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

6,828 篇 会议
93 篇 期刊文献
35 册 图书

馆藏范围

6,956 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,709 篇 工学
- 2,625 篇 计算机科学与技术...
- 1,558 篇 信息与通信工程
- 1,371 篇 软件工程
- 949 篇 电气工程
- 474 篇 光学工程
- 352 篇 控制科学与工程
- 244 篇 生物工程
- 231 篇 电子科学与技术（可...
- 207 篇 生物医学工程（可授...
- 175 篇 网络空间安全
- 134 篇 机械工程
- 108 篇 仪器科学与技术
- 95 篇 安全科学与工程
- 91 篇 材料科学与工程（可...
- 84 篇 化学工程与技术
- 84 篇 交通运输工程
- 72 篇 建筑学
- 72 篇 土木工程
- 68 篇 动力工程及工程热...
1,375 篇 理学
- 869 篇 物理学
- 419 篇 数学
- 263 篇 生物学
- 101 篇 统计学（可授理学、...
- 76 篇 化学
1,148 篇 医学
- 1,119 篇 临床医学
- 86 篇 基础医学(可授医学...
494 篇 管理学
- 267 篇 图书情报与档案管...
- 253 篇 管理科学与工程(可...
- 60 篇 工商管理
70 篇 法学
- 65 篇 社会学
29 篇 农学
25 篇 经济学
24 篇 教育学
23 篇 文学
17 篇 军事学
1 篇 艺术学

主题

1,018 篇 visualization
575 篇 image processing
518 篇 image coding
486 篇 feature extracti...
425 篇 deep learning
407 篇 image segmentati...
384 篇 accuracy
364 篇 visual communica...
346 篇 training
250 篇 computational mo...
229 篇 image enhancemen...
226 篇 signal processin...
186 篇 image edge detec...
184 篇 image color anal...
174 篇 image reconstruc...
169 篇 convolutional ne...
164 篇 real-time system...
160 篇 three-dimensiona...
160 篇 semantics
159 篇 image recognitio...

机构

43 篇 shanghai jiao to...
35 篇 institute of ima...
29 篇 shanghai jiao to...
28 篇 university of sc...
28 篇 beijing universi...
26 篇 school of electr...
17 篇 university of el...
16 篇 shanghai jiao to...
16 篇 tianjin univ sch...
15 篇 university of ch...
14 篇 shanghai jiao to...
13 篇 zhejiang univers...
13 篇 peng cheng labor...
13 篇 moscow technical...
13 篇 school of commun...
12 篇 univ sci & techn...
12 篇 tsinghua univ de...
11 篇 school of remote...
11 篇 school of electr...
11 篇 peking universit...

作者

42 篇 zhai guangtao
27 篇 song li
27 篇 sumei li
26 篇 guangtao zhai
25 篇 andré kaup
22 篇 li sumei
20 篇 li li
18 篇 li song
18 篇 min xiongkuo
17 篇 xiongkuo min
17 篇 dong liu
14 篇 chen zhibo
14 篇 xie rong
12 篇 yang yang
12 篇 shan liu
11 篇 liu dong
11 篇 jürgen seiler
11 篇 heming sun
11 篇 chen chen
11 篇 li chen

语言

6,689 篇 英文
203 篇 其他
127 篇 中文
50 篇 土耳其文

检索条件"任意字段=2024 Conference on Visual Communications and Image Processing"

共 6956 条记录，以下是291-300 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：

Coarse-to-fine Transformer For Lossless 3D Medical image Compression

Coarse-to-fine Transformer For Lossless 3D Medical Image Com...

引用

2024 conference on visual communications and image processing

作者： Yang, Xiaoxuan Lui, Guo Feng, Donghui Cheng, Zhengxue Yu, Guosheng Song, Li Shanghai Jiao Tong Univ Shanghai Peoples R China Alibaba Grp T Head Semicond Co Ltd Hangzhou Peoples R China

ISBN: (纸本)9798331529543;9798331529550

The rapid advancements in medical imaging have led to a growing demand for high-performance lossless compression of large 3D medical image datasets. Unlike natural images, medical images typically feature three-dimensional structures, and high bit-depth, necessitating specialized compression techniques. Based on a decoder-only transformer, we propose a learnable dual-decoder model for lossless compression of 3D medical images. Our approach packs voxels into patches, which are processed by a patch-level decoder to extract the patch feature. The voxels, along with the patch feature, are subsequently fed into a voxel-level decoder to model each voxel. This coarse-to-fine modeling strategy reduces the computational time for each voxel and enables long-range modeling dependencies. Experimental results demonstrate that our proposed model achieves state-of-the-art compression performance, with an approximately 15% improvement in compression performance over the traditional JP3D benchmark on various datasets.

关键词： Lossless image Compression Medical image Transformer

来源：评论

学校读者我要写书评

暂无评论

image Forensics Strikes Back: Defense Against Adversarial Patch

Image Forensics Strikes Back: Defense Against Adversarial Pa...

引用

2024 conference on visual communications and image processing

作者： Kao, Ching-Chia Lu, Chun-Shien Yu, Chia-Mu Acad Sinica Inst Informat Sci IIS Taipei Taiwan Natl Taiwan Univ Taipei Taiwan Natl Yang Ming Chiao Tung Univ Hsinchu Taiwan

ISBN: (纸本)9798331529543;9798331529550

Traffic sign recognition plays a crucial role in self-driving cars, but unfortunately, it is vulnerable to adversarial patches (AP). Although AP can efficiently fool DNN-based models in previous studies, the connection between image forensics and AP detection still needs to be explored. From a high-level point of view, their goals are the same. That is to find tampered regions and prevent false positives in the meantime. A natural question arises: "Is achieving application-agnostic anomaly detection possible?" In this paper, we propose image Forensics Defense Against Adversarial Patch (IDAP), a framework to defend against adversarial patches via generalizable features learned from tampered images. In addition, we incorporate the Hausdorff erosion loss into our network model for joint training to complete the shape of a predicted mask. Extensive experimental comparisons on three datasets, including COCO, DFG, and APRICOT demonstrate that IDAP outperforms state-of-the-art AP detection methods.

关键词： Adversarial Patch AI Security image Forensics

来源：评论

学校读者我要写书评

暂无评论

Frequency-Aware Hierarchical image Compression for Humans and Machines

Frequency-Aware Hierarchical Image Compression for Humans an...

引用

2024 conference on visual communications and image processing

作者： Luo, Yue Zhang, Zixiang Kuang, Jinhao Yu, Li Huazhong Univ Sci & Technol Wuhan Peoples R China Huazhong Univ Sci & Technol Shenzhen Res Inst Shenzhen Peoples R China

ISBN: (纸本)9798331529543;9798331529550

To achieve efficient compression for both human vision and machine perception, scalable coding methods have been proposed in recent years. However, existing methods do not fully eliminate the redundancy between features corresponding to different tasks, resulting in suboptimal coding performance. In this paper, we propose a frequency-aware hierarchical image compression framework designed for humans and machines. Specifically, we investigate task relationships from a frequency perspective, utilizing only HF information for machine vision tasks and leveraging both HF and LF features for image reconstruction. Besides, the residual block embedded octave convolution module is designed to enhance the information interaction between HF features and LF features. Additionally, a dual-frequency channel-wise entropy model is applied to reasonably exploit the correlation between different tasks, thereby improving multi-task performance. The experiments show that the proposed method offers -69.3%similar to-75.3% coding gains on machine vision tasks compared to the relevant benchmarks, and -19.1% gains over state-of-the-art scalable image codec in terms of image reconstruction quality.

关键词： scalable image coding image coding for machines learned image compression

来源：评论

学校读者我要写书评

暂无评论

AsymLLIC: Asymmetric Lightweight Learned image Compression

AsymLLIC: Asymmetric Lightweight Learned Image Compression

引用

2024 conference on visual communications and image processing

作者： Wang, Shen Cheng, Zhengxue Feng, Donghui Lu, Guo Song, Li Zhang, Wenjun Shanghai Jiao Tong Univ Dept Elect Engn Shanghai Peoples R China

ISBN: (纸本)9798331529543;9798331529550

Learned image compression (LIC) methods often employ symmetrical encoder and decoder architectures, evitably increasing decoding time. However, practical scenarios demand an asymmetric design, where the decoder requires low complexity to cater to diverse low-end devices, while the encoder can accommodate higher complexity to improve coding performance. In this paper, we propose an asymmetric lightweight learned image compression (AsymLLIC) architecture with a novel training scheme, enabling the gradual substitution of complex decoding modules with simpler ones. Building upon this approach, we conduct a comprehensive comparison of different decoder network structures to strike a better trade-off between complexity and compression performance. Experiment results validate the efficiency of our proposed method, which not only achieves comparable performance to VVC but also offers a lightweight decoder with only 51.47 GMACs computation and 19.65M parameters. Furthermore, this design methodology can be easily applied to any LIC models, enabling the practical deployment of LIC techniques.

关键词： Learned image compression neural network lightweight asymmetric

来源：评论

学校读者我要写书评

暂无评论

2nd CSIG conference on Emotional Intelligence, CEI 2024

2nd CSIG Conference on Emotional Intelligence, CEI 2024

引用

2nd CSIG conference on Emotional Intelligence, CEI 2024

ISBN: (纸本)9789819650835

The proceedings contain 16 papers. The special focus in this conference is on Emotional Intelligence. The topics include: EIDA: Explicit and Implicit-Space Self-supervised Learning for visual Emotion Adaptation;a Three Streams Convolutional Transformer Fusion Model for Facial Macro- and Micro-expressions Spotting;facial Action Unit Recognition with Micro-Action-Aware Transformer;local and Global Iterative Adaptation Based on Meta Learning for Source-Free Cross-Corpus Speech Emotion Recognition;decoupled Representation with Multimodal Prompts for Emotion Recognition in Conversation;generative Text Prompts for image Aesthetic Quality Assessment;large Language Model Enhanced Fuzzy Logic Fusion Framework for Stance Detection;skeleton-Based Online Action Detection with Temporal Enhancement;fine-Grained Spatial-Temporal Framework for Engagement Prediction;Multimodal Engagement Recognition by Fusing Transformer and Bi-LSTM;emotional Interaction Hardware Design for Wrist Rehabilitation Based on Secondary Fuzzy Reasoning;attention-Based Audio Depression Recognition Integrating Handcrafted and Deep Features;STC-ND: Leveraging Spatiotemporal Characteristics with NeXtVLAD for Depression Detection from Few-Channel EEG Signals;DepLLM: Fine-Tuning Large Language Models with a Chinese Dialogue Dataset for Depression Diagnosis via Mixture of Specialized Experts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Proposed Model to Transliterate Digitalized Braille Text into Gujarati: An Aid for visually Challenged People 3rd

A Proposed Model to Transliterate Digitalized Braille Text i...

引用

3rd International conference on Advancements in Smart Computing and Information Security, ASCIS 2024

作者： Jariwala, Nikisha Popat, Kalpesh Smt. Tanuben & Dr. Manubhai Trivedi College of Information Science Affiliated to Veer Narmad South Gujarat University Gujarat Surat India Faculty of Computer Applications Marwadi University Gujarat Rajkot India

ISBN: (纸本)9783031863011

Information and Communication Technology (ICT), in the modern digital era has become so cutting-edge and touched to each and every field but there is still a disconnect between visually impaired persons and communication technologies because of ignorance and inattention. Due to the limited availability of resources and tools;people with visual impairments are unable to communicate in writing. In this paper, researcher has tried to draw the attention towards the challenges that are faced by visually impaired individuals in written communication and also discussed the benefits of having a tool that eradicate the communication gap. To overcome the challenges faced by blind people;author has proposed a model based on Natural Language processing (NLP) and character mapping technique that act as an aid to transliterate the Braille text written by blind people to our regional language Gujarati. The technique used in the model uses standard Braille syntax. Rules are formed, lookup table is created, Braille characters are identified and they are transliterated to Gujarati language text. The model shows satisfactory result in the transliteration of Braille characters to Gujarati. It will also help visually impaired students in their education. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Intra Block Copy Prediction for Plenoptic 2.0 Video Coding under Macropixel Constraints

Enhancing Intra Block Copy Prediction for Plenoptic 2.0 Vide...

引用

2024 conference on visual communications and image processing

作者： Vinh Van Duong Thuc Nguyen Huu Yim, Jonghoon Jeon, Byeungwoo Sungkyunkwan Univ Dept Elect & Comp Engn Seoul South Korea Samsung Res Seoul South Korea

ISBN: (纸本)9798331529543;9798331529550

In this paper we introduce a novel approach to better utilize the intra block copy (IBC) prediction tool in encoding lenslet light field video (LFV) captured using plenoptic 2.0 cameras. Although the IBC tool has been recognized as promising for encoding LFV content, its fundamental limit due to its original design rooted for encoding conventional videos suggests slight modification possibility to better suit the property of LFV content. Observing the inherently large amount of repetitive image patterns due to the microlens array (MLA) structure of plenoptic cameras, several techniques are suggested in this paper to enhance the IBC coding tool itself for more efficiently encoding LFV contents. Our experimental results demonstrate that the proposed method significantly enhances the IBC coding performance in case of encoding LFV contents while concurrently reducing encoding time.

关键词： Light field plenoptic video coding fast motion estimation video coding microlens image

来源：评论

学校读者我要写书评

暂无评论

FRIDAY: Mitigating Unintentional Facial Identity in Deepfake Detectors Guided by Facial Recognizers

FRIDAY: Mitigating Unintentional Facial Identity in Deepfake...

引用

2024 conference on visual communications and image processing

作者： Kim, Younghun Kwon, Myung-Joon Lee, Wonjun Kim, Changick Korea Adv Inst Sci & Technol Grad Sch Green Growth & Sustainabil Daejeon South Korea Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon South Korea

ISBN: (纸本)9798331529543;9798331529550

Previous Deepfake detection methods perform well within their training domains, but their effectiveness diminishes significantly with new synthesis techniques. Recent studies have revealed that detection models make decision boundaries based on facial identity instead of synthetic artifacts, leading to poor cross-domain performance. To address this issue, we propose FRIDAY, a novel training method that attenuates facial identity utilizing a face recognizer. To be specific, we first train a face recognizer using the same backbone as the Deepfake detector. We then freeze the recognizer and use it during the detector's training to mitigate facial identity information. This is achieved by feeding input images into both the recognizer and the detector, then minimizing the similarity of their feature embeddings using our Facial Identity Attenuating loss. This process encourages the detector to produce embeddings distinct from the recognizer, effectively attenuating facial identity. Comprehensive experiments demonstrate that our approach significantly improves detection performance on both in-domain and cross-domain datasets.

关键词： Deepfake Detection Unintentional Facial Identity Face Recognition image Forensics

来源：评论

学校读者我要写书评

暂无评论

Variable Bitrate Models For Learned image Compression with Multi-gain units and Weighted Probability Assignment

Variable Bitrate Models For Learned Image Compression with M...

引用

2024 conference on visual communications and image processing

作者： Wang, Ran Jiang, Wen Sun, Heming Katto, Jiro Waseda Univ Dept Comp Sci & Commun Engn Tokyo Japan Yokohama Natl Univ Fac Engn Yokohama Kanagawa Japan Waseda Univ Waseda Res Inst Sci & Engn Dept Comp Sci & Commun Engn Tokyo Japan

ISBN: (纸本)9798331529543;9798331529550

With the advancement of deep learning techniques, learned image compression (LIC) has surpassed traditional compression methods. However, these methods typically require training separate models to achieve optimal rate-distortion performance, leading to increased time and resource consumption. To tackle this challenge, we propose leveraging multi-gain and inverse multi-gain unit pairs to enable variable rate adaptation within a single model. Nevertheless, experiments have shown that rate-distortion performance may degrade at certain bitrates. Therefore, we introduce weighted probability assignment, where different selection probabilities are assigned during training based on lambda values, to increase the model's training frequency under specific bitrate conditions. To validate our approach, extensive experiments were conducted on Transformer-based and CNN-based models. The experimental results validate the efficiency of our proposed method.

关键词： Learned image compression variable rate multigain units weighted probability assignment

来源：评论

学校读者我要写书评

暂无评论

Efficient Bitrate Ladder Construction for Per-Shot Adaptive Encoding

Efficient Bitrate Ladder Construction for Per-Shot Adaptive ...

引用

2024 conference on visual communications and image processing

作者： Zhao, Yan Cheng, ZhengXue Lu, Guo Xie, Rong Song, Li Shanghai Jiao Tong Univ Inst Image Commun & Network Engn Shanghai Peoples R China

ISBN: (纸本)9798331529543;9798331529550

HTTP adaptive streaming (HAS) constructs bitrate ladders to deliver videos with the best possible quality under varying network conditions. Though per-shot content adaptive encoding (CAE) largely improves the compression efficiency by constructing the optimal bitrate ladder for each video shot, it suffers from excessive encoding complexity as all the points in the operating space (typically resolution x bitrate) need to be encoded and compared. To address this issue, this paper proposes an efficient bitrate ladder construction method that encodes only a subset of operating points, then uses curve fitting and inter-curve prediction to estimate other points' RD performance. The proposed method enables low-complexity ladder construction even for high-dimension operating spaces that incorporate dimensions like encoding presets. Experiments show that this method can achieve RD performance comparable to the original per-shot CAE with only 42% encoding points. Even when minimizing the encoding points to 3.6% of the original CAE, it achieves 15% BDRate improvements compared to using the fixed bitrate ladder.

关键词： Content-adaptive encoding per-shot encoding bitrate ladder prediction adaptive streaming

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 << < 26 27 28 29 30 31 32 33 34 35 > >>

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：