 篇 管理科学与工程(可...
- 191 篇 图书情报与档案管...
- 121 篇 工商管理
107 篇 农学
79 篇 法学
44 篇 经济学
44 篇 教育学
39 篇 艺术学
37 篇 军事学
18 篇 文学

主题

2,737 篇 computer vision
1,686 篇 cameras
1,488 篇 signal processin...
1,444 篇 robot vision sys...
1,359 篇 image processing
1,176 篇 robot sensing sy...
911 篇 signal processin...
876 篇 mobile robots
837 篇 feature extracti...
770 篇 machine vision
549 篇 image segmentati...
504 篇 object detection
442 篇 visualization
424 篇 deep learning
409 篇 robustness
392 篇 estimation
367 篇 stereo vision
358 篇 navigation
341 篇 training
321 篇 robot kinematics

机构

83 篇 centre for visio...
63 篇 xi an jiao tong ...
54 篇 centre for visio...
37 篇 school of electr...
36 篇 centre for visio...
29 篇 carnegie mellon ...
28 篇 chinese acad sci...
27 篇 shanghai jiao to...
27 篇 center for machi...
27 篇 university of ch...
23 篇 centre for visio...
23 篇 harbin inst tech...
21 篇 univ chinese aca...
21 篇 nanyang technol ...
17 篇 centre for visio...
16 篇 university of sc...
16 篇 tsinghua univers...
13 篇 chinese acad sci...
13 篇 univ sci & techn...
13 篇 chinese univ hon...

作者

52 篇 j. kittler
40 篇 josef kittler
28 篇 nakadai kazuhiro
19 篇 anil fernando
19 篇 wang wei
15 篇 chen chen
14 篇 yang yang
13 篇 jing zhang
13 篇 liu yang
13 篇 sun fuchun
13 篇 nascimento jacin...
12 篇 sun lining
12 篇 hansung kim
11 篇 zhang lei
11 篇 bartolozzi chiar...
11 篇 hong liu
10 篇 wang lei
10 篇 li yang
10 篇 aguiar pedro m. ...
10 篇 qiuqiang kong

语言

17,892 篇 英文
158 篇 其他
88 篇 中文
12 篇 土耳其文
3 篇 俄文
2 篇 西班牙文

检索条件"任意字段=International Conference on Robot Vision and Signal Processing"

共 18150 条记录，以下是951-960 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：

CROSS-MODAL KNOWLEDGE DISTILLATION FOR vision-TO-SENSOR ACTION RECOGNITION 47

CROSS-MODAL KNOWLEDGE DISTILLATION FOR VISION-TO-SENSOR ACTI...

引用

47th IEEE international conference on Acoustics, Speech and signal processing (ICASSP)

作者： Ni, Jianyuan Sarbajna, Raunak Liu, Yang Ngu, Anne H. H. Yan, Yan Texas State Univ San Marcos TX 78666 USA Univ Houston Houston TX 77004 USA Sun Yat Sen Univ Guangzhou Guangdong Peoples R China IIT Chicago IL 60616 USA

ISBN: (纸本)9781665405409

Human activity recognition (HAR) based on multi-modal approach has been recently shown to improve the accuracy performance of HAR. However, restricted computational resources associated with wearable devices, i.e., smartwatch, failed to directly support such advanced methods. To tackle this issue, this study introduces an end-to-end vision-to-Sensor Knowledge Distillation (VSKD) framework. In this VSKD framework, only time-series data, i.e., accelerometer data, is needed from wearable devices during the testing phase. Therefore, this framework will not only reduce the computational demands on wearable devices, but also produce a learning model that closely matches the performance of the computational expensive multi-modal approach. In order to retain the local temporal relationship and facilitate visual deep learning models, we first convert time-series data to two-dimensional images by applying the Gramian Angular Field (GAF) based encoding method. We adopted multi-scale TRN with BN-Inception and ResNet18 as the teacher and student network in this study, respectively. A novel loss function, named Distance and Angle-wised Semantic Knowledge loss (DASK), is proposed to mitigate the modality variations between the vision and the sensor domain. Extensive experimental results on UTD-MHAD, MMAct, and Berkeley-MHAD datasets demonstrate the competitiveness of the proposed VSKD model which can be deployed on wearable devices.

关键词： Cross-modal knowledge distillation vision-to-sensor Human activity recognition

来源：评论

学校读者我要写书评

暂无评论

Path Planning for Mobile robot Based on Deep Reinforcement Learning and Fuzzy Control

Path Planning for Mobile Robot Based on Deep Reinforcement L...

引用

international conference on Image processing, Computer vision and Machine Learning (ICICML)

作者： Liu, Chunling Xu, Jun Guo, Kaiwen Dalian Univ Coll Informat Engn Dalian Peoples R China

ISBN: (纸本)9781665464680

Aiming at the problems of slow training speed and poor generalization ability of deep reinforcement learning model in path planning, this paper proposes a multi-controller model of Dueling DQN combined with fuzzy control(DDFC). At the beginning of training, fuzzy control is used to provide a large number of positive samples for the Dueling DQN model, so as to improve the training efficiency of the model while ensuring that the mobile robot has certain obstacle avoidance ability at the beginning of training. The negative feedback shaping reward function and state space are designed to alleviate the problem of sparse reward. Aiming at the fact that the membership function of traditional fuzzy control can't deal with difference situations in the process of moving, an improved membership function is designed, which can change according to the change of the situation. The simulation results show that the improved model can make the mobile robot avoid obstacles effectively and improve the rate of convergence. It also has good performance in different scenes and improves the generalization ability of the model.

关键词： Fuzzy control Deep reinforcement learning Dueling DQN Path planning

来源：评论

学校读者我要写书评

暂无评论

Development of Hybrid Image Caption Generation Method using Deep Learning 10

Development of Hybrid Image Caption Generation Method using ...

引用

10th international conference on signal processing and Integrated Networks, SPIN 2023

作者： Namdev, Anuja Reddy, S.R.N. Indira Gandhi Delhi Technical University for Women Dept. of Computer Science and Engineering Kashmere Gate Delhi India

ISBN: (纸本)9781665490993

The image captioning is a process of generating descriptive sentence for a given image in human understandable language and such sentence is known as caption of the image. The automatic image caption generated is a result of deep analysis performed on the image which involves detecting objects in the image as well as the relationship between them. The generated caption should be meaningful and related to the context of the image. Image captioning techniques are the most researched area. It involves expertise of computer vision (CV), natural language processing (NLP) and artificial intelligence (AI). This paper proposes a novel hybrid approach for higher accuracy of image captioning. A detailed review of traditional methods and methods based on deep learning developed for image captioning are analyzed. The different method has significantly different Bilingual Evaluation Understudy (BLEU) scores on similar images. Thus, the hybrid approach is developed to get high BLEU score for each input images. The data set generation, implementation of hybrid approach, and the challenges along with the future work are discussed. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Disentangling Hierarchical Features for Anomalous Sound Detection Under Domain Shift

Disentangling Hierarchical Features for Anomalous Sound Dete...

引用

2025 IEEE international conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Guan, Jian Tian, Jiantong Zhu, Qiaoxi Xiao, Feiyang Zhang, Hejing Liu, Xubo Group of Intelligent Signal Processing College of Computer Science and Technology Harbin Engineering University Harbin150001 China Acoustics Lab University of Technology Sydney UltimoNSW2007 Australia Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

ISBN: (纸本)9798350368741

Anomalous sound detection (ASD) encounters difficulties with domain shift, where the sounds of machines in target domains differ significantly from those in source domains due to varying operating conditions. Existing methods typically employ domain classifiers to enhance detection performance, but they often overlook the influence of domain-unrelated information. This oversight can hinder the model's ability to clearly distinguish between domains, thereby weakening its capacity to differentiate normal from abnormal sounds. In this paper, we propose a Gradient Reversal-based Hierarchical feature Disentanglement (GRHD) method to address the above challenge. GRHD uses gradient reversal to separate domain-related features from domain-unrelated ones, resulting in more robust feature representations. Additionally, the method employs a hierarchical structure to guide the learning of fine-grained, domain-specific features by leveraging available metadata, such as section IDs and machine sound attributes. Experimental results on the DCASE 2022 Challenge Task 2 dataset demonstrate that the proposed method significantly improves ASD performance under domain shift. © 2025 IEEE.

关键词： Anomalous sound detection domain shift feature learning gradient reversal

来源：评论

学校读者我要写书评

暂无评论

robot-on-Chip: Computing on a Single Chip for an Autonomous robot

Robot-on-Chip: Computing on a Single Chip for an Autonomous ...

引用

2022 IEEE international conference on Consumer Electronics, ICCE 2022

作者： Jeong, Young Woo Go, Kwang Hyun Lee, Seung Eun Seoul National University of Science and Technology Department of Electronic Engineering Seoul Korea Republic of

ISBN: (纸本)9781665441544

The interest in autonomous robots is growing due to diverse usability. Autonomous robots are equipped with various sensors for stable operation. As the sensor data increases, the system for sensor signal processing and actuators controlling is complicated. In this paper, we propose the robot-on-chip (RoC) which processes all functions for an autonomous robot on a single chip mounted on a robot. In order to realize the RoC, we designed an autonomous robot with a lightweight algorithm and a hardware-friendly architecture. We demonstrated the feasibility of the RoC that the robot moves successfully without bumping into people in a building by recognizing the environment. © 2022 IEEE.

关键词： signal processing

来源：评论

学校读者我要写书评

暂无评论

Pu-Edgeformer++: An Advanced Hierarchical Edge Transformer for Arbitrary-Scale Point Cloud Upsampling using Distance Fields 49

Pu-Edgeformer++: An Advanced Hierarchical Edge Transformer f...

引用

2024 IEEE international conference on Acoustics, Speech, and signal processing, ICASSP 2024

作者： Kim, Dohoon Shin, Minwoo Ryu, Jaeseok Lim, Heunseung Paik, Joonki Chung-Ang University Department of Image Seoul Korea Republic of Chung-Ang University Department of Artificial Intelligence Seoul Korea Republic of

Despite of pre-processing the raw point cloud is important, limited research has been conducted on learning-based approaches to point cloud upsampling. PU-EdgeFormer [1] model stands out for its exceptional performance, which is attributed to its unique inductive biases that seamlessly blend both local and global characteristics of point clouds through the integration of graph convolution and transformer mechanisms. In this paper, we present EdgeFormer++, an advanced hierarchical edge transformer module designed for arbitrary-scale point cloud upsampling. Our module employs crossattention and dense connections to integrate information from both feature and input point cloud while maintaining the structural elements of graph convolutions and transformers. Experimental results, both qualitative and quantitative, indicate that our proposed method outperforms existing techniques in point cloud upsampling. The official source code is accessible at https://***/dohoon2045/PU-EdgeFormer2. © 2024 IEEE.

关键词： graph convolution implicit neural representation Point cloud upsampling vision transformer

来源：评论

学校读者我要写书评

暂无评论

TRANSDUCTIVE CLIP WITH CLASS-CONDITIONAL CONTRASTIVE LEARNING 47

TRANSDUCTIVE CLIP WITH CLASS-CONDITIONAL CONTRASTIVE LEARNIN...

引用

47th IEEE international conference on Acoustics, Speech and signal processing (ICASSP)

作者： Huang, Junchu Chen, Weijie Yang, Shicai Xie, Di Pu, Shiliang Zhuang, Yueting South China Univ Technol Guangzhou Peoples R China Hikvis Res Inst Hangzhou Peoples R China Zhejiang Univ Hangzhou Peoples R China

ISBN: (纸本)9781665405409

Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of data labeling. However, such supervision inevitably contains the label noise, which significantly degrades the discriminative power of the classification model. In this work, we propose Transductive CLIP, a novel framework for learning a classification network with noisy labels from scratch. Firstly, a class-conditional contrastive learning mechanism is proposed to mitigate the reliance on pseudo labels and boost the tolerance to noisy labels. Secondly, ensemble labels is adopted as a pseudo label updating strategy to stabilize the training of deep neural networks with noisy labels. This framework can reduce the impact of noisy labels from CLIP model effectively by combining both techniques. Experiments on multiple benchmark datasets demonstrate the substantial improvements over other state-of-the-art methods.

关键词： vision-Language Pre-trained Model Transductive Learning Noisy Label Learning Contrastive Learning Unsupervised Model Optimization

来源：评论

学校读者我要写书评

暂无评论

DENSELY CONNECTED SWIN-UNET FOR MULTISCALE INFORMATION AGGREGATION IN MEDICAL IMAGE SEGMENTATION 30

DENSELY CONNECTED SWIN-UNET FOR MULTISCALE INFORMATION AGGRE...

引用

30th IEEE international conference on Image processing (ICIP)

作者： Wang, Ziyang Su, Meiwen Zheng, Jian-Qing Liu, Yang Univ Oxford Dept Comp Sci Oxford England Univ Hong Kong Dept Stat & Actuarial Sci Hong Kong Peoples R China Univ Oxford Kennedy Inst Rheumatol Oxford England Univ Plymouth Dept Comp Sci Plymouth Devon England

ISBN: (纸本)9781728198354

Image semantic segmentation is a dense prediction task in computer vision that is dominated by deep learning techniques in recent years. UNet, which is a symmetric encoder-decoder end-to-end Convolutional Neural Network (CNN) with skip connections, has shown promising performance. Aiming to process the multiscale feature information efficiently, we propose a new Densely Connected Swin-UNet (DCS-UNet) with multiscale information aggregation for medical image segmentation. Firstly, inspired by Swin-Transformer to model long-range dependencies via shift-window-based self-attention, this work proposes the use of fully ViT-based network blocks with a shift-window approach, resulting in a purely self-attention-based U-shape segmentation network. The relevant layers including feature sampling and image tokenization are re-designed to align with the ViT fashion. Secondly, a full-scale deep supervision scheme is developed to process the aggregated feature map with various resolutions generated by different levels of decoders. Thirdly, dense skip connections are proposed that allow the semantic feature information to be thoroughly transferred from different levels of encoders to lower level decoders. Our proposed method is validated on a public benchmark MRI Cardiac segmentation data set with comprehensive validation metrics showing competitive performance against other variant encoder-decoder networks. The code is available at https://***/ziyangwang007/VIT4UNet.

关键词： Semantic Segmentation UNet vision Transformer

来源：评论

学校读者我要写书评

暂无评论

robot Cleaner Localization Using RFID and vision System 16

Robot Cleaner Localization Using RFID and Vision System

引用

16th IEEE AFRICON, AFRICON 2023

作者： Helaly, Farida Bassiouny, Sarah Zaghloul, Yasmine German International University Department of Mechanical Engineering Egypt

ISBN: (纸本)9798350336214

Localization is a fundamental element required in various applications across fields such as vehicle navigation, smart factories, automation systems, and product shipping services. This paper discusses the fusion of two popular systems- RFID and vision systems to maximize their individual advantages and minimize their respective drawbacks. Using the RFID system, the Received signal Strength Indicator (RSSI) and tag ID are collected using the fingerprinting technique by utilizing two different types of antennas the far-field antenna (transmits and receives in range of meters) and the near-field antenna (transmits and receives in range of centimetres) and deploying passive tags. After comparing the two in terms of location error accuracy, it was found that the near-field antenna achieved significantly better results, with an accuracy level 55 % better than that of the far-field antenna. In the vision system, a fixed camera captures images for image processing algorithms to detect and localize the cleaner using the appearance-based approach. The accuracy level of this system alone was found to be 81.8%. However, upon fusing both systems, the accuracy levels improved to 90.9 % as each system contributed to the other to reduce each system's drawbacks eliminating the time incompatibility present in the vision system due to computational cost and the sensitivity of the RFID system from the materials used in the environment also, to get the best of RFID system two types of antennas where compared to choose the most accurate, the fusion resulted in an improved and a decreased average error localization system. © 2023 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

VLCAP: vision-LANGUAGE WITH CONTRASTIVE LEARNING FOR COHERENT VIDEO PARAGRAPH CAPTIONING 29

VLCAP: VISION-LANGUAGE WITH CONTRASTIVE LEARNING FOR COHEREN...

引用

IEEE international conference on Image processing (ICIP)

作者： Yamazaki, Kashu Truong, Sang Vo, Khoa Kidd, Michael Rainwater, Chase Luu, Khoa Le, Ngan Univ Arkansas Fayetteville AR 72701 USA

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

In this paper, we leverage the human perceiving process, that involves vision and language interaction, to generate a coherent paragraph description of untrimmed videos. We propose vision-language (VL) features consisting of two modalities, i.e., (i) vision modality to capture global visual content of the entire scene and (ii) language modality to extract scene elements description of both human and non-human objects (e.g. animals, vehicles, etc), visual and non-visual elements (e.g. relations, activities, etc). Furthermore, we propose to train our proposed VLCap under a contrastive learning VL loss. The experiments and ablation studies on ActivityNet Captions and YouCookII datasets show that our VLCap outperforms existing SOTA methods on both accuracy and diversity metrics. Source code: https://***/UARK- AICV/VLCAP

关键词： Contrastive Learning Video Captioning vision Language

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500页 << < 92 93 94 95 96 97 98 99 100 101 > >>

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：