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

6,810 篇 会议
36 篇 期刊文献
12 册 图书

馆藏范围

6,857 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

4,042 篇 工学
- 3,808 篇 计算机科学与技术...
- 1,615 篇 软件工程
- 847 篇 光学工程
- 383 篇 信息与通信工程
- 286 篇 控制科学与工程
- 212 篇 机械工程
- 189 篇 电气工程
- 97 篇 生物医学工程（可授...
- 80 篇 电子科学与技术（可...
- 79 篇 生物工程
- 62 篇 仪器科学与技术
- 39 篇 力学（可授工学、理...
- 38 篇 建筑学
- 37 篇 土木工程
- 34 篇 航空宇航科学与技...
- 29 篇 安全科学与工程
- 24 篇 测绘科学与技术
- 23 篇 交通运输工程
- 22 篇 化学工程与技术
1,618 篇 理学
- 1,021 篇 物理学
- 1,005 篇 数学
- 379 篇 统计学（可授理学、...
- 160 篇 生物学
- 38 篇 系统科学
- 27 篇 化学
185 篇 管理学
- 132 篇 图书情报与档案管...
- 56 篇 管理科学与工程(可...
- 32 篇 工商管理
153 篇 医学
- 153 篇 临床医学
- 22 篇 基础医学(可授医学...
18 篇 法学
11 篇 教育学
10 篇 农学
7 篇 经济学
2 篇 军事学
1 篇 艺术学

主题

2,394 篇 computer vision
879 篇 pattern recognit...
667 篇 cameras
663 篇 computer science
633 篇 face recognition
577 篇 layout
550 篇 image segmentati...
524 篇 conferences
520 篇 shape
479 篇 object recogniti...
470 篇 robustness
411 篇 humans
354 篇 feature extracti...
338 篇 object detection
308 篇 training
278 篇 application soft...
270 篇 image recognitio...
263 篇 lighting
241 篇 image reconstruc...
236 篇 computational mo...

机构

43 篇 microsoft resear...
26 篇 department of co...
21 篇 swiss fed inst t...
21 篇 school of comput...
20 篇 department of co...
19 篇 swiss fed inst t...
19 篇 carnegie mellon ...
18 篇 department of co...
18 篇 the robotics ins...
17 篇 department of in...
17 篇 robotics institu...
17 篇 institute of com...
16 篇 univ sci & techn...
15 篇 tsinghua univ pe...
14 篇 department of el...
14 篇 computer vision ...
14 篇 school of comput...
14 篇 microsoft resear...
14 篇 school of comput...
13 篇 univ maryland co...

作者

39 篇 timofte radu
28 篇 s.k. nayar
26 篇 huang thomas s.
24 篇 xiaoou tang
24 篇 t. kanade
21 篇 t.s. huang
20 篇 van gool luc
20 篇 chellappa rama
19 篇 nayar shree k.
19 篇 t. darrell
17 篇 li stan z.
17 篇 torralba antonio
17 篇 a.k. jain
17 篇 a. zisserman
17 篇 jain anil k.
16 篇 m. hebert
16 篇 g. healey
16 篇 heung-yeung shum
16 篇 zisserman andrew
15 篇 m. shah

语言

6,856 篇 英文
2 篇 中文
1 篇 土耳其文

检索条件"任意字段=2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006"

共 6858 条记录，以下是281-290 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：

Attenuating Catastrophic Forgetting by Joint Contrastive and Incremental Learning

Attenuating Catastrophic Forgetting by Joint Contrastive and...

引用

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

作者： Ferdinand, Quentin Clement, Benoit Oliveau, Quentin Le Chenadec, Gilles Papadakis, Panagiotis Naval Grp Res Cherbourg En Cotentin France ENSTA Bretagne Lab STICC UMR 6285 Brest France IMT Atlantique Lab STICC UMR 6285 Brest France

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

In class incremental learning, discriminative models are trained to classify images while adapting to new instances and classes incrementally. Training a model to adapt to new classes without total access to previous class data, however, leads to the known problem of catastrophic forgetting of the previously learnt classes. To alleviate this problem, we show how we can build upon recent progress on contrastive learning methods. In particular, we develop an incremental learning approach for deep neural networks operating both at classification and representation level which alleviates forgetting and learns more general features for data classification. Experiments performed on several datasets demonstrate the superiority of the proposed method with respect to well known state-of-the-art methods.

关键词： Learning systems Training Deep learning Adaptation models computer vision conferences Computational modeling

来源：评论

学校读者我要写书评

暂无评论

À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting

À-la-carte Prompt Tuning (APT): Combining Distinct Data Via...

引用

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

作者： Bowman, Benjamin Achille, Alessandro Zancato, Luca Trager, Matthew Perera, Pramuditha Paolini, Giovanni Soatto, Stefano Aws Ai Labs United States Ucla United States

ISBN: (纸本)9798350301298

We introduce À-la-carte Prompt Tuning (APT), a transformer-based scheme to tune prompts on distinct data so that they can be arbitrarily composed at inference time. The individual prompts can be trained in isolation, possibly on different devices, at different times, and on different distributions or domains. Furthermore each prompt only contains information about the subset of data it was exposed to during training. During inference, models can be assembled based on arbitrary selections of data sources, which we call à-la-carte learning. À-la-carte learning enables constructing bespoke models specific to each user's individual access rights and preferences. We can add or remove information from the model by simply adding or removing the corresponding prompts without retraining from scratch. We demonstrate that à-la-carte built models achieve accuracy within 5% of models trained on the union of the respective sources, with comparable cost in terms of training and inference time. For the continual learning benchmarks Split CIFAR- 100 and CORe50, we achieve state-of-the-art performance. © 2023 ieee.

关键词： Efficient and scalable vision

来源：评论

学校读者我要写书评

暂无评论

Edge-enhanced Feature Distillation Network for Efficient Super-Resolution

Edge-enhanced Feature Distillation Network for Efficient Sup...

引用

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

作者： Wang, Yan Nankai Univ Nankai Baidu Joint Lab Tianjin Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

With the recently massive development in convolution neural networks, numerous lightweight CNN-based image super-resolution methods have been proposed for practical deployments on edge devices. However, most existing methods focus on one specific aspect: network or loss design, which leads to the difficulty of minimizing the model size. To address the issue, we conclude block devising, architecture searching, and loss design to obtain a more efficient SR structure. In this paper, we proposed an edge-enhanced feature distillation network, named EFDN, to preserve the high-frequency information under constrained resources. In detail, we build an edge-enhanced convolution block based on the existing reparameterization methods. Meanwhile, we propose edge-enhanced gradient loss to calibrate the reparameterized path training. Experimental results show that our edge-enhanced strategies preserve the edge and significantly improve the final restoration quality. Code is available at https://***/icandle/EFDN.

关键词： Training computer vision Convolution Image edge detection conferences Superresolution Neural networks

来源：评论

学校读者我要写书评

暂无评论

SymDNN: Simple & Effective Adversarial Robustness for Embedded Systems

SymDNN: Simple & Effective Adversarial Robustness for Embedd...

引用

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

作者： Dey, Swarnava Dasgupta, Pallab Chakrabarti, Partha P. Indian Inst Technol Kharagpur Kharagpur 721302 W Bengal India

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

We propose SymDNN, a Deep Neural Network (DNN) inference scheme, to segment an input image into small patches, replace those patches with representative symbols, and use the reconstructed image for CNN inference. This approach of deconstruction of images, and the reconstruction from cluster centroids trained on clean images, enhances robustness against adversarial attacks. The input transform used in SymDNN is learned from very large datasets, making it difficult to approximate for adaptive adversarial attacks. For example, SymDNN achieves 23% and 42% robust accuracy at L-infinity attack strengths of 8/255 and 4/255 respectively, against BPDA under a complete white box setting, where most input processing based defenses break completely. SymDNN is not a future-proof adversarial defense that can defend any attack, but it is one of the few readily usable defenses in resource-limited embedded systems that defends against a wide range of attacks.

关键词： computer vision Adaptation models Visualization Embedded systems Computational modeling Symbols Transforms

来源：评论

学校读者我要写书评

暂无评论

Multi-view Multi-label Canonical Correlation Analysis for Cross-modal Matching and Retrieval

Multi-view Multi-label Canonical Correlation Analysis for Cr...

引用

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

作者： Sanghavi, Rushil Verma, Yashaswi IIT Jodhpur Jodhpur Rajasthan India

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

In this paper, we address the problem of cross-modal retrieval in presence of multi-view and multi-label data. For this, we present Multi-view Multi-label Canonical Correlation Analysis (or MVMLCCA), which is a generalization of CCA for multi-view data that also makes use of high-level semantic information available in the form of multi-label annotations in each view. While CCA relies on explicit pairings/associations of samples between two views (or modalities), MVMLCCA uses the available multi-label annotations to establish correspondence across multiple (two or more) views without the need of explicit pairing of multi-view samples. Extensive experiments on two multi-modal datasets demonstrate that the proposed approach offers much more flexibility than the related approaches without compromising on scalability and cross-modal retrieval performance. Our code and precomputed features are available at https://***/Rushil231100/MVMLCCA.

关键词： computer vision Correlation Codes Annotations Scalability conferences Semantics

来源：评论

学校读者我要写书评

暂无评论

CarlaScenes: A synthetic dataset for odometry in autonomous driving

CarlaScenes: A synthetic dataset for odometry in autonomous ...

引用

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

作者： Kloukiniotis, Andreas Papandreou, Andreas Anagnostopoulos, Christos Lalos, Aris Kapsalas, Petros Nguyen, D-, V Moustakas, Konstantinos Univ Patras Patras Greece ISI Ind Syst Inst Patras Patras Greece Panasonic Automot Langen Germany

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Despite the great scientific effort to capture adequately the complex environments in which autonomous vehicles (AVs) operate there are still use-cases that even SoA methods fail to handle. Specifically in odometry problems, on the one hand, geometric solutions operate with certain assumptions that are often breached in AVs, and on the other hand, deep learning methods do not achieve high accuracy. To contribute to that we present CarlaScenes, a large-scale simulation dataset captured using the CARLA simulator. The dataset is oriented to address the challenging odometry scenarios that cause the current state of art odometers to deviate from their normal operations. Based on a case study of failures presented in experiments we distinguished 7 different sequences of data. CarlaScenes besides providing consistent reference poses, includes data with semantic annotation at the instance level for both image and lidar. The full dataset is available at https://***/CarlaScenes/***.

关键词： Deep learning computer vision Laser radar conferences Semantics XML Trajectory

来源：评论

学校读者我要写书评

暂无评论

Searching for Efficient Neural Architectures for On-Device ML on Edge TPUs

Searching for Efficient Neural Architectures for On-Device M...

引用

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

作者： Akin, Berkin Gupta, Suyog Long, Yun Spiridonov, Anton Wang, Zhuo White, Marie Xu, Hao Zhou, Ping Zhou, Yanqi

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

On-device ML accelerators are becoming a standard in modern mobile system-on-chips (SoC). Neural architecture search (NAS) comes to the rescue for efficiently utilizing the high compute throughput offered by these accelerators. However, existing NAS frameworks have several practical limitations in scaling to multiple tasks and different target platforms. In this work, we provide a two-pronged approach to this challenge: (i) a NAS-enabling infrastructure that decouples model cost evaluation, search space design, and the NAS algorithm to rapidly target various on-device ML tasks, and (ii) search spaces crafted from group convolution based inverted bottleneck (IBN) variants that provide flexible quality/performance trade-offs on ML accelerators, complementing the existing full and depthwise convolution based IBNs. Using this approach we target a state-of-the-art mobile platform, Google Tensor SoC, and demonstrate neural architectures1 that improve the quality-performance pareto frontier for various computer vision (classification, detection, segmentation) as well as natural language processing tasks.

关键词： computer vision Tensors Costs Convolution Image edge detection computer architecture Throughput

来源：评论

学校读者我要写书评

暂无评论

Alleviating Representational Shift for Continual Fine-tuning

Alleviating Representational Shift for Continual Fine-tuning

引用

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

作者： Jie, Shibo Deng, Zhi-Hong Li, Ziheng Peking Univ Sch Artificial Intelligence Beijing Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

We study a practical setting of continual learning: fine-tuning on a pre-trained model continually. Previous work has found that, when training on new tasks, the features (penultimate layer representations) of previous data will change, called representational shift. Besides the shift of features, we reveal that the intermediate layers' representational shift (IRS) also matters since it disrupts batch normalization, which is another crucial cause of catastrophic forgetting. Motivated by this, we propose ConFiT, a fine-tuning method incorporating two components, cross-convolution batch normalization (Xconv BN) and hierarchical fine-tuning. Xconv BN maintains pre-convolution running means instead of post-convolution, and recovers post-convolution ones before testing, which corrects the inaccurate estimates of means under IRS. Hierarchical fine-tuning leverages a multi-stage strategy to fine-tune the pre-trained network, preventing massive changes in Conv layers and thus alleviating IRS. Experimental results on four datasets show that our method remarkably outperforms several state-of-the-art methods with lower storage overhead.

关键词： Training computer vision conferences pattern recognition Task analysis Testing

来源：评论

学校读者我要写书评

暂无评论

Out-Of-Distribution Detection In Unsupervised Continual Learning

Out-Of-Distribution Detection In Unsupervised Continual Lear...

引用

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

作者： He, Jiangpeng Zhu, Fengqing Purdue Univ Elmore Family Sch Elect & Comp Engn W Lafayette IN 47907 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Unsupervised continual learning aims to learn new tasks incrementally without requiring human annotations. However, most existing methods, especially those targeted on image classification, only work in a simplified scenario by assuming all new data belong to new tasks, which is not realistic if the class labels are not provided. Therefore, to perform unsupervised continual learning in real life applications, an out-of-distribution detector is required at beginning to identify whether each new data corresponds to a new task or already learned tasks, which still remains under-explored yet. In this work, we formulate the problem for Out-of-distribution Detection in Unsupervised Continual Learning (OOD-UCL) with the corresponding evaluation protocol. In addition, we propose a novel OOD detection method by correcting the output bias at first and then enhancing the output confidence for in-distribution data based on task discriminativeness, which can be applied directly without modifying the learning procedures and objectives of continual learning. Our method is evaluated on CIFAR-100 dataset by following the proposed evaluation protocol and we show improved performance compared with existing OOD detection methods under the unsupervised continual learning scenario.

关键词： computer vision Protocols Annotations conferences Detectors pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Camera Vehicle Tracking System for AI City Challenge 2022

Multi-Camera Vehicle Tracking System for AI City Challenge 2...

引用

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

作者： Li, Fei Wang, Zhen Nie, Ding Zhang, Shiyi Jiang, Xingqun Zhao, Xingxing Hu, Peng BOE Technol Grp Beijing Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Multi-Target Multi-Camera tracking is a fundamental task for intelligent traffic systems. The track 1 of AI City Challenge 2022 aims at the city-scale multi-camera vehicle tracking task. In this paper we propose an accurate vehicle tracking system composed of 4 parts, including: (1) State-of-the-art detection and re-identification models for vehicle detection and feature extraction. (2) Single camera tracking, where we introduce augmented tracks prediction and multi-level association method on top of tracking-by-detection paradigm.(3) Zone-based singe-camera track-let merging strategy. (4) Multi-camera spatial-temporal matching and clustering strategy. The proposed system achieves promising results and ranks the second place in Track 1 of the AI City Challenge 2022 with a IDF1 score of 0.8437.

关键词： computer vision Vehicle detection conferences Urban areas Merging Predictive models Feature extraction

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 << < 25 26 27 28 29 30 31 32 33 34 > >>

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：