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

23,015 篇 会议
126 册 图书
93 篇 期刊文献

馆藏范围

23,233 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,637 篇 工学
- 11,122 篇 计算机科学与技术...
- 3,490 篇 软件工程
- 2,446 篇 机械工程
- 1,719 篇 光学工程
- 1,078 篇 电气工程
- 1,024 篇 控制科学与工程
- 791 篇 信息与通信工程
- 412 篇 仪器科学与技术
- 352 篇 生物工程
- 251 篇 生物医学工程（可授...
- 198 篇 电子科学与技术（可...
- 114 篇 化学工程与技术
- 110 篇 安全科学与工程
- 100 篇 测绘科学与技术
- 89 篇 交通运输工程
- 88 篇 建筑学
- 84 篇 土木工程
3,496 篇 医学
- 3,482 篇 临床医学
- 81 篇 基础医学(可授医学...
3,249 篇 理学
- 1,943 篇 物理学
- 1,645 篇 数学
- 564 篇 统计学（可授理学、...
- 500 篇 生物学
- 249 篇 系统科学
- 108 篇 化学
525 篇 管理学
- 313 篇 图书情报与档案管...
- 227 篇 管理科学与工程(可...
- 76 篇 工商管理
276 篇 艺术学
- 276 篇 设计学（可授艺术学...
67 篇 法学
- 64 篇 社会学
38 篇 农学
28 篇 教育学
22 篇 经济学
10 篇 军事学
4 篇 文学

主题

10,190 篇 computer vision
3,972 篇 pattern recognit...
3,005 篇 training
2,007 篇 computational mo...
1,818 篇 visualization
1,816 篇 cameras
1,516 篇 feature extracti...
1,481 篇 shape
1,455 篇 three-dimensiona...
1,438 篇 image segmentati...
1,287 篇 robustness
1,206 篇 computer archite...
1,155 篇 semantics
1,147 篇 conferences
1,107 篇 layout
1,093 篇 computer science
1,089 篇 object detection
1,025 篇 benchmark testin...
970 篇 codes
922 篇 face recognition

机构

136 篇 univ sci & techn...
121 篇 univ chinese aca...
118 篇 chinese univ hon...
106 篇 carnegie mellon ...
101 篇 tsinghua univers...
101 篇 microsoft resear...
95 篇 swiss fed inst t...
93 篇 zhejiang univ pe...
82 篇 university of sc...
81 篇 zhejiang univers...
79 篇 university of ch...
77 篇 shanghai ai lab ...
74 篇 shanghai jiao to...
69 篇 national laborat...
67 篇 microsoft res as...
67 篇 alibaba grp peop...
64 篇 adobe research
60 篇 peking univ peop...
60 篇 tsinghua univ pe...
59 篇 univ oxford oxfo...

作者

81 篇 van gool luc
73 篇 timofte radu
65 篇 zhang lei
47 篇 luc van gool
40 篇 yang yi
40 篇 li stan z.
37 篇 loy chen change
35 篇 chen chen
33 篇 xiaoou tang
32 篇 liu yang
32 篇 qi tian
31 篇 tian qi
31 篇 sun jian
30 篇 murino vittorio
29 篇 darrell trevor
29 篇 pascal fua
29 篇 li fei-fei
28 篇 ling haibin
28 篇 li xin
28 篇 ying shan

语言

22,989 篇 英文
216 篇 其他
22 篇 中文
5 篇 土耳其文
2 篇 日文

检索条件"任意字段=IEEE Conference on Computer Vision and Pattern Recognition Workshops"

共 23234 条记录，以下是981-990 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：

Real-time Hyper-Dimensional Reconfiguration at the Edge using Hardware Accelerators

Real-time Hyper-Dimensional Reconfiguration at the Edge usin...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Kandaswamy, Indhumathi Farkya, Saurabh Daniels, Zachary van der Wal, Gooitzen Raghavan, Aswin Zhang, Yuzheng Hu, Jun Lomnitz, Michael Isnardi, Michael Zhang, David Piacentino, Michael SRI Int Ctr Vis Technol Princeton NJ 08540 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

In this paper we present Hyper-Dimensional Reconfigurable Analytics at the Tactical Edge (HyDRATE) using low-SWaP embedded hardware that can perform real-time reconfiguration at the edge leveraging non-MAC (free of floating-point Multiply-ACcumulate operations) deep neural nets (DNN) combined with hyperdimensional (HD) computing accelerators. We describe the algorithm, trained quantized model generation, and simulated performance of a feature extractor free of multiply-accumulates feeding a hyperdimensional logic-based classifier. Then we show how performance increases with the number of hyperdimensions. We describe the realized low-SWaP FPGA hardware and embedded software system compared to traditional DNNs and detail the implemented hardware accelerators. We discuss the measured system latency and power, noise robustness due to use of learnable quantization and HD computing, actual versus simulated system performance for a video activity classification task and demonstration of reconfiguration on this same dataset. We show that reconfigurability in the field is achieved by retraining only the feed-forward HD classifier without gradient descent backpropagation (gradient-free), using few-shot learning of new classes at the edge. Initial work performed used LRCN DNN and is currently extended to use Two-stream DNN with improved performance.

关键词： Quantization (signal) Power measurement System performance Software algorithms Feature extraction Real-time systems pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An Once-for-All Budgeted Pruning Framework for ConvNets Considering Input Resolution

An Once-for-All Budgeted Pruning Framework for ConvNets Cons...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Sun, Wenyu Cao, Jian Xu, Pengtao Liu, Xiangcheng Zhang, Yuan Wang, Yuan Peking Univ Sch Software & Microelect Beijing Peoples R China Peking Univ Sch Integrated Circuits Beijing Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

We propose an efficient once-for-all budgeted pruning framework (OFARPruning) to find many compact network architectures close to winner tickets in the early training stage considering the effect of input resolution during the pruning process. In architecture searching stage, we measure the similarity of the pruning mask to get high-quality network architecture with low energy and time consumption. After searching stage, our proposed method randomly sample the compact architectures with different pruning rates and input resolution to achieve joint optimization. Ultimately, we can obtain a cohort of compact networks adaptive to various resolution to meet dynamic FLOPs constraints on different edge devices with only once training. The experiments based on image classification and object detection show that OFARPruning has a higher accuracy than the once-for-all compression methods such as US-Net and MutualNet (1-2% better with less FLOPs), and achieve competitive performance as the conventional pruning methods (72.6% vs. 70.5% on MobileNetv2 under 170 MFLOPs) with much higher efficiency.

关键词： Training Image resolution Adaptive systems Image edge detection Energy resolution Object detection computer architecture

来源：评论

学校读者我要写书评

暂无评论

Transformer for Single Image Super-Resolution

Transformer for Single Image Super-Resolution

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Lu, Zhisheng Li, Juncheng Liu, Hong Huang, Chaoyan Zhang, Linlin Zeng, Tieyong Peking Univ Shenzhen Grad Sch Shenzhen Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Nanjing Univ Posts & Telecommun Nanjing Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Single image super-resolution (SISR) has witnessed great strides with the development of deep learning. However, most existing studies focus on building more complex networks with a massive number of layers. Recently, more and more researchers start to explore the application of Transformer in computer vision tasks. However, the heavy computational cost and high GPU memory occupation of the vision Transformer cannot be ignored. In this paper, we propose a novel Efficient Super-Resolution Transformer (ESRT) for SISR. ESRT is a hybrid model, which consists of a Lightweight CNN Backbone (LCB) and a Lightweight Transformer Backbone (LTB). Among them, LCB can dynamically adjust the size of the feature map to extract deep features with a low computational costs. LTB is composed of a series of Efficient Transformers (ET), which occupies a small GPU memory occupation, thanks to the specially designed Efficient Multi-Head Attention (EMHA). Extensive experiments show that ESRT achieves competitive results with low computational cost. Compared with the original Transformer which occupies 16,057M GPU memory, ESRT only occupies 4,191M GPU memory. All codes are available at https://***/luissen/ESRT.

关键词： computer vision Adaptation models Computational modeling Superresolution Memory management Graphics processing units Transformers

来源：评论

学校读者我要写书评

暂无评论

Comprehensive and Delicate: An Efficient Transformer for Image Restoration

Comprehensive and Delicate: An Efficient Transformer for Ima...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Zhao, Haiyu Gou, Yuanbiao Li, Boyun Peng, Dezhong Lv, Jiancheng Peng, Xi Sichuan Univ Coll Comp Sci Chengdu Peoples R China

ISBN: (纸本)9798350301298

vision Transformers have shown promising performance in image restoration, which usually conduct window- or channel-based attention to avoid intensive computations. Although the promising performance has been achieved, they go against the biggest success factor of Transformers to a certain extent by capturing the local instead of global dependency among pixels. In this paper, we propose a novel efficient image restoration Transformer that first captures the superpixel-wise global dependency, and then transfers it into each pixel. Such a coarse-to-fine paradigm is implemented through two neural blocks, i.e., condensed attention neural block (CA) and dual adaptive neural block (DA). In brief, CA employs feature aggregation, attention computation, and feature recovery to efficiently capture the global dependency at the superpixel level. To embrace the pixel-wise global dependency, DA takes a novel dual-way structure to adaptively encapsulate the globality from superpixels into pixels. Thanks to the two neural blocks, our method achieves comparable performance while taking only similar to 6% FLOPs compared with SwinIR.

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

SoccerTrack: A Dataset and Tracking Algorithm for Soccer with Fish-eye and Drone Videos

SoccerTrack: A Dataset and Tracking Algorithm for Soccer wit...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Scott, Atom Uchida, Ikuma Onishi, Masaki Kameda, Yoshinari Fukui, Kazuhiro Fujii, Keisuke Univ Tsukuba Tsukuba Ibaraki Japan Natl Inst Adv Ind Sci & Technol Tsukuba Japan Nagoya Univ Nagoya Aichi Japan RIKEN JST PRESTO Tokyo Japan

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Tracking devices that can track both players and balls are critical to the performance of sports teams. Recently, significant effort has been focused on building larger broadcast sports video datasets. However, broadcast videos do not show the entire pitch and only provides partial information about the game. On the other hand, other camera perspectives can capture the whole field in a single frame, such as fish-eye and bird-eye view (drone) cameras. Unfortunately, there has not been a dataset where such data has been publicly shared until now. This paper proposes SoccerTrack, a dataset set consisting of GNSS and bounding box tracking data annotated on video captured with a 8K-resolution fish-eye camera and a 4K-resolution drone camera. In addition to a benchmark tracking algorithm, we include code for camera calibration and other preprocessing. Finally, we evaluate the tracking accuracy among a GNSS, fish-eye camera and drone camera data. SoccerTrack is expected to provide a more robust foundation for designing MOT algorithms that are less reliant on visual cues and more reliant on motion analysis.

关键词： Performance evaluation Global navigation satellite system Visualization Codes Tracking Cameras pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Improving Robustness of vision Transformers by Reducing Sensitivity to Patch Corruptions

Improving Robustness of Vision Transformers by Reducing Sens...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Guo, Yong Stutz, David Schiele, Bernt Saarland Informat Campus Max Planck Inst Informat Saarbrucken Germany

ISBN: (纸本)9798350301298

Despite their success, vision transformers still remain vulnerable to image corruptions, such as noise or blur. Indeed, we find that the vulnerability mainly stems from the unstable self-attention mechanism, which is inherently built upon patch-based inputs and often becomes overly sensitive to the corruptions across patches. For example, when we only occlude a small number of patches with random noise (e.g., 10%), these patch corruptions would lead to severe accuracy drops and greatly distract intermediate attention layers. To address this, we propose a new training method that improves the robustness of transformers from a new perspective - reducing sensitivity to patch corruptions (RSPC). Specifically, we first identify and occlude/corrupt the most vulnerable patches and then explicitly reduce sensitivity to them by aligning the intermediate features between clean and corrupted examples. We highlight that the construction of patch corruptions is learned adversarially to the following feature alignment process, which is particularly effective and essentially different from existing methods. In experiments, our RSPC greatly improves the stability of attention layers and consistently yields better robustness on various benchmarks, including CIFAR-10/100-C, ImageNet-A, ImageNet-C, and ImageNet-P.

关键词： Deep learning architectures and techniques

来源：评论

学校读者我要写书评

暂无评论

Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning

Gradient-based Uncertainty Attribution for Explainable Bayes...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Wang, Hanjing Joshi, Dhiraj Wang, Shiqiang Ji, Qiang Rensselaer Polytech Inst Troy NY 12180 USA IBM Res Armonk NY USA

ISBN: (纸本)9798350301298

Predictions made by deep learning models are prone to data perturbations, adversarial attacks, and out-of-distribution inputs. To build a trusted AI system, it is therefore critical to accurately quantify the prediction uncertainties. While current efforts focus on improving uncertainty quantification accuracy and efficiency, there is a need to identify uncertainty sources and take actions to mitigate their effects on predictions. Therefore, we propose to develop explainable and actionable Bayesian deep learning methods to not only perform accurate uncertainty quantification but also explain the uncertainties, identify their sources, and propose strategies to mitigate the uncertainty impacts. Specifically, we introduce a gradient-based uncertainty attribution method to identify the most problematic regions of the input that contribute to the prediction uncertainty. Compared to existing methods, the proposed UA-Backprop has competitive accuracy, relaxed assumptions, and high efficiency. Moreover, we propose an uncertainty mitigation strategy that leverages the attribution results as attention to further improve the model performance. Both qualitative and quantitative evaluations are conducted to demonstrate the effectiveness of our proposed methods.

关键词： Explainable computer vision

来源：评论

学校读者我要写书评

暂无评论

Learning Expressive Prompting With Residuals for vision Transformers

Learning Expressive Prompting With Residuals for Vision Tran...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Das, Rajshekhar Dukler, Yonatan Ravichandran, Avinash Swarninathan, Ashwin Carnegie Mellon Univ Pittsburgh PA 15213 USA AWS AI Labs Shanghai Peoples R China

ISBN: (纸本)9798350301298

Prompt learning is an efficient approach to adapt transformers by inserting learnable set of parameters into the input and intermediate representations of a pre-trained model. In this work, we present Expressive Prompts with Residuals (EXPRES) which modifies the prompt learning paradigm specifically for effective adaptation of vision transformers (ViT). Our method constructs downstream representations via learnable "output" tokens (shallow prompts), that are akin to the learned class tokens of the ViT. Further for better steering of the downstream representation processed by the frozen transformer, we introduce residual learnable tokens that are added to the output of various computations. We apply EXPRES for image classification and few-shot semantic segmentation, and show our method is capable of achieving state of the art prompt tuning on 3/3 categories of the VTAB benchmark. In addition to strong performance, we observe that our approach is an order of magnitude more prompt efficient than existing visual prompting baselines. We analytically show the computational benefits of our approach over weight space adaptation techniques like finetuning. Lastly we systematically corroborate the architectural design of our method via a series of ablation experiments.

关键词： continual low-shot meta or long-tail learning Transfer

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning-based Robust Object Detection under Smoky Conditions

Contrastive Learning-based Robust Object Detection under Smo...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Wu, Wei Chang, Hao Zheng, Yonghua Li, Zhu Chen, Zhiwen Zhang, Ziheng Xidian Univ State Key Lab Integrated Serv Networks Xian Peoples R China Univ Missouri Dept Comp Sci & Elect Engn Kansas City MO 64110 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Object detection is to effectively find out interested targets in images and then accurately determine their categories and positions. Recently many excellent methods have been developed to provide powerful detection capability. However, their performance may degrade significantly under severe weather such as smoky conditions. In this paper, we propose a contrastive learning-based robust object detection algorithm for smoke images. The proposed object detector consists of two modules: contrastive learning module and object bounding box prediction module. The first module learns representation vectors by maximizing agreement between different augmented views of the same smoke image. These representations are then sent to the second module to yield the bounding box for each object. In addition, we also propose a novel affine data augmentation method. Extensive experiments have been conducted on A2I2-Haze dataset which is the first real haze dataset with in-situ smoke measurement aligned to aerial and ground imagery. This dataset is also the only dataset used in the 5th UG(2)+ challenges of CVPR 2022 for both training and testing. Compared with state-of-the-art methods, evaluation results show the superiority of our proposed object detector.

关键词： Training computer vision conferences Object detection Detectors Transforms Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

MARRS: Modern Backbones Assisted Co-training for Rapid and Robust Semi-Supervised Domain Adaptation

MARRS: Modern Backbones Assisted Co-training for Rapid and R...

引用

2023 ieee/CVF conference on computer vision and pattern recognition workshops, CVPRW 2023

作者： Jain, Saurabh Kumar Das, Sukhendu Indian Institute of Technology Visualization and Perception Lab Department of Computer Science Engineering Madras India

ISBN: (纸本)9798350302493

Semi-Supervised Domain Adaptation (SSDA) aims to develop domain invariant models from scarcely labeled target domain in addition to the fully labeled source domain. Current SSDA works are often applied in conjunction with ResNet34 backbone, which makes them overlook the advantages of utilizing other backbones. Hence, in this paper, we investigate the impact of employing different modern backbones in SSDA and propose a novel solution named Modern Backbones Assisted Co-training for Rapid and Robust Semi-Supervised Domain Adaptation (MARRS), that uses discriminative features of two modern backbones for training linear classifiers using the well established co-training framework. To induce diversity among classifiers for effective co-training, we propose a novel module that produces diversity at three levels, namely image, backbone, and feature distribution levels. Experiments reveal that MARRS not only achieves state-of-the-art performance across all popular SSDA datasets, but also drastically cuts the computation time compared to other SSDA approaches, making MARRS a rapid and robust solution for SSDA. We also provide extensive ablation experiments to verify our framework's vitality and primary design choices. © 2023 ieee.

关键词： computer vision

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 << < 95 96 97 98 99 100 101 102 103 104 > >>

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：