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

17,661 篇 会议
259 册 图书
190 篇 期刊文献
1 篇 学位论文

馆藏范围

18,110 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

10,534 篇 工学
- 6,233 篇 计算机科学与技术...
- 4,015 篇 电气工程
- 3,829 篇 控制科学与工程
- 2,908 篇 软件工程
- 1,924 篇 信息与通信工程
- 1,554 篇 光学工程
- 1,406 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
- 154 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...
3,400 篇 理学
- 2,548 篇 物理学
- 805 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
1,654 篇 医学
- 1,577 篇 临床医学
- 185 篇 基础医学(可授医学...
761 篇 管理学
- 582 篇 管理科学与工程(可...
- 190 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

2,736 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
424 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

17,927 篇 英文
86 篇 中文
84 篇 其他
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 18111 条记录，以下是311-320 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：

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

Object-Centric Discriminative Learning for Text-Based Person Retrieval

Object-Centric Discriminative Learning for Text-Based Person...

引用

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

作者： Haiwen Li Delong Liu Fei Su Zhicheng Zhao Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System and Network Culture China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Text-based person retrieval (TBPR) is a vision-language task that aims to find specific pedestrians in a large image gallery using the textual description. However, due to the heterogeneity between modalities and the redundancy in visual representations, it remains a challenging task. Existing methods do not explicitly reduce the influence of the background regions in images, inevitably decreasing representation ability and reducing the image-text matching performance. In this paper, we propose a novel framework for text-based person retrieval, termed Object-Centric Discriminative Learning (OCDL), which incorporates person masks to indicate attentive regions, thereby enhancing the model’s focus on the pedestrians in images while suppressing the background noise. Additionally, a novel crossmodal matching loss, namely Soft Angular Distribution Matching (SADM), is introduced to learn discriminative visual and textual representations. Extensive experiments on three widely-used TBPR datasets demonstrate the effectiveness of our approach. The code is available at https://***/JThuge/OCDL.

关键词： Visualization Pedestrians Codes Redundancy signal processing Performance gain Benchmark testing Feature extraction Speech processing Cross modal retrieval

来源：评论

学校读者我要写书评

暂无评论

Constructing Datasets From Public Police Body Camera Footage

Constructing Datasets From Public Police Body Camera Footage

引用

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

作者： Jamie Rosas-Smith Martijn Bartelds Ruizhe Huang Leibny Paola García-Perera Karen Livescu Dan Jurafsky Anjalie Field Johns Hopkins University Stanford University Toyota Technological Institute Chicago

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The enormous potential of body-worn cameras to improve accountability in policing remains largely unrealized due to large volumes of unreviewed footage. Transcription and diarization tools could aid in reviewing footage, but lack of public data hinders their development. We develop a pipeline to construct public datasets, making use of the small number of videos publicly released by police departments, with capacity to update the data as footage gets released or removed. Our pipeline produces two datasets, a large one with transcriptions automatically extracted from department-generated captions, and a smaller test set where we manually validated transcripts and alignment. We benchmark ASR models, including models fine-tuned on our data, on our test set, to show applications of our datasets and continued challenges of this domain. Our work presents a new vision for leveraging public body-worn camera footage—even when it can’t be rereleased—to help address this critical social issue.

关键词： Law enforcement Pipelines Speech recognition signal processing Benchmark testing Cameras Data models Acoustics Speech processing Videos

来源：评论

学校读者我要写书评

暂无评论

Multi-label body constitution recognition via dual transform MLP-like architecture using tongue images

Multi-label body constitution recognition via dual transform...

引用

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

作者： Mengjian Zhang Guihua Wen Pei Yang School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

According to the traditional Chinese medicine composite constitution theory, body constitution recognition is modeled as a unique task of multi-label problems using tongue images. Although MLP-like architecture is one of the base models except for CNN-based, Transformer-based, and MLP-like-based for computer vision tasks, the performance of the MLP-like-based architecture for the multi-label BCR task needs to expand for multi-label BCR task with a specific module using tongue images. Thus, a novel dual transform MLP-like (DT-MLP) model is designed, in which discrete Fourier transform and chaos transform are used for feature extraction of their branches. Besides, a new multi-label tongue body constitution dataset is constructed. The results demonstrate that the proposed DT-MLP outperforms other state-of-the-art MLP-like models on mAP, AUC, and Acc, respectively.

关键词： Tongue Image recognition Computational modeling Transforms Speech recognition Computer architecture signal processing Transformers Speech processing IEEE Constitution

来源：评论

学校读者我要写书评

暂无评论

Training Dialogue Systems by AI Feedback for Improving Overall Dialogue Impression

Training Dialogue Systems by AI Feedback for Improving Overa...

引用

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

作者： Kai Yoshida Masahiro Mizukami Seiya Kawano Canasai Kruengkrai Hiroaki Sugiyama Koichiro Yoshino Nara Institute of Science and Technology Japan Guardian Robot Project RIKEN Japan NTT Communication Science Laboratories Japan Institute of Science Tokyo Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

To improve user engagement during conversations with dialogue systems, we must improve individual dialogue responses and dialogue impressions such as consistency, personality, and empathy throughout the entire dialogue. While such dialogue systems have been developing rapidly with the help of large language models (LLMs), reinforcement learning from AI feedback (RLAIF) has attracted attention to align LLM-based dialogue models for such dialogue impressions. In RLAIF, a reward model based on another LLM is used to create a training signal for an LLM-based dialogue model using zero-shot/few-shot prompting techniques. However, evaluating an entire dialogue only by prompting LLMs is challenging. In this study, the supervised fine-tuning (SFT) of LLMs prepared reward models corresponding to 12 metrics related to the impression of the entire dialogue for evaluating dialogue responses. We tuned our dialogue models using the reward model signals as feedback to improve the impression of the system. The results of automatic and human evaluations showed that tuning the dialogue model using our reward model corresponding to dialogue impression improved the evaluation of individual metrics and the naturalness of the dialogue response.

关键词： Measurement Training Hands Adaptation models Large language models Reinforcement learning Oral communication signal processing Speech processing Tuning

来源：评论

学校读者我要写书评

暂无评论

Super Capacity SRS Design for 5G and beyond using Channel In-painting

Super Capacity SRS Design for 5G and beyond using Channel In...

引用

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

作者： Usman Akram Fan Zhang Shawn Ma Yang Li Haris Vikalo Department of Electrical and Computer Engineering University of Texas at Austin Austin TX USA Standards and Mobility Innovation Lab Samsung Research America Plano TX USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Reliable communication of data in modern wireless systems requires accurate channel state information (CSI). Sounding Reference signal (SRS) based CSI acquisition enables the estimation of the channel between the base station and user equipment through the uplink transmission of known SRS by the user equipment to the base station. However, limited SRS resources and limited signal to Noise Ratio (SNR) coverage for which SRS-based CSI acquisition can be performed renders the acquisition of CSI challenging. We propose an approach to perform sparse non-uniform SRS resource allocation and use a masked auto-encoder with a vision transformer backbone to reconstruct full band channel from partial sub-band information. Experiments on data emulating transmission over CDL-A, B, and C channels demonstrate that the proposed method can achieve state-of-the-art normalized mean square error (NMSE) using only 25% of the band information. This translates to a four fold increase in SRS resource capacity and 6dB improvement in SRS coverage under current 5G NR specifications.

关键词： Wireless communication Base stations 5G mobile communication signal processing Transformers Resource management Reliability Uplink Speech processing signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Smart Spectacles to Assist Blind Individuals in Developing Countries

Low-Cost Smart Spectacles to Assist Blind Individuals in Dev...

引用

international conference on robotics,Electrical and signal processing Techniques (ICREST)

作者： Shuvra Mondal Md. Ashiquzzaman Tarifuzzaman Riyad Samiu Javed Islam Asif Imtiaz Anik Department of Electrical and Electronic Engineering American International University-Bangladesh (AIUB) Dhaka Bangladesh Department of Engineering The University of Adelaide South Australia Australia

ISBN: (数字)9798331530952

ISBN: (纸本)9798331530969

Advancements in assistive technologies present a promising avenue for enhancing the independence and safety of visually impaired individuals, integrating seamlessly into their daily routines and providing essential support for navigating environments. This research introduces a low-cost Smart Glass (Spectacles) for blind people, utilizing an ultrasonic sensor, NE 555 IC, 10 UF 25V capacitor and buzzer. The proposed device excels in non-invasive detection of obstacles, offering real-time auditory feedback to alert users of potential hazards. By incorporating widely available and cost-effective components, the Smart Glass offers an accessible solution to improve the mobility and autonomy of visually impaired individuals, particularly in developing regions. The test results show promising outcomes that may significantly impact personal safety, independence, and overall quality of life.

关键词： Accuracy Systematics Blindness Assistive technologies robot sensing systems Real-time systems Artificial light Acoustics Sustainable development Smart glasses

来源：评论

学校读者我要写书评

暂无评论

RFEM: Remote Feature Enhancement Module for Target Detection

RFEM: Remote Feature Enhancement Module for Target Detection

引用

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

作者： Feng Hu Chuangye Wang Jian Xiong Wenhua Zhang Haolun Li Hao Gao College of Automation and College of Artificial Intelligence Nanjing University of Posts and Telecommunications China Stage Grid Bengbu Power China MIGU Co. Ltd China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The research and development of dense crowd detection technology have always been one of the hot and challenging topics in the field of computer vision. DETR-like models have shown good performance in both training efficiency and inference capabilities. Nevertheless, as the optimization proceeds, these models can demonstrate sparse long-range feature correlations. This paper presents a specialized long-range feature enhancement module intended for optimizing DETR-like detection models. By utilizing an optimized PVM clustering algorithm, the robustness of the model is enhanced, and linear attention is incorporated into the aggregated tokens to reinforce long-range feature relationships. Besides, our method maintains the connections between occluded segmentation features during both training and inference phases. It also enhances the detection accuracy of small targets without increasing computational overhead. We conducted experiments on the COCO 2017 and the CrowdHuman datasets, and extensive experimental results demonstrate the effectiveness of our proposed method.

关键词： Training Accuracy Computational modeling signal processing algorithms Object detection Speech enhancement signal processing Feature extraction Robustness Research and development

来源：评论

学校读者我要写书评

暂无评论

ViCo: A Multitask Video-enhanced and Cognition-preserving Modality Alignment Training Framework

ViCo: A Multitask Video-enhanced and Cognition-preserving Mo...

引用

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

作者： Zhenda Yu Jin Chen Jiayu Shen Lanxiang Zhou Han Fang Xianghao Zang Chao Ban Jingfeng Chen Zhongjiang He Hao Sun Zerui Li Yanmei Kang Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China TeleAI Beijing China School of Artificial Intelligence Anhui University Hefei China School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China Duke Kunshan University Suzhou China The Department of Automation University of Science and Technology of China Hefei China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The rapid development of multimodal large language models (MLLMs) has brought significant breakthroughs to this field. However, current MLLMs typically rely on vision instruction tuning based on large language models (LLMs) to endow them with multimodal capabilities, which may lead to low video utilization and catastrophic forgetting due to the task-specific nature of vision instruction tuning. Take case of multiple-choice Video Question Answering (VideoQA) as an example, requiring only selecting correct answers makes it easier for LLMs to shortcut rather than fully comprehend video content. Moreover, the fixed task format of ’’predicting the correct option" risks catastrophic forgetting, which can cause LLMs to lose their origin cognitive abilities. To address this, we propose ViCo, a training framework that enables LLMs to perform a specific auxiliary tasks during vision instruction tuning, which helps the model leverage video information more thoroughly while mitigating catastrophic forgetting, thereby improving modality alignment and enhancing performance. We evaluate our method on several strong VideoQA benchmarks, where it outperforms all state-of-the-art methods, demonstrating its effectiveness and generality. Additionally, we also provide extensive analysis on the video information utilization and catastrophic forgetting resulting. The code will be made available at https://***/dunknsabsw/ViCo.

关键词： Training Codes Large language models signal processing Benchmark testing Question answering (information retrieval) Acoustics Speech processing Tuning

来源：评论

学校读者我要写书评

暂无评论

vision-text Enhancement Network For Weakly Supervised Video Anomaly Detection

Vision-text Enhancement Network For Weakly Supervised Video ...

引用

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

作者： Yiheng Chen Shuai Fu Niantong Qin Xinning Du Jianping Ren Shuhua Liu Northeast Normal University ChangChun China Changchun Humanities and Sciences College ChangChun China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The recent vision-language pre-training model ImageBind has shown significant success in a wide range of visual tasks, demonstrating excellent ability of joint embedding space across different modalities in visual or textual representation. A worthwhile problem is utilizing such a strong model for weakly supervised video anomaly detection (WSVAD). Most previous works only use the single visual modality, and define anomaly detection as a simple video classification task. However, such solutions ignore the textual information in the dataset and the anomaly event localization. To address these issues, this paper proposes the vision-text enhancement network (VTENet). For text features, it adopts the frozen ImageBind model directly without any fine-tuning process. For video features, it enhances visual feature representation through the proposed temporal enhancement graph convolution module (TGC). VTENet makes full use of associations between vision and text, contains two branches to complete coarse-grained and fine-grained video anomaly detection. One branch utilizes visual features for coarse-grained binary classification, while the other compares the text features with the entire video features across the dataset to complete fine-grained video anomaly detection. Extensive experiments on XD-Violence and UCF-Crime demonstrate the superiority of the proposed approach in both coarse-grained and fine-grained tasks.

关键词： Location awareness Visualization Correlation Convolution Speech enhancement Benchmark testing Feature extraction Boosting Acoustics Anomaly detection

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 << < 28 29 30 31 32 33 34 35 36 37 > >>

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：