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331-340 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：

Modular Prompt Learning Improves vision-Language Models

Modular Prompt Learning Improves Vision-Language Models

引用

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

作者： Zhenhan Huang Tejaswini Pedapati Pin-Yu Chen Jianxi Gao Rensselaer Polytechnic Institute Troy USA IBM Research Yorktown Heights USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily adapts them to new scenarios. Compared to fine-tuning, prompt learning enables the model to achieve comparable or better performance using fewer trainable parameters. Besides, prompt learning freezes the pre-trained model and avoids the catastrophic forgetting issue in the fine-tuning. Continuous prompts inserted into the input of every transformer layer (i.e. deep prompts) can improve the performances of pre-trained models on downstream tasks. For i-th transformer layer, the inserted prompts replace previously inserted prompts in the (i − 1)-th layer. Although the self-attention mechanism contextualizes newly inserted prompts for the current layer and embeddings from the previous layer’s output, removing all inserted prompts from the previous layer inevitably loses information contained in the continuous prompts. In this work, we propose Modular Prompt Learning (MPL) that is designed to promote the preservation of information contained in the inserted prompts. We evaluate the proposed method on base-to-new generalization and cross-dataset tasks. On average of 11 datasets, our method achieves 0.7% performance gain on the base-to-new generalization task compared to the state-of-the-art method. The largest improvement on the individual dataset is 10.7% (EuroSAT dataset). Our code is available at https://***/Zhenhan-Huang/Modular-Prompt-Learning.

关键词： Multiprotocol label switching Adaptation models Visualization Codes Semantics signal processing Performance gain Transformers Acoustics Speech processing

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

Unlocking Personality Insights: Assessing Videos with Deep Learning Techniques 3rd

Unlocking Personality Insights: Assessing Videos with Deep L...

引用

3rd international conference on signal and Data processing, ICSDP 2023

作者： Athilakshmi, R. Jansi, R. Dutta, Indira Amulya Pavikars, M.M. Department of Computational Intelligence Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur 603203 India Department of Electronics and Communication Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur 603203 India

ISBN: (纸本)9789819795772

In contemporary times, monitoring criminal behavior and providing mental health therapy requires various activities related to an individual’s character. The development of an automated process for personality assessment through behavior analysis is still under research. Our contribution to this field involves combining deep learning with a regression-based machine learning model through a data pipeline for both audio and video data. We propose a comprehensive classification pipeline that utilizes supervised methods such as LSTM, GRU, and RNN, coupled with Visual Geometry Group (VGG) models for analyzing audio and visual data. The aim is to draw a comparative analysis between these methods to effectively analyze personalities. Our approach yields quality results, achieving an accuracy rate of 88.9% by combining VGG and NN for processing audio-visual data to analyze one’s personality composition. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Computer vision Deep learning Natural language processing Neural networks Regression Supervised learning

来源：评论

学校读者我要写书评

暂无评论

OwlsEye: Real-Time Low-Light Video Instance Segmentation on Edge and Exploration of Fixed-Posit Quantization

OwlsEye: Real-Time Low-Light Video Instance Segmentation on ...

引用

international conference on VLSI Design

作者： Gaurav Shah Abhinav Goud Zaqi Momin Joycee Mekie Indian Institute of Technology Gandhinagar

ISBN: (数字)9798331522445

ISBN: (纸本)9798331522452

Video Instance Segmentation (VIS) in low light conditions presents a significant challenge when deployed on resource-constrained edge devices, especially in autonomous vehicles, surveillance, robotics, or similar applications. This paper presents OwlsEye, which, to the best of our knowledge, is the first hardware implementation for real-time Video Instance Segmentation under low-light settings using an off-the-shelf RGB camera. Implemented on the Intel Nezha Embedded platform, OwlsEye demonstrates an improvement in Frames Per Second (FPS) from 0.6 to 28 FPS using model weight quantization, brightness verification, and asynchronous FIFO Pipelining. This paper also presents the EQyTorch framework, an extension of Qtorch+ for fixed-posit numbers, used in weight quantization for the YOLOv8 architecture. We show that fixed-posit quantization achieves an improvement in latency and power utilization of $2.35\times, 3.6\times$ , and $9.02\times, 87.91\times$ compared to INT8 and FP32 for 65nm CMOS. Furthermore, this paper presents a synthetic DarkCOCO2017 validation dataset to test the OwlsEye segmentation performance in enhanced, original, and dark images. Our work highlights a novel real-time low-light VIS system and the potential of using Fixed-Posit quantization for edge AI applications.

关键词： Instance segmentation Quantization (signal) Image edge detection Surveillance robot vision systems Streaming media Very large scale integration Real-time systems robots Pipeline processing

来源：评论

学校读者我要写书评

暂无评论

FPGA Based Approximate Vector Operation Accelerator for VLMs

FPGA Based Approximate Vector Operation Accelerator for VLMs

引用

international conference on Electronics, Information and Communications (ICEIC)

作者： Raehyeong Kim Chaebin Lee Dayoung Lee Yue Ri Jeong Seung Eun Lee Dept. of Electronic Engineering Seoul National University of Science and Technology Seoul Republic of Korea

ISBN: (数字)9798331510756

ISBN: (纸本)9798331510763

As artificial intelligence continues to advance, the importance of autonomous robotic systems and human-robot in-teractions is growing, particularly in the areas of language-based control and behavior prediction. vision-language models (VLMs), which simultaneously process images and texts, are essential for interpreting commands and analyzing environments. However, their high computational demands, particularly for vector op-erations like softmax and layer normalization, pose significant challenges. These operations, involving complex functions such as exponentials and square roots, consume substantial resources as model sizes grow. This paper proposes a vector operation accelerator for VLMs through approximation techniques, specifically Newton-Raphson and piecewise linear approximations, to improve speed while reducing resource usage. The optimized architecture reuses resources by targeting redundant operations. Implemented on an FPGA, the accelerator achieved up to 54% faster performance compared to an RTX 3070 GPU, with minimal aproximation error.

关键词： Navigation Computational modeling Piecewise linear approximation Graphics processing units Human-robot interaction Computer architecture Vectors Newton method Field programmable gate arrays robots

来源：评论

学校读者我要写书评

暂无评论

Dual Encoders for Diffusion-based Image Inpainting

Dual Encoders for Diffusion-based Image Inpainting

引用

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

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence signal processing Diffusion models Decoding Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

Imperceptible Transfer Attack on Large vision-Language Models

Imperceptible Transfer Attack on Large Vision-Language Model...

引用

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

作者： Xiaowen Cai Daizong Liu Runwei Guan Pan Zhou School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Wangxuan Institute of Computer Technology Peking University Beijing China Department of Electrical Engineering and Electronics University of Liverpool Liverpool United Kingdom

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In spite of achieving significant progress in recent years, Large vision-Language Models (LVLMs) are proven to be vulnerable to adversarial examples. Therefore, there is an urgent need for an effective adversarial attack to identify the deficiencies of LVLMs in security-sensitive applications. However, existing LVLM attackers generally optimize adversarial samples against a specific textual prompt with a certain LVLM model, tending to overfit the target prompt/network and hardly remain malicious once they are transferred to attack a different prompt/model. To this end, in this paper, we propose a novel Imperceptible Transfer Attack (ITA) against LVLMs to generate prompt/model-agnostic adversarial samples to enhance such adversarial transferability while further improving the imperceptibility. Specifically, we learn to apply appropriate visual transformations on image inputs to create diverse input patterns by selecting the optimal combination of operations from a pool of candidates, consequently improving adversarial transferability. We conceptualize the selection of optimal transformation combinations as an adversarial learning problem and employ a gradient approximation strategy with noise budget constraints to effectively generate imperceptible transferable samples. Extensive experiments on three LVLM models and two widely used datasets with three tasks demonstrate the superior performance of our ITA.

关键词： Visualization Noise Adversarial machine learning Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Sensory Feedback Cancellation: Developing Resonator Networks to Mimic A. leptorhynchu’s Cerebellar processing of Sensory Feedback 13th

Sensory Feedback Cancellation: Developing Resonator Networks...

引用

13th international conference on Biomimetic and Biohybrid Systems, Living Machines 2024

作者： Johnson, Sheldon P. Marsat, Gary Szczecinski, Nicholas S. Neuro-Mechanical Intelligence Laboratory Department of Mechanical Materials and Aero-Space Engineering West Virginia University MorgantownWV26506 United States Department of Biology West Virginia University MorgantownWV26506 United States

ISBN: (纸本)9783031725968

Sensory feedback allows animals to read, react, and adapt to an environment. However, the sensory information received by the body could become overwhelming, thus overloading the brain. Yet, animals are able to process all this information by canceling redundant signals from their surroundings. One species in which this phenomenon has been explored is the Apteronotus leptorhynchu (brown ghost knife fish), a small electric fish that generates a bioelectric field. Sensory signals from electrical sensing organs are passed through granular cerebellar cells, which then feedback onto the primary sensory neurons to cancel low-frequency components of the sensory information. This enables the canceling of redundant sensory information and noise and makes downstream networks more sensitive to changes in sensory input. In this preliminary study, we take the first step of replicating this functionality using a series of neural resonators. Each resonator has a unique preferred frequency and then should feed back onto the sensory signal with a frequency-specific phase delay. Our resonator is a neural "differentiator" from our prior work, which amplifies frequencies up to the cutoff frequency of the network. We propose how sensory feedback cancellation could be incorporated into bioinspired robot control. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Cutoff frequency

来源：评论

学校读者我要写书评

暂无评论

Attention-Enhanced Feature Fusion Network for No-Reference Image Quality Assessment

Attention-Enhanced Feature Fusion Network for No-Reference I...

引用

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

作者： Jiliang Ma Yihua Chen Pengsheng Huang Zhenjun Tang Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of MultiSource Information Mining & Security Guangxi Normal University Guilin China Beijing MeiyiLab Co. Ltd. Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

No-Reference Image Quality Assessment (NR-IQA) is a fundamental computer vision task. In this paper, we propose a new Attention-Enhanced Feature Fusion Network for NR-IQA (AEFF-IQA) that integrates multi-scale local and non-local features. Firstly, multi-scale local and non-local features containing distortion information at semantic level are extracted by a feature extraction module consisting of two pre-trained deep neural networks. Secondly, a self-attention enhanced fusion module with four self-attention enhanced fusion components fuses the local and non-local features at the same scale to obtain multi-scale fusion features. Then, a cross-attention enhanced fusion module containing three cross-attention enhanced fusion components integrates these fusion features across multiple scales. Finally, the quality score is obtained by using a prediction module. Extensive experiments are conducted on five public datasets. The results show that our AEFF-IQA outperforms some state-of-the-art models and exhibits good generalization performance.

关键词： Image quality Computer vision Acoustic distortion Fuses Databases Semantics Artificial neural networks Feature extraction Data mining Speech processing

来源：评论

学校读者我要写书评

暂无评论

UniIVFT: Towards a Unified Framework for Infrared-Visible Fusion and Translation

UniIVFT: Towards a Unified Framework for Infrared-Visible Fu...

引用

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

作者： Honglin Wu Xueqiong Li Shaowu Yang Huibin Tan Yuhua Tang Tianrui Liu College of Computer Science and Technology National University of Defense Technology

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Infrared-visible image fusion (IVF) and infrared-to-visible image translation (I2V) are two closely related tasks in multimodal image processing, both aimed at combining or transforming infrared and visible modalities to enhance image information content. Existing methods typically focus on either fusion or translation, often requiring redundant construction of similar components for each task, which limits the effective utilization of cross-modal interactions and feature encoding capabilities. Furthermore, these approaches are often hindered by their reliance on complex feature extract models, limiting their overall effectiveness and adaptability. In this paper, we introduce the Unified Multimodal Infrared-Visible Image Fusion and Translation (UniIVFT) framework, which integrates both fusion and translation tasks within a single architecture. We employ a vision transformer (ViT) encoder-decoder structure augmented with task-specific tokens and introduce a contrastive loss to effectively align infrared and visible image features before multimodal encoding. This alignment enhances the encoder’s ability to capture cross-modal interactions. In UniIVFT, both IVF and I2V tasks share a unified encoder architecture and use task-specific tokens to control model outputs, reducing redundant model construction and training. Extensive experiments demonstrate that UniIVFT achieves performance on par with that of SOTAs across multiple tasks while maintaining a lightweight architecture with fewer model parameters.

关键词： Training Computer vision Translation Image coding Limiting Transformers Feature extraction Usability Speech processing Image fusion

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 << < 30 31 32 33 34 35 36 37 38 39 > >>

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：