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

20,798 篇 会议
88 篇 期刊文献
65 册 图书

馆藏范围

20,950 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,275 篇 工学
- 10,923 篇 计算机科学与技术...
- 2,484 篇 机械工程
- 2,307 篇 软件工程
- 913 篇 光学工程
- 771 篇 电气工程
- 556 篇 控制科学与工程
- 405 篇 信息与通信工程
- 210 篇 测绘科学与技术
- 131 篇 生物医学工程（可授...
- 104 篇 电子科学与技术（可...
- 100 篇 生物工程
- 92 篇 仪器科学与技术
- 56 篇 化学工程与技术
- 52 篇 建筑学
- 48 篇 土木工程
- 44 篇 安全科学与工程
- 38 篇 力学（可授工学、理...
- 38 篇 航空宇航科学与技...
- 35 篇 交通运输工程
3,457 篇 医学
- 3,449 篇 临床医学
- 34 篇 基础医学(可授医学...
2,315 篇 理学
- 1,154 篇 数学
- 1,132 篇 物理学
- 417 篇 统计学（可授理学、...
- 386 篇 生物学
- 252 篇 系统科学
- 57 篇 化学
353 篇 管理学
- 184 篇 图书情报与档案管...
- 176 篇 管理科学与工程(可...
- 32 篇 工商管理
28 篇 法学
20 篇 农学
15 篇 教育学
9 篇 经济学
8 篇 艺术学
5 篇 文学
5 篇 军事学

主题

8,203 篇 computer vision
3,010 篇 pattern recognit...
2,732 篇 training
1,769 篇 computational mo...
1,657 篇 visualization
1,483 篇 cameras
1,415 篇 shape
1,369 篇 three-dimensiona...
1,369 篇 face recognition
1,285 篇 image segmentati...
1,272 篇 feature extracti...
1,178 篇 robustness
1,090 篇 semantics
1,040 篇 layout
1,007 篇 object detection
975 篇 object recogniti...
969 篇 computer science
946 篇 computer archite...
946 篇 benchmark testin...
931 篇 codes

机构

174 篇 univ sci & techn...
154 篇 carnegie mellon ...
148 篇 univ chinese aca...
144 篇 chinese univ hon...
113 篇 microsoft resear...
103 篇 zhejiang univ pe...
99 篇 swiss fed inst t...
97 篇 tsinghua univ pe...
93 篇 tsinghua univers...
91 篇 microsoft res as...
88 篇 shanghai ai lab ...
81 篇 zhejiang univers...
76 篇 alibaba grp peop...
74 篇 hong kong univ s...
73 篇 university of sc...
72 篇 peking univ peop...
69 篇 university of ch...
68 篇 shanghai jiao to...
66 篇 google res mount...
66 篇 univ oxford oxfo...

作者

80 篇 van gool luc
71 篇 zhang lei
59 篇 timofte radu
48 篇 yang yi
47 篇 xiaoou tang
44 篇 darrell trevor
43 篇 tian qi
43 篇 luc van gool
42 篇 loy chen change
42 篇 sun jian
42 篇 li fei-fei
40 篇 qi tian
39 篇 li stan z.
37 篇 liu yang
37 篇 chen xilin
36 篇 shan shiguang
35 篇 liu xiaoming
35 篇 vasconcelos nuno
35 篇 torralba antonio
32 篇 zhou jie

语言

20,928 篇 英文
14 篇 中文
6 篇 其他
2 篇 日文
2 篇 土耳其文

检索条件"任意字段=2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009"

共 20951 条记录，以下是4961-4970 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：

Content-aware Token Sharing for Efficient Semantic Segmentation with vision Transformers

Content-aware Token Sharing for Efficient Semantic Segmentat...

引用

conference on computer vision and pattern recognition (cvpr)

作者： Chenyang Lu Daan de Geus Gijs Dubbelman Eindhoven University of Technology

This paper introduces Content-aware Token Sharing (CTS), a token reduction approach that improves the computational efficiency of semantic segmentation networks that use vision Transformers (ViTs). Existing works have proposed token reduction approaches to improve the efficiency of ViT-based image classification networks, but these methods are not directly applicable to semantic segmentation, which we address in this work. We observe that, for semantic segmentation, multiple image patches can share a token if they contain the same semantic class, as they contain redundant information. Our approach leverages this by employing an efficient, class-agnostic policy network that predicts if image patches contain the same semantic class, and lets them share a token if they do. With experiments, we explore the critical design choices of CTS and show its effectiveness on the ADE20K, Pascal Context and Cityscapes datasets, various ViT backbones, and different segmentation decoders. With Content-aware Token Sharing, we are able to reduce the number of processed tokens by up to 44%, without diminishing the segmentation quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Class Incremental Learning with Multi-Teacher Distillation

Class Incremental Learning with Multi-Teacher Distillation

引用

conference on computer vision and pattern recognition (cvpr)

作者： Haitao Wen Lili Pan Yu Dai Heqian Qiu Lanxiao Wang Qingbo Wu Hongliang Li University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Distillation strategies are currently the primary approaches for mitigating forgetting in class incremental learning (CIL). Existing methods generally inherit previous knowledge from a single teacher. However, teachers with different mechanisms are talented at different tasks, and inheriting diverse knowledge from them can enhance compatibility with new knowledge. In this paper, we propose the MTD method to find multiple diverse teachers for CIL. Specifically, we adopt weight permutation, feature perturbation, and diversity regularization techniques to ensure diverse mechanisms in teachers. To reduce time and memory consumption, each teacher is represented as a small branch in the model. We adapt existing CIL distillation strategies with MTD and extensive experiments on CIFAR-100, ImageNet-100, and ImageNet-1000 show significant performance improvement. Our code is available at https://***/HaitaoWen/CLearning.

关键词： computer vision Adaptation models Incremental learning Codes Perturbation methods Memory management Teleportation

来源：评论

学校读者我要写书评

暂无评论

Dense vision Transformer Compression with Few Samples

Dense Vision Transformer Compression with Few Samples

引用

conference on computer vision and pattern recognition (cvpr)

作者： Hanxiao Zhang Yifan Zhou Guo-Hua Wang National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Few-shot model compression aims to compress a large model into a more compact one with only a tiny training set (even without labels). Block-level pruning has recently emerged as a leading technique in achieving high accuracy and low latency in few-shot CNN compression. But, few-shot compression for vision Transformers (ViT) remains largely unexplored, which presents a new challenge. In particular, the issue of sparse compression exists in traditional CNN few-shot methods, which can only produce very few compressed models of different model sizes. This paper proposes a novel framework for few-shot ViT compression named DC-ViT. Instead of dropping the entire block, DC-ViT selectively eliminates the attention module while retaining and reusing portions of the MLP module. DC-ViT enables dense compression, which outputs numerous compressed models that densely populate the range of model complexity. DC-ViT outperforms state-of-the-art few-shot compression methods by a significant margin of 10 percentage points, along with lower latency in the compression of ViT and its variants.

关键词： Training computer vision Accuracy Computational modeling Transformers pattern recognition Complexity theory

来源：评论

学校读者我要写书评

暂无评论

From Semantic Categories to Fixations: A Novel Weakly-supervised Visual-auditory Saliency Detection Approach

From Semantic Categories to Fixations: A Novel Weakly-superv...

引用

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

作者： Wang, Guotao Chen, Chenglizhao Fan, Dengping Hao, Aimin Qin, Hong Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing Peoples R China Qingdao Univ Coll Comp Sci & Technol Qingdao Peoples R China Chinese Acad Med Sci Res Unit Virtual Human & Virtual Surg Beijing Peoples R China Incept Inst Artificial Intelligence Abu Dhabi U Arab Emirates SUNY Stony Brook Stony Brook NY 11794 USA Pengcheng Lab Shenzhen Peoples R China

ISBN: (纸本)9781665445092

Thanks to the rapid advances in the deep learning techniques and the wide availability of large-scale training sets, the performances of video saliency detection models have been improving steadily and significantly. However, the deep learning based visual-audio fixation prediction is still in its infancy. At present, only a few visual-audio sequences have been furnished with real fixations being recorded in the real visual-audio environment. Hence, it would be neither efficiency nor necessary to re-collect real fixations under the same visual-audio circumstance. To address the problem, this paper advocate a novel approach in a weakly-supervised manner to alleviating the demand of large-scale training sets for visual-audio model training. By using the video category tags only, we propose the selective class activation mapping (SCAM), which follows a coarse-to-fine strategy to select the most discriminative regions in the spatial-temporal-audio circumstance. Moreover, these regions exhibit high consistency with the real human-eye fixations, which could subsequently be employed as the pseudo GTs to train a new spatial-temporal-audio (STA) network. Without resorting to any real fixation, the performance of our STA network is comparable to that of the fully supervised ones.

关键词： Training Deep learning computer vision Codes Semantics pattern recognition Saliency detection

来源：评论

学校读者我要写书评

暂无评论

Seesaw Loss for Long-Tailed Instance Segmentation

Seesaw Loss for Long-Tailed Instance Segmentation

引用

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

作者： Wang, Jiaqi Zhang, Wenwei Zang, Yuhang Cao, Yuhang Pang, Jiangmiao Gong, Tao Chen, Kai Liu, Ziwei Loy, Chen Change Lin, Dahua Chinese Univ Hong Kong SenseTime CUHK Joint Lab Hong Kong Peoples R China Nanyang Technol Univ S Lab Singapore Singapore SenseTime Res Shanghai Peoples R China Shanghai AI Lab Shanghai Peoples R China Zhejiang Univ Hangzhou Peoples R China Univ Sci & Technol China Hefei Peoples R China

ISBN: (纸本)9781665445092

Instance segmentation has witnessed a remarkable progress on class-balanced benchmarks. However, they fail to perform as accurately in real-world scenarios, where the category distribution of objects naturally comes with a long tail. Instances of head classes dominate a long-tailed dataset and they serve as negative samples of tail categories. The overwhelming gradients of negative samples on tail classes lead to a biased learning process for classifiers. Consequently, objects of tail categories are more likely to be misclassified as backgrounds or head categories. To tackle this problem, we propose Seesaw Loss to dynamically re-balance gradients of positive and negative samples for each category, with two complementary factors, i.e., mitigation factor and compensation factor. The mitigation factor reduces punishments to tail categories w.r.t. the ratio of cumulative training instances between different categories. Meanwhile, the compensation factor increases the penalty of misclassified instances to avoid false positives of tail categories. We conduct extensive experiments on Seesaw Loss with mainstream frameworks and different data sampling strategies. With a simple end-to-end training pipeline, Seesaw Loss obtains significant gains over Cross-Entropy Loss, and achieves state-of-the-art performance on LVIS dataset without bells and whistles. Code is available at https://***/open- mmlab/mmdetection.

关键词： Training computer vision Codes Pipelines Benchmark testing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

PaReNeRF: Toward Fast Large-Scale Dynamic NeRF with Patch-Based Reference

PaReNeRF: Toward Fast Large-Scale Dynamic NeRF with Patch-Ba...

引用

conference on computer vision and pattern recognition (cvpr)

作者： Xiao Tang Min Yang Penghui Sun Hui Li Yuchao Dai Feng Zhu Hojae Lee Samsung R&D Institute China Xi'an (SRCX) Northwestern Polytechnical University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

With photo-realistic image generation, Neural Radiance Field (NeRF) is widely used for large-scale dynamic scene reconstruction as autonomous driving simulator. However, large-scale scene reconstruction still suffers from extremely long training time and rendering time. Low-resolution (L-R) rendering combined with upsampling can alleviate this problem but it degrades image quality. In this paper, we design a lightweight reference decoder which exploits prior information from known views to improve image reconstruction quality of new views. In addition, to speed up prior information search, we propose an optical flow and structural similarity based prior information search method. Results on KITTI and VKITTI2 datasets show that our method significantly outperforms the baseline method in terms of training speed, rendering speed and rendering quality.

关键词： Training Search methods Rendering (computer graphics) Neural radiance field Real-time systems Decoding pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Locate then Segment: A Strong Pipeline for Referring Image Segmentation

Locate then Segment: A Strong Pipeline for Referring Image S...

引用

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

作者： Jing, Ya Kong, Tao Wang, Wei Wang, Liang Li, Lei Tan, Tieniu Chinese Acad Sci CASIA Ctr Res Intelligent Percept & Comp CRIPAC Natl Lab Pattern Recognit NLPR Inst Automat Beijing Peoples R China Univ Chinese Acad Sci UCAS Sch Artificial Intelligence Beijing Peoples R China ByteDance AI Lab Beijing Peoples R China

ISBN: (纸本)9781665445092

Referring image segmentation aims to segment the objects referred by a natural language expression. Previous methods usually focus on designing an implicit and recurrent feature interaction mechanism to fuse the visuallinguistic features to directly generate the final segmentation mask without explicitly modeling the localization information of the referent instances. To tackle these problems, we view this task from another perspective by decoupling it into a "Locate-Then-Segment" (LTS) scheme. Given a language expression, people generally first perform attention to the corresponding target image regions, then generate a fine segmentation mask about the object based on its context. The LTS first extracts and fuses both visual and textual features to get a cross-modal representation, then applies a cross-model interaction on the visual-textual features to locate the referred object with position prior, and finally generates the segmentation result with a light-weight segmentation network. Our LTS is simple but surprisingly effective. On three popular benchmark datasets, the LTS outperforms all the previous state-of-the-arts methods by a large margin (e.g., +3.2% on RefCOCO+ and +3.4% on RefCOCOg). In addition, our model is more interpretable with explicitly locating the object, which is also proved by visualization experiments. We believe this framework is promising to serve as a strong baseline for referring image segmentation.

关键词： Location awareness Image segmentation Visualization Fuses Pipelines Object segmentation Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Adversarial Approach for Explaining the Predictions of Deep Neural Networks

An Adversarial Approach for Explaining the Predictions of De...

引用

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

作者： Rahnama, Arash Tseng, Andrew Modzy Vienna VA 22182 USA

ISBN: (纸本)9781665448994

Machine learning models have been successfully applied to a wide range of applications including computer vision, natural language processing, and speech recognition. A successful implementation of these models however, usually relies on deep neural networks (DNNs) which are treated as opaque black-box systems due to their incomprehensible complexity and intricate internal mechanism. In this work, we present a novel algorithm for explaining the predictions of a DNN using adversarial machine learning. Our approach identifies the relative importance of input features in relation to the predictions based on the behavior of an adversarial attack on the DNN. Our algorithm has the advantage of being fast, consistent, and easy to implement and interpret. We present our detailed analysis that demonstrates how the behavior of an adversarial attack, given a DNN and a task, stays consistent for any input test data point proving the generality of our approach. Our analysis enables us to produce consistent and efficient explanations. We illustrate the effectiveness of our approach by conducting experiments using a variety of DNNs, tasks, and datasets. Finally, we compare our work with other well-known techniques in the current literature.

关键词： Deep learning computer vision Machine learning algorithms Computational modeling conferences Speech recognition Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

A Generative Approach for Wikipedia-Scale Visual Entity recognition

A Generative Approach for Wikipedia-Scale Visual Entity Reco...

引用

conference on computer vision and pattern recognition (cvpr)

作者： Mathilde Caron Ahmet Iscen Alireza Fathi Cordelia Schmid Google Research

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

In this paper, we address web-scale visual entity recognition, specifically the task of mapping a given query image to one of the 6 million existing entities in Wikipedia. One way of approaching a problem of such scale is using dual-encoder models (e.g. CLIP), where all the entity names and query images are embedded into a unified space, paving the way for an approximate kNN search. Alternatively, it is also possible to re-purpose a captioning model to directly generate the entity names for a given image. In contrast, we introduce a novel Generative Entity recognition (GER)framework, which given an input image learns to auto-regressively decode a semantic and discriminative “code” identifying the target entity. Our experiments demonstrate the efficacy of this GER paradigm, showcasing state-of-the-art performance on the challenging OVEN benchmark. GER surpasses strong captioning, dual-encoder, visual matching and hier-archical classification baselines, affirming its advantage in tackling the complexities of web-scale recognition.

关键词： Visualization Codes Image recognition Target recognition Ovens Semantics Encyclopedias

来源：评论

学校读者我要写书评

暂无评论

Structured Gradient-Based Interpretations via Norm-Regularized Adversarial Training

Structured Gradient-Based Interpretations via Norm-Regulariz...

引用

conference on computer vision and pattern recognition (cvpr)

作者： Shizhan Gong Qi Dou Farzan Farnia The Chinese University of Hong Kong

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Gradient-based saliency maps have been widely used to explain the decisions of deep neural network classifiers. However, standard gradient-based interpretation maps, including the simple gradient and integrated gradient algorithms, often lack desired structures such as sparsity and connectedness in their application to real-world computer vision models. A frequently used approach to inducing sparsity structures into gradient-based saliency maps is to alter the simple gradient scheme using sparsification or norm-based regularization. A drawback with such post-processing methods is their frequently-observed significant loss in fidelity to the original simple gradient map. In this work, we propose to apply adversarial training as an inprocessing scheme to train neural networks with structured simple gradient maps. We show a duality relation between the regularized norms of the adversarial perturbations and gradient-based maps, based on which we design adversarial training loss functions promoting sparsity and group-sparsity properties in simple gradient maps. We present several numerical results to show the influence of our proposed norm-based adversarial training methods on the standard gradient-based maps of standard neural network architectures on benchmark image datasets 1 1 The paper's code is available at: https://***/peterant330/AdvGrad.

关键词： Training computer vision Perturbation methods Benchmark testing Stability analysis Robustness pattern recognition

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 << < 491 492 493 494 495 496 497 498 499 500 > >>

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：