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

245 篇 会议
80 篇 期刊文献
2 册 图书

馆藏范围

327 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

178 篇 工学
- 130 篇 计算机科学与技术...
- 104 篇 软件工程
- 45 篇 信息与通信工程
- 23 篇 控制科学与工程
- 20 篇 电子科学与技术（可...
- 18 篇 电气工程
- 17 篇 生物工程
- 12 篇 光学工程
- 12 篇 仪器科学与技术
- 10 篇 机械工程
- 10 篇 动力工程及工程热...
- 9 篇 生物医学工程（可授...
- 6 篇 交通运输工程
- 4 篇 安全科学与工程
- 3 篇 材料科学与工程（可...
- 3 篇 化学工程与技术
70 篇 理学
- 36 篇 数学
- 20 篇 物理学
- 17 篇 生物学
- 9 篇 系统科学
- 9 篇 统计学（可授理学、...
- 4 篇 化学
- 3 篇 地球物理学
56 篇 管理学
- 30 篇 图书情报与档案管...
- 29 篇 管理科学与工程(可...
- 12 篇 工商管理
12 篇 医学
- 11 篇 临床医学
- 8 篇 基础医学(可授医学...
- 6 篇 公共卫生与预防医...
6 篇 法学
- 4 篇 社会学
3 篇 农学
2 篇 经济学
2 篇 艺术学
1 篇 教育学
1 篇 文学

主题

27 篇 computer science
23 篇 web services
15 篇 training
11 篇 optimization
11 篇 computational mo...
9 篇 quality of servi...
9 篇 semantics
9 篇 algorithm design...
8 篇 feature extracti...
8 篇 accuracy
7 篇 deep learning
7 篇 image segmentati...
7 篇 wireless sensor ...
7 篇 predictive model...
7 篇 benchmark testin...
7 篇 costs
7 篇 hardware
7 篇 robustness
6 篇 reinforcement le...
6 篇 memory managemen...

机构

60 篇 department of co...
48 篇 department of co...
38 篇 school of comput...
29 篇 school of comput...
27 篇 department of co...
17 篇 joint research l...
14 篇 joint research l...
14 篇 joint research l...
13 篇 department of co...
9 篇 school of comput...
8 篇 university of sc...
8 篇 anhui university...
7 篇 school of comput...
7 篇 school of data s...
7 篇 department of co...
6 篇 linke lab school...
6 篇 ustc-cityu joint...
6 篇 joint research l...
6 篇 school of softwa...
6 篇 suzhou institute...

作者

21 篇 qing li
19 篇 li qing
18 篇 xuehai zhou
14 篇 chen enhong
14 篇 xi li
14 篇 gu naijie
12 篇 ke tang
10 篇 liu an
10 篇 an liu
10 篇 naijie gu
9 篇 zhou xuehai
8 篇 chao wang
8 篇 wenyin liu
7 篇 hu dawei
7 篇 liusheng huang
7 篇 huang liusheng
7 篇 liu wenyin
7 篇 shi jun
7 篇 gangyong jia
7 篇 enhong chen

语言

300 篇 英文
15 篇 其他
12 篇 中文

检索条件"机构=Computer Science and Technology USTC"

共 327 条记录，以下是1-10 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：

DiffST: High-Level Style Feature Transfer Via Diffusion Models 3

DiffST: High-Level Style Feature Transfer Via Diffusion Mode...

引用

3rd International Conference on computer science, Electronic Information Engineering and Intelligent Control technology, CEI 2023

作者： Cheng, Hongche School of Computer Science and Technology Ustc Hefei China

ISBN: (纸本)9798350372052

Image style transfer aims to transfer the style of one image to another to create a new image with a specific artistic style. Existing style transfer algorithms primarily focus on transferring low-level features, such as textures, colors, strokes, etc., while neglecting the transfer of high-level features like semantic elements and object shapes. To address this issue, we propose DiffST, a new style transfer architecture based on pretrained text-to-image diffusion models. Specifically, DiffST can fully extract the feature of the style images to guide the redrawing of the content image, thereby completing the style transfer. Moreover, DiffST introduces a new image redrawing method called two-stage inversion, which effectively preserves the information of the content image and enhances the quality of the generated image. We demonstrate the quality of our transfer using numerous different paintings and compare DiffST with state-of-the-art methods, proving the superiority of DiffST. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks Pruning Based on Energy Adaptation 10

Convolutional Neural Networks Pruning Based on Energy Adapta...

引用

10th International Conference on Big Data Computing and Communications, BIGCOM 2024

作者： Guo, Fan Guo, Xing Du, Haohua Anhui University School of Computer Science and Technology HeFei China Anhui University School of Computer Science and Technology USTC-DEQING Alpha Innovation Institute HeFei China Beihang University School of Cyber Science and Technology USTC-DEQING Alpha Innovation Institute Beijing China

ISBN: (纸本)9798331509538

Convolutional neural networks have achieved remarkable performance in many areas of computer vision, but typically require significant computational resources, making them difficult to deploy on resource-constrained devices. To address this challenge, researchers have explored a number of model compression methods. Most of the pruning methods mainly simplify the network structure by reducing the amount of computation or the number of parameters, which indirectly reduces the resource requirements such as energy consumption of the model, but may not match the energy budget in the actual deployment environment. In this paper, we propose an energy adaptive pruning algorithm with energy consumption as the optimization objective. With continuous iterative optimization during the training process, the final sparse model not only reduces the number of parameters and computation, but also maintains the performance while meeting the energy budget. We conducted a series of experiments on VGG16-BN and MobileNet-VI to verify the effectiveness and superiority of our method. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

AdaViT: Task Adaptive ViT Compression Based on Module Replacement 10

AdaViT: Task Adaptive ViT Compression Based on Module Replac...

引用

10th International Conference on Big Data Computing and Communications, BIGCOM 2024

作者： Zhang, Weijian Guo, Xing Du, Haohua Anhui University School of Computer Science and Technology HeFei China Anhui University School of Computer Science and Technology USTC-DEQING Alpha Innovation Institute HeFei China Beihang University School of Cyber Science and Technology USTC-DEQING Alpha Innovation Institute Beijing China

ISBN: (纸本)9798331509538

Large pre-trained visual models, such as Vision Transformer (ViT), have shown excellent results in a variety of visual processing tasks. However, the large parameter sizes of these models make them difficult to deploy in applications that require limited resources for fast real-time inference. Existing model compression methods compress pre-trained ViTs into models of the same structure, but the compressed models fail to maximise performance on different tasks and consume significant computational and storage resources to adapt to downstream tasks. Pre-trained ViT models learn rich knowledge from large datasets and require different knowledge for different tasks, so removing task-specific redundant knowledge from pre-trained models is the key to achieve model compression while maximising model performance on different tasks. Based on this idea, we propose a novel ViT compression method, AdaViT. Firstly, a lightweight module is introduced, which adds less than 2% of extra parameters to realise the adaptive tuning of the model to different tasks to show the best prediction, and its effectiveness is proved by experiments. Second, inspired by the idea of knowledge distillation, we propose a new module replacement compression method, which effectively compresses the ViT by gradually replacing the Transformer module in the original ViT, and achieves task-oriented adaptive ViT compression through the combination of adaptive modules and model replacement methods. We evaluate AdaViT on several visual classification tasks and compare it with other ViT compression methods, demonstrating the effectiveness of task-adaptive ViT compression. © 2024 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Automated Pragma-Based Loop Optimization 8

Reinforcement Learning for Automated Pragma-Based Loop Optim...

引用

8th IEEE Information technology and Mechatronics Engineering Conference, ITOEC 2025

作者： Li, Jiaxuan Zheng, Qilong University of Science and Technology of China (USTC) School of Computer Science Hefei China University of Science and Technology of China (USTC) National High Performance Computing Center Hefei China

ISBN: (纸本)9798331517915

Loops often dominate the execution time in high-performance computing, effective loop optimization is critical for overall performance. We propose a reinforcement learning-based framework that automatically discovers and composes transformations - including tiling, fusion, interchange, and unrolling - and evaluate the framework on a subset of Polybench benchmarks. Compared to the Polly compiler baseline, our approach achieves an average speedup of 2.46×, peaking at 7× on the jacobi-1d kernel, while also consistently outperforming a global greedy scheduling algorithm. By adaptively combining multiple transformations, the RL-based method exploits deeper synergies with minimal overhead once trained, thus alleviating the repeated manual tuning and hardware-specific adjustments required by conventional techniques. © 2025 IEEE.

关键词： Autotuning Loop transformation Performance optimization Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

Pondering About Task Spatial Misalignment: Classification-Localization Equilibrated Object Detection 48

Pondering About Task Spatial Misalignment: Classification-Lo...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhang, Yudong Lu, Wei Wang, Xu Wang, Pengkun Wang, Yang Hefei China School of Software Engineering Ustc Hefei China School of Computer Science and Technology Ustc Hefei China School of Data Science Ustc Hefei China Suzhou Institute for Advanced Research Ustc Suzhou China

ISBN: (纸本)9781728163277

Object detection is a fundamental task in computer vision, consisting of both classification and localization tasks. Previous works mostly perform classification and localization with shared feature extractor like Convolution Neural Network. However, the tasks of classification and localization exhibit different sensitivities with regard to the same feature, hence the "task spatial misalignment"issue. This issue can result in a hedge issue between the performances of localizer and classifier. To address these issues, we first propose a novel Dynamic Coefficient Loss to simultaneously consider and balance the performances of classification and localization tasks. To well address anchor label misjudgment issue in irregular- shaped object detection, we define a new classification-aware IoU metric to assign anchors intelligently. Finally, we further introduce the localization factor into NMS by proposing a Classification-Localization balanced NMS. Extensive experiments on MS COCO and PASCAL VOC demonstrate that our proposals can improve RetinaNet by around 1.5% AP with various backbones. © 2023 IEEE.

关键词： Non-Maximum Suppression Object detection task spatial misalignment

来源：评论

学校读者我要写书评

暂无评论

GRETO: REMEDYING DYNAMIC GRAPH TOPOLOGY-TASK DISCORDANCE VIA TARGET HOMOPHILY 11

GRETO: REMEDYING DYNAMIC GRAPH TOPOLOGY-TASK DISCORDANCE VIA...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Zhou, Zhengyang Huang, Qihe Lin, Gengyu Yang, Kuo Bai, Lei Wang, Yang Hefei China School of Software Engineering USTC China School of Computer Science and Technology USTC China Shanghai AI Laboratory Shanghai China

Dynamic graphs are ubiquitous across disciplines where observations usually change over time. Regressions on dynamic graphs often contribute to diverse critical tasks, such as climate early-warning and traffic controlling. Existing homophily Graph Neural Networks (GNNs) adopt physical connections or feature similarity as adjacent matrix to perform node-level aggregations. However, on dynamic graphs with diverse node-wise relations, exploiting a pre-defined fixed topology for message passing inevitably leads to the aggregations of target-deviated neighbors. We designate such phenomenon as the topology-task discordance, which naturally challenges the homophily assumption. In this work, we revisit node-wise relationships and explore novel homophily measurements on dynamic graphs with both signs and distances, capturing multiple node-level spatial relations and temporal evolutions. We discover that advancing homophily aggregations to signed target-oriented message passing can effectively resolve the discordance and promote aggregation capacity. Therefore, a GReTo is proposed, which performs signed message passing in immediate neighborhood, and exploits both local environments and target awareness to realize high-order message propagation. Empirically, our solution achieves significant improvements against best baselines, notably improving 24.79% on KnowAir and 3.60% on Metr-LA. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

NUWADYNAMICS: DISCOVERING AND UPDATING IN CAUSAL SPATIO-TEMPORAL MODELING 12

NUWADYNAMICS: DISCOVERING AND UPDATING IN CAUSAL SPATIO-TEMP...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Wang, Kun Wu, Hao Duan, Yifan Zhang, Guibin Wang, Kai Peng, Xiaojiang Zheng, Yu Liang, Yuxuan Wang, Yang China Suzhou Institute for Advanced Research USTC China School of Software Engineering USTC China School of Computer Science USTC China Hong Kong Tongji University China Shenzhen Technology University China National University of Singapore Singapore JD iCity JD Technology

Spatio-temporal (ST) prediction plays a pivotal role in earth sciences, such as meteorological prediction, urban computing. Adequate high-quality data, coupled with deep models capable of inference, are both indispensable and prerequisite for achieving meaningful results. However, the sparsity of data and the high costs associated with deploying sensors lead to significant data imbalances. Models that are overly tailored and lack causal relationships further compromise the generalizabilities of inference methods. Towards this end, we first establish a causal concept for ST predictions, named NuwaDynamics, which targets to identify causal regions in data and endow model with causal reasoning ability in a two-stage process. Concretely, we initially leverage upstream self-supervision to discern causal important patches, imbuing the model with generalized information and conducting informed interventions on complementary trivial patches to extrapolate potential test distributions. This phase is referred to as the discovery step. Advancing beyond the discovery step, we transfer the data to downstream tasks for targeted ST objectives, aiding the model in recognizing a broader potential distribution and fostering its causal perceptual capabilities (denoted as Update step). Our concept aligns seamlessly with the contemporary backdoor adjustment mechanism in causality theory. Extensive experiments on six real-world ST benchmarks showcase that models can gain outcomes upon the integration of the NuwaDynamics concept. NuwaDynamics also can significantly benefit a wide range of changeable ST tasks like extreme weather and long temporal step super-resolution predictions. Our codes are available at https://***/easylearningscores/NuwaDynamics. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

Using Sensors to Complement Cameras to Save Arithmetic Power for Autonomous Driving Recognition 9

Using Sensors to Complement Cameras to Save Arithmetic Power...

引用

9th International Conference on Big Data Computing and Communications, BigCom 2023

作者： Chen, Rui Guo, Xing Du, Haohua Anhui University School of Computer Science and Technology HeFei China Anhui University School of Computer Science and Technology USTC-DEQING Alpha Innovation Institute HeFei China Beihang University School of Cyber Science and Technology USTC-DEQING Alpha Innovation Institute Beijing China

ISBN: (纸本)9798350331240

For the development of autonomous driving technology, object recognition is undoubtedly an important issue that cannot be ignored. Existing object recognition methods rely heavily on large deep neural networks, but there are still scenarios of incorrect recognition. Large deep networks also lead to an increase in recognition arithmetic. We work on an approach that addresses the scenarios where recognition errors still occur at this stage and does not require training giant networks. Our approach essentially explores the causes of recognition errors and analyzes the characteristics of the erroneous scenes. Other onboard sensors are then used to help the camera recognize the object. This avoids training deep neural networks to save computing power. We tested our approach on an existing dataset of bad weather and object occlusion and compared it with 2D detection and other sensor fusion methods. It can be seen that the mAP of our method increases by about 0.2 compared to the 2D detection, and the inference time saves about 60ms compared to the general 3D fusion method. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Pre-Segmentation: A Data Augmentation-Based Strategy for Thinning ViT Models 10

Pre-Segmentation: A Data Augmentation-Based Strategy for Thi...

引用

10th International Conference on Big Data Computing and Communications, BIGCOM 2024

作者： Guo, Houbin Guo, Xing Du, Haohua Anhui University School of Computer Science and Technology HeFei China USTC-DEQING Alpha Innovation Institute China Beihang University School of Cyber Science and Technology Beijing China

ISBN: (纸本)9798331509538

In the basic Vision transformer (ViT) model, the way to process the image is to cut the image into a certain number of patches as labeled (location coded) tokens, which are inputted to the multi-attention part of the model to extract the information, and then passed through the full connectivity layer to a classifier to classify the image. If all the Tokens are utilized for interaction, the complex ViT structure brings a huge amount of computation, which is a major drawback of the model. The ViT model itself is characterized by global interaction, and Attention is extremely sensitive to global information, so the over-pursuit of interaction with all the Tokens will bring about a sharp increase in complexity and a multiplication of the pressure on the hardware facilities, such as the reduction in the number of Tokens, which will bring about a reduction in the amount of information. If the number of Tokens is reduced, it brings about loss of information and unsatisfactory accuracy. In this study, we take the lightweight ViT model as a starting point, and preprocess the images: the images are chunked and then entered into the coding layer for information extraction respectively, and finally the respective cls labels are processed to get the classification results, which can solve the problem of over-attention to global attention of ViT as well as avoiding the loss of information due to the reduction of Tokens, and ultimately realizing the model's lightweighting. In conclusion, our model (PS-ViT) starts from two aspects, firstly, data enhancement is used to improve the generalization ability of the model;secondly, in the processing of input images, pre-blocking can both change the range of model information interaction and reduce the computation of the model in order to achieve efficient reasoning. Finally, a 40% reduction in computation can be achieved while maintaining accuracy. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Self-Play for Learning Robust Human-Robot Interaction on Crowd Navigation Tasks 3

Asymmetric Self-Play for Learning Robust Human-Robot Interac...

引用

3rd International Conference on Electronics, Communications and Information technology, CECIT 2022

作者： Ma, Jun Qiu, Quecheng Chen, Shuyan Yao, Shunyi Chen, Yuan Ji, Jianmin School of Data Science China USTC School of Computer Science and Technology China

ISBN: (纸本)9798350331974

A robot can make a sound to aware nearby pedestrians during its navigation, which often results in a more efficient and safer trajectory in a crowded environment. However, it is challenging to integrate such interaction capability into an existing robot navigation policy. In this paper, we propose a deep reinforcement learning (DRL) approach for integration, which results in effective interactive robot navigation policies in crowded environments. In particular, we specify the interaction capability by a set of high-level actions with flexible control. Then the navigation policy can be considered as a specific implementation of the 'move' action. Based on these high-level actions, we can train a robust human-robot interaction policy via asymmetric self-play, where the robot and some pedestrians, considered as naughty kids, play a game. Then the interaction policy can not only interact with pedestrians who cooperate with the robot but also with pedestrians who try to block the robot. We evaluate our approach in various simulation environments and compare it with multiple approaches. The experimental results show that our approach is robust and performs well in dense environments that are challenging for others. We also deploy the trained policy on a robot and evaluate its performance in multiple real-world crowded environments. A demonstration video is available online at https://***/x32YmivsIh0. © 2022 IEEE.

关键词： Reinforcement learning

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33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：