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

204 篇 期刊文献
170 篇 会议

馆藏范围

374 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

235 篇 工学
- 192 篇 计算机科学与技术...
- 168 篇 软件工程
- 49 篇 信息与通信工程
- 29 篇 控制科学与工程
- 22 篇 光学工程
- 18 篇 机械工程
- 16 篇 建筑学
- 16 篇 土木工程
- 15 篇 网络空间安全
- 13 篇 电气工程
- 11 篇 电子科学与技术（可...
- 11 篇 测绘科学与技术
- 11 篇 生物工程
- 10 篇 化学工程与技术
- 8 篇 安全科学与工程
- 6 篇 交通运输工程
- 6 篇 生物医学工程（可授...
- 5 篇 仪器科学与技术
- 4 篇 动力工程及工程热...
76 篇 管理学
- 43 篇 图书情报与档案管...
- 40 篇 管理科学与工程(可...
- 8 篇 工商管理
67 篇 理学
- 35 篇 数学
- 17 篇 统计学（可授理学、...
- 12 篇 物理学
- 12 篇 生物学
- 10 篇 化学
4 篇 经济学
- 4 篇 应用经济学
4 篇 法学
- 4 篇 社会学
- 3 篇 法学
2 篇 农学
2 篇 医学
1 篇 教育学

主题

15 篇 semantics
12 篇 image segmentati...
10 篇 training
9 篇 reinforcement le...
9 篇 contrastive lear...
8 篇 visual languages
7 篇 speech processin...
7 篇 convolution
7 篇 computer vision
7 篇 image reconstruc...
6 篇 semantic segment...
6 篇 distillation
6 篇 visualization
6 篇 pipelines
5 篇 costs
5 篇 benchmarking
5 篇 codes
4 篇 object detection
4 篇 signal processin...
4 篇 redundancy

机构

214 篇 key laboratory o...
62 篇 institute of art...
40 篇 key laboratory o...
36 篇 tencent youtu la...
33 篇 peng cheng labor...
32 篇 school of inform...
25 篇 key laboratory o...
22 篇 fujian key labor...
20 篇 fujian key labor...
18 篇 youtu lab tencen...
17 篇 key laboratory o...
10 篇 school of inform...
10 篇 national univers...
8 篇 tencent
8 篇 skywork ai
8 篇 school of comput...
8 篇 the key laborato...
8 篇 department of ar...
7 篇 key laboratory o...
6 篇 department of co...

作者

152 篇 ji rongrong
67 篇 sun xiaoshuai
49 篇 rongrong ji
40 篇 cao liujuan
37 篇 ji jiayi
30 篇 zhou yiyi
30 篇 zhang shengchuan
28 篇 wang cheng
25 篇 ma yiwei
24 篇 zhang yuxin
24 篇 zheng xiawu
22 篇 chao fei
19 篇 luo gen
18 篇 lin mingbao
18 篇 zhang yan
17 篇 xiaoshuai sun
16 篇 wang haowei
15 篇 shen yunhang
15 篇 jiang guannan
15 篇 li hui

语言

318 篇 英文
56 篇 其他

检索条件"机构=Key Laboratory of Multimedia Trusted Perception and Efficient Computing"

共 374 条记录，以下是11-20 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：

efficient Perceiving Local Details via Adaptive Spatial-Frequency Information Integration for Multi-focus Image Fusion 24

Efficient Perceiving Local Details via Adaptive Spatial-Freq...

引用

32nd ACM International Conference on multimedia, MM 2024

作者： Huang, Jingjia Tu, Jingyan Meng, Ge Wang, Yingying Dong, Yuhang Tu, Xiaotong Ding, Xinghao Huang, Yue School of Informatics Xiamen University Xiamen China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen University Xiamen China

ISBN: (纸本)9798400706868

Multi-focus image fusion (MFIF) aims to combine multiple images with different focused regions into a single all-in-focus image. Existing unsupervised deep learning-based methods only fuse structural information of images in the spatial domain, neglecting potential solutions from the frequency domain exploration. In this paper, we make the first attempt to integrate spatial-frequency information to achieve high-quality MFIF. We propose a novel unsupervised spatial-frequency interaction MFIF network named SFIMFN, which consists of three key components: Adaptive Frequency Domain Information Interaction Module (AFIM), Ret-Attention-Based Spatial Information Extraction Module (RASEM), and Invertible Dual-domain Feature Fusion Module (IDFM). Specifically, in AFIM, we interactively explore global contextual information by combining the amplitude and phase information of multiple images separately. In RASEM, we design a customized transformer to encourage the network to capture important local high-frequency information by redesigning the self-attention mechanism with a bidirectional, two-dimensional form of explicit decay. Finally, we employ IDFM to fuse spatial-frequency information without information loss to generate the desired all-in-focus image. Extensive experiments on different datasets demonstrate that our method significantly outperforms state-of-the-art unsupervised methods in terms of qualitative and quantitative metrics as well as the generalization ability. © 2024 ACM.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Prompt-Enhanced Software Vulnerability Detection Using ChatGPT 24

Prompt-Enhanced Software Vulnerability Detection Using ChatG...

引用

46th International Conference on Software Engineering: Companion, ICSE-Companion 2024

作者： Zhang, Chenyuan Liu, Hao Zeng, Jiutian Yang, Kejing Li, Yuhong Li, Hui Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Alibaba China

ISBN: (纸本)9798400705021

With the increase in software vulnerabilities that cause significant economic and social losses, automatic vulnerability detection has become essential in software development and maintenance. Recently, large language models (LLMs) have received considerable attention due to their stunning intelligence, and some studies consider using ChatGPT for vulnerability detection. However, they do not fully consider the characteristics of LLMs, since their designed questions to ChatGPT are simple without a prompt design tailored for vulnerability detection. This paper launches a study on the performance of software vulnerability detection using ChatGPT with different prompt designs. Firstly, we complement previous work by applying various improvements to the basic prompt. Moreover, we incorporate structural and sequential auxiliary information to improve the prompt design. Moreover, we leverage ChatGPT's ability of memorizing multi-round dialogue to design suitable prompts for vulnerability detection. We conduct extensive experiments on two vulnerability datasets to demonstrate the effectiveness of promptenhanced vulnerability detection using ChatGPT. © 2024 IEEE Computer Society. All rights reserved.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Robustness-Enhanced Data-Free Quantization for Vision Transformer 24

Robustness-Enhanced Data-Free Quantization for Vision Transf...

引用

9th International Conference on Cyber Security and Information Engineering, ICCSIE 2024

作者： Zhou, Yuyao Chao, Fei Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Informatics Xiamen University China

ISBN: (纸本)9798400718137

Transformer has been a huge success in computer vision tasks, but its complex architecture and huge computational overhead limit the application of Vision Transformer (ViT) on edge devices. Recently, some works have focused on the field of data-free quantization of ViTs with good results. However, as they ignore the properties of ViT’s non-smooth loss landscape, it leads to a quantization model that is susceptible to small perturbations. This paper proposes RE-ViT, a robustness-enhanced data-free quantization method for ViTs. RE-ViT utilizes Image Robustness Enhancement, which does interference with the input during data generation, to obtain synthetic samples with high semanticity and robustness. In the model quantization stage, contrast learning is introduced to alleviate the non-smooth loss landscape phenomenon of ViTs. A large number of experiments demonstrate the effectiveness of RE-ViT and it is shown to be superior to State-of-the-Art. RE-ViT establishes a new baseline for data-free quantization of ViTs. © 2024 Copyright held by the owner/author(s).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for efficient Adaptation 24

Advancing Multimodal Large Language Models with Quantization...

引用

32nd ACM International Conference on multimedia, MM 2024

作者： Xie, Jingjing Zhang, Yuxin Lin, Mingbao Cao, Liujuan Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen China SkyWork AI Singapore Singapore

ISBN: (纸本)9798400706868

This paper presents the first study to explore the potential of parameter quantization for multimodal large language models to alleviate the significant resource constraint encountered during vision-language instruction tuning. We introduce a Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW. This method is grounded in two key innovations: (1) The learning of group-wise scale factors for quantized LLM weights to mitigate the quantization error arising from activation outliers and achieve more effective vision-language instruction tuning;(2) The implementation of a multimodal warmup that progressively integrates linguistic and multimodal training samples, thereby preventing overfitting of the quantized model to multimodal data while ensuring stable adaptation of multimodal large language models to downstream vision-language tasks. Extensive experiments demonstrate that models quantized by QSLAW perform on par with, or even surpass, their full-precision counterparts, while facilitating up to 1.4 times reduction in VL tuning time and GPU consumption. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification 38

RLE: A Unified Perspective of Data Augmentation for Cross-Sp...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lei, Tan Zhang, Yukang Han, Keke Dai, Pingyang Zhang, Yan Wu, Yongjian Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University 361005 China Tencent Youtu Lab China

This paper makes a step towards modeling the modality discrepancy in the cross-spectral re-identification task. Based on the Lambertain model, we observe that the non-linear modality discrepancy mainly comes from diverse linear transformations acting on the surface of different materials. From this view, we unify all data augmentation strategies for cross-spectral re-identification by mimicking such local linear transformations and categorizing them into moderate transformation and radical transformation. By extending the observation, we propose a Random Linear Enhancement (RLE) strategy which includes Moderate Random Linear Enhancement (MRLE) and Radical Random Linear Enhancement (RRLE) to push the boundaries of both types of transformation. Moderate Random Linear Enhancement is designed to provide diverse image transformations that satisfy the original linear correlations under constrained conditions, whereas Radical Random Linear Enhancement seeks to generate local linear transformations directly without relying on external information. The experimental results not only demonstrate the superiority and effectiveness of RLE but also confirm its great potential as a general-purpose data augmentation for cross-spectral re-identification. The code is available at https://***/stone96123/RLE. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

QueryMatch: A Query-based Contrastive Learning Framework for Weakly Supervised Visual Grounding 24

QueryMatch: A Query-based Contrastive Learning Framework for...

引用

32nd ACM International Conference on multimedia, MM 2024

作者： Chen, Shengxin Luo, Gen Zhou, Yiyi Sun, Xiaoshuai Jiang, Guannan Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Fujian Xiamen China Fujian Ningde China

ISBN: (纸本)9798400706868

Visual grounding is a task of locating the object referred by a natural language description. To reduce annotation costs, recent researchers are devoted into one-stage weakly supervised methods for visual grounding, which typically adopt the anchor-text matching paradigm. Despite the efficiency, we identify that anchor representations are often noisy and insufficient to describe object information, which inevitably hinders the vision-language alignments. In this paper, we propose a novel query-based one-stage framework for weakly supervised visual grounding, namely QueryMatch. Different from previous work, QueryMatch represents candidate objects with a set of query features, which inherently establish accurate one-to-one associations with visual objects. In this case, QueryMatch re-formulates weakly supervised visual grounding as a query-text matching problem, which can be optimized via the query-based contrastive learning. Based on QueryMatch, we further propose an innovative strategy for effective weakly supervised learning, namely Active Query Selection (AQS). In particular, AQS aims to enhance the effectiveness of query-based contrastive learning by actively selecting high-quality query features. Through this strategy, AQS can greatly benefit the weakly supervised learning of QueryMatch. To validate our approach, we conduct extensive experiments on three benchmark datasets of two grounding tasks, i.e., referring expression comprehension (REC) and segmentation (RES). Experimental results not only show the state-of-art performance of QueryMatch in two tasks, e.g., over +5% IoU@0.5 on RefCOCO in REC and over +20% mIOU on RefCOCO in RES, but also confirm the effectiveness of AQS in weakly supervised learning. Source codes are available at https://***/TensorThinker/QueryMatch. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Designing Quantizers for Low-Precision Post-Training Quantization: A Standard Pipeline Approach for CNNs 24

Designing Quantizers for Low-Precision Post-Training Quantiz...

引用

9th International Conference on Cyber Security and Information Engineering, ICCSIE 2024

作者： Yang, Xiao Chao, Fei Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Informatics Xiamen University China

ISBN: (纸本)9798400718137

Quantization is a widely adopted technique for enhancing the inference performance of neural networks by exploiting hardware support for low-precision algorithms. It offers significant advantages such as higher throughput, reduced memory traffic, and decreased storage requirements. Neural networks have demonstrated robustness to quantization, allowing them to be quantized to lower bit widths with minimal impact on accuracy. However, the quantization process often leads to a loss in precision, especially when performed without retraining. Addressing this issue, this paper focuses on the design of quantizers for low-precision post-training quantization tasks, aiming to minimize accuracy loss without the need for access to the full training dataset or extensive computational resources. We propose a novel approach that introduces outlier clipping for weights and designs bias correction schemes for both weights and activations. Our methodology emphasizes the development of a standard pipeline for low-precision post-training quantization, which balances simplicity and performance. Through comprehensive experiments, we demonstrate that our proposed pipeline achieves superior accuracy compared to many existing post-training quantization methods. This work contributes to the ongoing efforts in the field by providing a practical and efficient solution for quantizing convolutional neural networks (CNNs) in low-precision scenarios. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric Regularization 41

Fast Text-to-3D-Aware Face Generation and Manipulation via D...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Jinlu Zhou, Yiyi Zheng, Qiancheng Du, Xiaoxiong Luo, Gen Peng, Jun Sun, Xiaoshuai Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University 361005 China Peng Cheng Laboratory Shenzhen518000 China

Text-to-3D-aware face (T3D Face) generation and manipulation is an emerging research hot spot in machine learning, which still suffers from low efficiency and poor *** this paper, we propose an End-to-End efficient and Effective network for fast and accurate T3D face generation and manipulation, termed *** from existing complex generation paradigms, E3-FaceNet resorts to a direct mapping from text instructions to 3D-aware visual *** introduce a novel Style Code Enhancer to enhance cross-modal semantic alignment, alongside an innovative Geometric Regularization objective to maintain consistency across multi-view *** experiments on three benchmark datasets demonstrate that E3-FaceNet can not only achieve picture-like 3D face generation and manipulation, but also improve inference speed by orders of *** instance, compared with Latent3D, E3-FaceNet speeds up the five-view generations by almost 470 times, while still exceeding in generation *** code is released at https://***/Aria-Zhangjl/E3-FaceNet. Copyright 2024 by the author(s)

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Intelligent Urban Emergency Response: Integrating Large Language Models, Multi-Objective Optimization, and Reinforcement Learning 10

Intelligent Urban Emergency Response: Integrating Large Lang...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Chen, Siyao Luo, Guofeng Chen, Longbiao Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart Cities 361005 China Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China 361005 China

ISBN: (纸本)9798331520861

Urban emergency response plays a critical role in protecting lives and property during crises. However, traditional emergency response systems often struggle with inefficient resource allocation, uncoordinated relief efforts, and delayed decision-making. To address these challenges, we propose a novel intelligent decision-making framework that integrates large language models for victim interaction, multi-objective optimization for resource allocation, and reinforcement learning for personalized dispatch. Our approach consists of three main components: an intelligent voice assistant that engages in human-like conversations with victims, a multi-objective optimization model (ERMOO) for efficient resource allocation, and a Deep Q-Networks (DQN) based reinforcement learning approach for personalized dispatch policies. Extensive experiments on both synthetic and real-world datasets demonstrate the superior performance of our approach compared to existing baselines. The results highlight the immense potential of integrating cutting-edge AI techniques to revolutionize urban emergency response practices. By bridging the gap between artificial intelligence and human intelligence, our framework provides a solid foundation for creating more resilient, equitable, and human-centered emergency management systems. This work aims to inspire further research and innovation in this critical domain, ultimately benefiting urban societies worldwide. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models 38

ControlMLLM: Training-Free Visual Prompt Learning for Multim...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wu, Mingrui Cai, Xinyue Ji, Jiayi Li, Jiale Huang, Oucheng Luo, Gen Fei, Hao Jiang, Guannan Sun, Xiaoshuai Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University 361005 China National University of Singapore Singapore CATL Canada

In this work, we propose a training-free method to inject visual prompts into Multimodal Large Language Models (MLLMs) through learnable latent variable optimization. We observe that attention, as the core module of MLLMs, connects text prompt tokens and visual tokens, ultimately determining the final results. Our approach involves adjusting visual tokens from the MLP output during inference, controlling the attention response to ensure text prompt tokens attend to visual tokens in referring regions. We optimize a learnable latent variable based on an energy function, enhancing the strength of referring regions in the attention map. This enables detailed region description and reasoning without the need for substantial training costs or model retraining. Our method offers a promising direction for integrating referring abilities into MLLMs, and supports referring with box, mask, scribble and point. The results demonstrate that our method exhibits out-of-domain generalization and interpretability. Code: https://***/mrwu-mac/ControlMLLM. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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38页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：