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

17,662 篇 会议
257 册 图书
190 篇 期刊文献
1 篇 学位论文

馆藏范围

18,109 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

10,535 篇 工学
- 6,235 篇 计算机科学与技术...
- 4,015 篇 电气工程
- 3,831 篇 控制科学与工程
- 2,909 篇 软件工程
- 1,925 篇 信息与通信工程
- 1,553 篇 光学工程
- 1,408 篇 机械工程
- 997 篇 仪器科学与技术
- 583 篇 电子科学与技术（可...
- 549 篇 生物医学工程（可授...
- 433 篇 生物工程
- 232 篇 材料科学与工程（可...
- 195 篇 交通运输工程
- 163 篇 安全科学与工程
- 155 篇 化学工程与技术
- 139 篇 力学（可授工学、理...
- 115 篇 建筑学
- 110 篇 土木工程
- 104 篇 航空宇航科学与技...
3,401 篇 理学
- 2,548 篇 物理学
- 806 篇 数学
- 486 篇 生物学
- 295 篇 系统科学
- 209 篇 统计学（可授理学、...
- 134 篇 化学
1,655 篇 医学
- 1,577 篇 临床医学
- 185 篇 基础医学(可授医学...
762 篇 管理学
- 582 篇 管理科学与工程(可...
- 191 篇 图书情报与档案管...
- 120 篇 工商管理
107 篇 农学
78 篇 法学
43 篇 经济学
42 篇 教育学
39 篇 艺术学
37 篇 军事学
18 篇 文学

主题

2,739 篇 computer vision
1,685 篇 cameras
1,489 篇 signal processin...
1,441 篇 robot vision sys...
1,355 篇 image processing
1,173 篇 robot sensing sy...
912 篇 signal processin...
874 篇 mobile robots
839 篇 feature extracti...
769 篇 machine vision
549 篇 image segmentati...
504 篇 object detection
440 篇 visualization
425 篇 deep learning
409 篇 robustness
393 篇 estimation
367 篇 stereo vision
358 篇 navigation
343 篇 training
319 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
18 篇 wang wei
15 篇 chen chen
14 篇 yang yang
14 篇 nascimento jacin...
13 篇 jing zhang
13 篇 liu yang
13 篇 sun fuchun
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

17,924 篇 英文
86 篇 其他
86 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 18110 条记录，以下是281-290 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：

Uncertainty-aware Correspondence Distillation for Deep Image Clustering

Uncertainty-aware Correspondence Distillation for Deep Image...

引用

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

作者： Luyao Chang Leiting Chen Chuan Zhou School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Image clustering is a challenging task in computer vision, with performance heavily dependent on the quality of feature representations due to the inherent complexity of images. However, current image clustering methods overlook the underlying semantic information during representation learning, leading to low-quality feature representations. Moreover, the absence of ground-truth labels amplifies the detrimental effects of unreliable data on semantic guidance, steering the model towards incorrect learning directions. In this work, we propose a novel deep image clustering method named Uncertainty-aware Correspondence Distillation (UCD) to address these issues. Specifically, we introduce the concept of representation correspondence to establish cross-level connections between instances and semantics, which is further employed as a distillation target to improve the network’s feature learning by complementing semantic information. To mitigate unnecessary similarity penalties arising from unreliable data, we develop robust dynamic weights for semantic guidance by modeling the uncertainty of image semantics. Extensive experiments on five benchmark datasets demonstrate the superiority of the proposed method. The code is available at https://***/YL616/UCD.

关键词： Representation learning Computer vision Uncertainty Clustering methods Semantics Noise Interference Data models Complexity theory Speech processing

来源：评论

学校读者我要写书评

暂无评论

Emerging Technology for the Biohybrid robotics

Emerging Technology for the Biohybrid Robotics

引用

IEEE international conference on Micro Electro Mechanical Systems

作者： Shoji Takeuchi Graduate School of Information Science and Technology The University of Tokyo Japan Kanagawa Institute of Industrial Science and Technology (KISTEC) Japan

ISBN: (数字)9798331508890

ISBN: (纸本)9798331508906

Biohybrid robotics integrates living tissues with synthetic systems, enabling robots to perform nature-inspired functions. Recent advancements include biohybrid (BH) sensors for highly sensitive and selective detection, BH reactors replicating organ-like processes for drug testing and artificial organ development, BH actuators enabling efficient and silent movement, and BH processors offering energy-efficient signal processing and adaptive learning. Future biohybrid robots may feature living skin and energy systems that metabolize food, potentially serving roles in organ transplantation. Although challenges such as scalability, stability, and ethical considerations remain, interdisciplinary research continues to drive progress, merging biology and engineering to address critical societal needs.

关键词： Ethics Program processors Scalability Transforms signal processing robot sensing systems Skin Sensor systems Biosensors Testing

来源：评论

学校读者我要写书评

暂无评论

Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras

Event Masked Autoencoder: Point-wise Action Recognition with...

引用

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

作者： Jingkai Sun Qiang Zhang Jiaxu Wang Jiahang Cao Hao Cheng Renjing Xu Hong Kong University of Science and Technology Guangzhou

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Dynamic vision sensors (DVS) are bio-inspired devices that capture visual information in the form of asynchronous events, which encode changes in pixel intensity with high temporal resolution and low latency. These events provide rich motion cues that can be exploited for various computer vision tasks, such as action recognition. However, most existing DVS-based action recognition methods lose temporal information during data transformation or suffer from noise and outliers caused by sensor imperfections or environmental factors. To address these challenges, we propose a novel framework that preserves and exploits the spatiotemporal structure of event data for action recognition. Our framework consists of two main components: 1) a point-wise event masked autoencoder (MAE) that learns a compact and discriminative representation of event patches by reconstructing them from masked raw event camera points data; 2) an improved event points patch generation algorithm that leverages an event data inlier model and point-wise data augmentation techniques to enhance the quality and diversity of event points patches. To the best of our knowledge, our approach introduces the pre-train method into event camera raw points data for the first time, and we propose a novel event points patch embedding to utilize transformer-based models on event cameras.

关键词： Visualization Autoencoders Speech recognition vision sensors Cameras Transformers Data models Spatiotemporal phenomena Voltage control Speech processing

来源：评论

学校读者我要写书评

暂无评论

When Does Visual Prompting Outperform Linear Probing for vision-Language Models? A Likelihood Perspective

When Does Visual Prompting Outperform Linear Probing for Vis...

引用

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

作者： Hsi-Ai Tsao Lei Hsiung Pin-Yu Chen Tsung-Yi Ho National Tsing Hua University Hsinchu Taiwan Dartmouth College NH USA IBM Research NY USA The Chinese University of Hong Kong Hong Kong

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Adapting pre-trained models to new tasks can exhibit varying effectiveness across datasets. Visual prompting, a state-of-the-art parameter-efficient transfer learning method, can significantly improve the performance of out-of-distribution tasks. On the other hand, linear probing, a standard transfer learning method, can sometimes become the best approach. We propose a log-likelihood ratio (LLR) approach to analyze the comparative benefits of visual prompting and linear probing. By employing the LLR score alongside resource-efficient visual prompts approximations, our cost-effective measure attains up to a 100-fold reduction in run time compared to full training, while achieving prediction accuracies up to 91%. The source code is available at VP-LLR.

关键词： Training Visualization Accuracy Source coding Transfer learning signal processing Time measurement Reliability Speech processing Standards

来源：评论

学校读者我要写书评

暂无评论

COCO-OLAC: A Benchmark for Occluded Panoptic Segmentation and Image Understanding

COCO-OLAC: A Benchmark for Occluded Panoptic Segmentation an...

引用

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

作者： Wenbo Wei Jun Wang Abhir Bhalerao Department of Computer Science University of Warwick UK

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

To help address the occlusion problem in panoptic segmentation and image understanding, this paper proposes a new large-scale dataset named COCO-OLAC (COCO Occlusion Labels for All Computer vision Tasks), which is derived from the COCO dataset by manually labelling images into three perceived occlusion levels. Using COCO-OLAC, we systematically assess and quantify the impact of occlusion on panoptic segmentation on samples having different levels of occlusion. Comparative experiments with SOTA panoptic models demonstrate that the presence of occlusion significantly affects performance, with higher occlusion levels resulting in notably poorer performance. Additionally, we propose a straightforward yet effective method as an initial attempt to leverage the occlusion annotation using contrastive learning to render a model that learns a more robust representation capturing different severities of occlusion. Experimental results demonstrate that the proposed approach boosts the performance of the baseline model and achieves SOTA performance on the proposed COCO-OLAC dataset. 1

关键词： Training Learning systems Image segmentation Annotations Manuals Benchmark testing signal processing Robustness Labeling Speech processing

来源：评论

学校读者我要写书评

暂无评论

Towards Automatic Assessment of Self-Supervised Speech Models using Rank

Towards Automatic Assessment of Self-Supervised Speech Model...

引用

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

作者： Zakaria Aldeneh Vimal Thilak Takuya Higuchi Barry-John Theobald Tatiana Likhomanenko Apple

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This study explores using embedding rank as an unsupervised evaluation metric for general-purpose speech encoders trained via self-supervised learning (SSL). Traditionally, assessing the performance of these encoders is resource-intensive and requires labeled data from the downstream tasks. Inspired by the vision domain, where embedding rank has shown promise for evaluating image encoders without tuning on labeled downstream data, this work examines its applicability in the speech domain, considering the temporal nature of the signals. The findings indicate rank correlates with downstream performance within encoder layers across various downstream tasks and for in- and out-of-domain scenarios. However, rank does not reliably predict the best-performing layer for specific downstream tasks, as lower-ranked layers can outperform higher-ranked ones. Despite this limitation, the results suggest that embedding rank can be a valuable tool for monitoring training progress in SSL speech models, offering a less resource-demanding alternative to traditional evaluation methods.

关键词： Training Measurement Speech recognition Self-supervised learning signal processing Acoustics Reliability Speech processing Tuning Monitoring

来源：评论

学校读者我要写书评

暂无评论

Multi-Point Positional Insertion Tuning for Small Object Detection

Multi-Point Positional Insertion Tuning for Small Object Det...

引用

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

作者： Kanoko Goto Takumi Karasawa Takumi Hirose Rei Kawakami Nakamasa Inoue Dept. of Computer Science Institute of Science Tokyo Tokyo Japan Dept. of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Small object detection aims to localize and classify small objects within images. With recent advances in large-scale vision-language pretraining, finetuning pretrained object detection models has emerged as a promising approach. However, finetuning large models is computationally and memory expensive. To address this issue, this paper introduces multi-point positional insertion (MPI) tuning, a parameter-efficient finetuning (PEFT) method for small object detection. Specifically, MPI incorporates multiple positional embeddings into a frozen pretrained model, enabling the efficient detection of small objects by providing precise positional information to latent features. Through experiments, we demonstrated the effectiveness of the proposed method on the SODA-D dataset. MPI performed comparably to conventional PEFT methods, including CoOp and VPT, while significantly reducing the number of parameters that need to be tuned.

关键词： Computational modeling Object detection signal processing Feature extraction Encoding Acoustics Speech processing Tuning

来源：评论

学校读者我要写书评

暂无评论

CHASE: Channel-Wise and Spatial Attention for Early Exiting in Image Classification

CHASE: Channel-Wise and Spatial Attention for Early Exiting ...

引用

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

作者： Youva Addad Alexis Lechervy Frédéric Jurie GREYC Normandy University UNICAEN ENSICAEN UMR CNRS France

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Dynamic early-exiting neural networks have been proposed for image classification to balance the trade-off between classification performance and inference cost. In this context, we propose a multi-exit neural network architecture that exploits the power of attention mechanisms, which improve performance but incur significant computational overhead. In CHASE, we introduce two attention-like mechanisms to go beyond existing multi-exit architectures. The first mechanism dynamically adjusts the importance of different feature channels and spatial locations, recalibrating channel-wise feature responses. The second mechanism, based on self-attention, aggregates features from different spatial locations at the end of the network. We evaluate the proposed architecture on the CIFAR and ImageNet datasets, comparing it with the original network and other state-of-the-art approaches. Our results show that the proposed architecture achieves competitive performance in terms of accuracy and computational efficiency.

关键词： Computer vision Attention mechanisms Accuracy Costs Neural networks Computer architecture signal processing Dynamic scheduling Speech processing Image classification

来源：评论

学校读者我要写书评

暂无评论

Semi-Automatic Labeling for Action Recognition by Diversity Preserving Sampling

Semi-Automatic Labeling for Action Recognition by Diversity ...

引用

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

作者： Ryuhei Ando Takashi Shibata Toru Takahashi NEC Corporation

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Deep learning for action recognition is an important technology for understanding videos. However, collecting video training dataset for deep learning model with low cost while maintaining enough diversity is challenging. In this paper, we propose a semi-automatic labeling framework for action recognition by diversity-preserving sampling. The proposed framework utilizes a pre-trained vision-language model (VLM) to search through video clips to filter data that matches the text that describes the appropriate context for the target action. Since this simple approach by VLM tends to lack diversity, our framework is also equipped with diversity-preserving sampling that consists of two sampling strategies. One is confidence-based weighted sampling, which is based on action class confidence obtained from VLM, and the other is isolate-constraint-based weighted sampling, which samples points that are far apart in the text-image feature space. We conduct experiments to demonstrate that the proposed approach efficiently collects data with variations that could train a better action recognition model than the baseline.

关键词： Deep learning Training Matched filters Training data Speech recognition signal processing Data models Labeling Speech processing Videos

来源：评论

学校读者我要写书评

暂无评论

FedTG: Text-guided Federated Domain Generalization

FedTG: Text-guided Federated Domain Generalization

引用

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

作者： Yiming Chen Nan He Lifeng Sun Department of Computer Science and Technology Tsinghua University Key Laboratory of Pervasive Computing Ministry of Education

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Federated Domain Generalization is aimed at learning a global model that generalizes well to new clients with domain shift in a privacy-preserving manner. Inspired by the powerful generation capability of Large language models (LLMs), we propose a novel method for this problem, named Text-guided Federated Domain Generalization (FedTG), which utilizes text generated by LLMs to guide the training of visual models. In the client, we align the image embeddings to the text embeddings, which provides strong generalization knowledge. In the server, we generate abundant textual descriptions about different classes, subsequently converting them into embeddings for fine-tuning the global classifier, which helps the global classifier not overfit to a particular domain. Moreover, we utilize the powerful image generation capabilities of LLMs to generate a cross-domain validation dataset to help select the most generalized model. We conduct experiments on several datasets, and the results prove that FedTG outperforms relevant baselines.

关键词： Training Visualization Computer vision Image synthesis Large language models Computational modeling signal processing Acoustics Servers Speech processing

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 << < 25 26 27 28 29 30 31 32 33 34 > >>

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：