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

29,393 篇 会议
1,358 册 图书
225 篇 期刊文献

馆藏范围

30,974 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

17,280 篇 工学
- 13,630 篇 计算机科学与技术...
- 5,193 篇 软件工程
- 2,983 篇 机械工程
- 2,643 篇 光学工程
- 1,421 篇 控制科学与工程
- 1,411 篇 电气工程
- 1,344 篇 信息与通信工程
- 656 篇 生物工程
- 577 篇 仪器科学与技术
- 513 篇 生物医学工程（可授...
- 468 篇 电子科学与技术（可...
- 251 篇 化学工程与技术
- 212 篇 安全科学与工程
- 140 篇 交通运输工程
- 132 篇 建筑学
- 123 篇 材料科学与工程（可...
- 119 篇 土木工程
5,054 篇 理学
- 3,127 篇 物理学
- 2,406 篇 数学
- 824 篇 生物学
- 802 篇 统计学（可授理学、...
- 299 篇 系统科学
- 228 篇 化学
3,831 篇 医学
- 3,799 篇 临床医学
- 185 篇 基础医学(可授医学...
- 140 篇 药学(可授医学、理...
1,059 篇 管理学
- 617 篇 图书情报与档案管...
- 467 篇 管理科学与工程(可...
- 145 篇 工商管理
373 篇 艺术学
- 373 篇 设计学（可授艺术学...
116 篇 法学
81 篇 农学
48 篇 教育学
43 篇 经济学
18 篇 军事学
8 篇 文学

主题

12,602 篇 computer vision
5,697 篇 pattern recognit...
3,180 篇 training
2,263 篇 cameras
2,178 篇 computational mo...
2,116 篇 feature extracti...
2,048 篇 image segmentati...
1,970 篇 visualization
1,967 篇 shape
1,642 篇 robustness
1,493 篇 layout
1,476 篇 three-dimensiona...
1,445 篇 computer science
1,338 篇 computer archite...
1,296 篇 object detection
1,220 篇 semantics
1,142 篇 face recognition
1,107 篇 conferences
1,077 篇 benchmark testin...
1,056 篇 humans

机构

137 篇 univ sci & techn...
134 篇 tsinghua univers...
134 篇 univ chinese aca...
118 篇 chinese univ hon...
101 篇 microsoft resear...
97 篇 zhejiang univers...
94 篇 national laborat...
93 篇 shanghai jiao to...
93 篇 zhejiang univ pe...
85 篇 university of sc...
79 篇 shanghai ai lab ...
78 篇 swiss fed inst t...
65 篇 microsoft res as...
62 篇 adobe research
62 篇 computer vision ...
61 篇 peking univ peop...
58 篇 univ oxford oxfo...
57 篇 google mountain ...
57 篇 hong kong univ s...
56 篇 google res mount...

作者

107 篇 umapada pal
81 篇 van gool luc
68 篇 zhang lei
59 篇 timofte radu
41 篇 yang yi
37 篇 loy chen change
37 篇 hanqing lu
33 篇 liu yang
33 篇 xiaoou tang
32 篇 nassir navab
32 篇 wang liang
30 篇 tian qi
29 篇 h. bischof
29 篇 jan-michael frah...
29 篇 vittorio murino
29 篇 darrell trevor
27 篇 li xin
27 篇 vasconcelos nuno
27 篇 murino vittorio
27 篇 chen chen

语言

30,833 篇 英文
92 篇 中文
73 篇 其他
6 篇 土耳其文
2 篇 日文
2 篇 俄文
1 篇 西班牙文

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

共 30976 条记录，以下是4861-4870 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：

Unsupervised Learning of Debiased Representations with Pseudo-Attributes

Unsupervised Learning of Debiased Representations with Pseud...

引用

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

作者： Seo, Seonguk Lee, Joon-Young Han, Bohyung Seoul Natl Univ ECE Seoul South Korea Seoul Natl Univ ASRI Seoul South Korea Seoul Natl Univ IPAL Seoul South Korea Adobe Res San Jose CA USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Dataset bias is a critical challenge in machine learning since it often leads to a negative impact on a model due to the unintended decision rules captured by spurious correlations. Although existing works often handle this issue based on human supervision, the availability of the proper annotations is impractical and even unrealistic. To better tackle the limitation, we propose a simple but effective unsupervised debiasing technique. Specifically, we first identify pseudoattributes based on the results from clustering performed in the feature embedding space even without an explicit bias attribute supervision. Then, we employ a novel cluster-wise reweighting scheme to learn debiased representation;the proposed method prevents minority groups from being discounted for minimizing the overall loss, which is desirable for worst-case generalization. The extensive experiments demonstrate the outstanding performance of our approach on multiple standard benchmarks, even achieving the competitive accuracy to the supervised counterpart. The source code is available at our project page(1).

关键词： computer vision Correlation Codes Annotations Computational modeling Machine learning Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Masked-attention Mask Transformer for Universal Image Segmentation

Masked-attention Mask Transformer for Universal Image Segmen...

引用

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

作者： Cheng, Bowen Misra, Ishan Schwing, Alexander G. Kirillov, Alexander Girdhar, Rohit Facebook AI Res FAIR Menlo Pk CA 94025 USA Univ Illinois Urbana Champaign UIUC Champaign IL 61820 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Image segmentation groups pixels with different semantics, e.g., category or instance membership. Each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing specialized architectures for each task. We present Masked-attention Mask Transformer (Mask2Former), a new architecture capable of addressing any image segmentation task (panoptic, instance or semantic). Its key components include masked attention, which extracts localized features by constraining cross-attention within predicted mask regions. In addition to reducing the research effort by at least three times, it outperforms the best specialized architectures by a significant margin on four popular datasets. Most notably, Mask2Former sets a new state-of-the-art for panoptic segmentation (57.8 PQ on COCO), instance segmentation (50.1 AP on COCO) and semantic segmentation (57.7 mIoU on ADE20K).

关键词： Image segmentation Shape Computational modeling Semantics computer architecture Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations 30

Efficient Diffusion on Region Manifolds: Recovering Small Ob...

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Iscen, Ahmet Tolias, Giorgos Avrithis, Yannis Furon, Teddy Chum, Ondrej Inria Rennes Rennes France CTU FEE VRG Prague Czech Republic

ISBN: (纸本)9781538604571

Query expansion is a popular method to improve the quality of image retrieval with both conventional and CNN representations. It has been so far limited to global image similarity. This work focuses on diffusion, a mechanism that captures the image manifold in the feature space. The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches. An efficient off-line stage allows optional reduction in the number of stored regions. In the on-line stage, the proposed handling of unseen queries in the indexing stage removes additional computation to adjust the precomputed data. We perform diffusion through a sparse linear system solver, yielding practical query times well below one second. Experimentally, we observe a significant boost in performance of image retrieval with compact CNN descriptors on standard benchmarks, especially when the query object covers only a small part of the image. Small objects have been a common failure case of CNN-based retrieval.

关键词： IMAGING MANIFOLD diffusion CASING FAILURE image retrieval Quantum efficiency Descriptors region of an image Eigenvector Small parts Compact Compact pattern representations Manifolds RECOVERING Imagery (Psychotherapy)

来源：评论

学校读者我要写书评

暂无评论

A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Network

A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neu...

引用

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

作者： Ma, Ruichen Qiao, Guanchao Liu, Yian Meng, Liwei Ning, Ning Liu, Yang Hu, Shaogang Univ Elect Sci & Technol China Chengdu Peoples R China

ISBN: (纸本)9798350353013;9798350353006

Binary neural networks utilize 1-bit quantized weights and activations to reduce both the model's storage demands and computational burden. However, advanced binary architectures still incorporate millions of inefficient and non-hardware-friendly full-precision multiplication operations. A&B BNN is proposed to directly remove part of the multiplication operations in a traditional BNN and replace the rest with an equal number of bit operations, introducing the mask layer and the quantized RPReLU structure based on the normalizer-free network architecture. The mask layer can be removed during inference by leveraging the intrinsic characteristics of BNN with straightforward mathematical transformations to avoid the associated multiplication operations. The quantized RPReLU structure enables more efficient bit operations by constraining its slope to be integer powers of 2. Experimental results achieved 92.30%, 69.35%, and 66.89% on the CIFAR-10, CIFAR-100, and ImageNet datasets, respectively, which are competitive with the state-of-the-art. Ablation studies have verified the efficacy of the quantized RPReLU structure, leading to a 1.14% enhancement on the ImageNet compared to using a fixed slope RLeakyReLU. The proposed add&bit-operation-only BNN offers an innovative approach for hardware-friendly network architecture.

关键词： Binary neural networks Hardware-friendly structure Multiplication-free structure pattern recognition

来源：评论

学校读者我要写书评

暂无评论

GLID: Pre-training a Generalist Encoder-Decoder vision Model

GLID: Pre-training a Generalist Encoder-Decoder Vision Model

引用

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

作者： Liu, Jihao Zheng, Jinliang Liu, Yu Li, Hongsheng CUHK MMLab Hong Kong Peoples R China SenseTime Res Hong Kong Peoples R China Shanghai AI Lab Shanghai Peoples R China CPII InnoHK Hong Kong Peoples R China Tsinghua Univ Inst AI Ind Res AIR Shanghai Peoples R China

ISBN: (纸本)9798350353006

This paper proposes a GeneraLIst encoder-Decoder (GLID) pre-training method for better handling various downstream computer vision tasks. While self-supervised pre-training approaches, e.g., Masked Autoencoder, have shown success in transfer learning, task-specific sub-architectures are still required to be appended for different downstream tasks, which cannot enjoy the benefits of large-scale pre-training. GLID overcomes this challenge by allowing the pre-trained generalist encoder-decoder to be fine-tuned on various vision tasks with minimal task-specific architecture modifications. In the GLID training scheme, pre-training pretext task and other downstream tasks are modeled as "query-to-answer" problems, including the pre-training pretext task and other downstream tasks. We pre-train a task-agnostic encoder-decoder with query-mask pairs. During fine-tuning, GLID maintains the pre-trained encoder-decoder and queries, only replacing the topmost linear transformation layer with task-specific linear heads. This minimizes the pretrain-finetune architecture inconsistency and enables the pre-trained model to better adapt to downstream tasks. GLID achieves competitive performance on various vision tasks, including object detection, image segmentation, pose estimation, and depth estimation, outper-forming or matching specialist models such as Mask2Former, DETR, ViTPose, and BinsFormer.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep-BCN: Deep networks meet biased competition to create a brain-inspired model of attention control 31

Deep-BCN: Deep networks meet biased competition to create a ...

引用

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

作者： Adeli, Hossein Zelinsky, Gregory SUNY Stony Brook Stony Brook NY 11794 USA

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

The mechanism of attention control is best described by biased-competition theory (BCT), which suggests that a top-down goal state biases a competition among object representations for the selective routing of a visual input for classification. Our work advances this theory by making it computationally explicit as a deep neural network (DNN) model, thereby enabling predictions of goal-directed attention control using real-world stimuli. This model, which we call Deep-BCN, is built on top of an 8-layer DNN pre-trained for object classification, but has layers mapped to early visual (V1, V2/V3, V4), ventral (PIT, AIT), and frontal (PFC) brain areas that have their functional connectivity informed by BCT. Deep-BCN also has a superior colliculus and a frontal-eye field, and can therefore make eye movements. We compared Deep-BCN's eye movements to those made from 15 people performing a categorical search for one of 25 target object categories, and found that it predicted both the number of fixations during search and the saccade-distance travelled before search termination. With Deep-BCN a DNN implementation of BCT now exists, which can be used to predict the neural and behavioral responses of an attention control mechanism as it mediates a goal-directed behavior-in our study the eye movements made in search of a target goal.

关键词： Visualization Brain modeling Computational modeling Object detection Search problems computer vision

来源：评论

学校读者我要写书评

暂无评论

What Should Be Equivariant In Self-Supervised Learning

What Should Be Equivariant In Self-Supervised Learning

引用

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

作者： Xie, Yuyang Wen, Jianhong Lau, Kin Wai Rehman, Yasar Abbas Ur Shen, Jiajun TCL AI Lab Hong Kong Peoples R China Fuzhou Univ Fuzhou Peoples R China City Univ Hong Kong Hong Kong Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Self-supervised learning (SSL) aims to learn feature representation without human-annotated data. Existing methods approach this goal by encouraging the feature representations to be invariant under a set of task-irrelevant transformations and distortions defined a priori. However, multiple studies have shown that such an assumption often limits the expressive power of the representations and model would perform poorly when downstream tasks violate this assumption. For example, being invariant to rotations would prevent features from retaining enough information to estimate object rotation angles. This suggests additional manual work and domain knowledge are required for selecting augmentation types during SSL. In this work, we relax the transformation-invariance assumption by introducing a SSL framework that encourages the feature representations to preserve the order of transformation scale in embedding space for some transformations while maintaining invariance to other transformations. This allows the learned feature representations to retain information about task-relevant transformations. In addition, this framework gives rise to a handy mechanism to determine the augmentation types to which the features representations should be invariant and equivariant during SSL. We demonstrate the effectiveness of our method on various datasets such as Fruits 360, Caltech-UCSD Birds 200, and Blood cells dataset.

关键词： computer vision conferences Self-supervised learning Cells (biology) Feature extraction Distortion Birds

来源：评论

学校读者我要写书评

暂无评论

Cross-MPI: Cross-scale Stereo for Image Super-Resolution using Multiplane Images

Cross-MPI: Cross-scale Stereo for Image Super-Resolution usi...

引用

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

作者： Zhou, Yuemei Wu, Gaochang Fu, Ying Li, Kun Liu, Yebin Tsinghua Univ Beijing Peoples R China ZhuoHe Tech Beijing Peoples R China Northeastern Univ Boston MA 02115 USA Beijing Inst Technol Beijing Peoples R China Tianjin Univ Tianjin Peoples R China

ISBN: (纸本)9781665445092

Various combinations of cameras enrich computational photography, among which reference-based superresolution (RefSR) plays a critical role in multiscale imaging systems. However, existing RefSR approaches fail to accomplish high-fidelity super-resolution under a large resolution gap, e.g., 8x upscaling, due to the lower consideration of the underlying scene structure. In this paper, we aim to solve the RefSR problem in actual multiscale camera systems inspired by multiplane image (MPI) representation. Specifically, we propose Cross-MPI, an end-to-end RefSR network composed of a novel plane-aware attention-based MPI mechanism, a multiscale guided upsampling module as well as a super-resolution (SR) synthesis and fusion module. Instead of using a direct and exhaustive matching between the cross-scale stereo, the proposed plane-aware attention mechanism fully utilizes the concealed scene structure for efficient attention-based correspondence searching. Further combined with a gentle coarse-to-fine guided upsampling strategy, the proposed Cross-MPI can achieve a robust and accurate detail transmission. Experimental results on both digitally synthesized and optical zoom cross-scale data show that the Cross-MPI framework can achieve superior performance against the existing RefSR methods and is a real fit for actual multiscale camera systems even with large-scale differences.

关键词： Photography computer vision Optical design Superresolution Cameras Optical imaging pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Patch2Pix: Epipolar-Guided Pixel-Level Correspondences

Patch2Pix: Epipolar-Guided Pixel-Level Correspondences

引用

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

作者： Zhou, Qunjie Sattler, Torsten Leal-Taixe, Laura Tech Univ Munich Munich Germany Czech Tech Univ CIIRC Prague Czech Republic

ISBN: (纸本)9781665445092

The classical matching pipeline used for visual localization typically involves three steps: (i) local feature detection and description, (ii) feature matching, and (iii) outlier rejection. Recently emerged correspondence networks propose to perform those steps inside a single network but suffer from low matching resolution due to the memory bottle-neck. In this work, we propose a new perspective to estimate correspondences in a detect-to-refine manner, where we first predict patch-level match proposals and then refine them. We present Patch2Pix, a novel refinement network that refines match proposals by regressing pixel-level matches from the local regions defined by those proposals and jointly rejecting outlier matches with confidence scores. Patch2Pix is weakly supervised to learn correspondences that are consistent with the epipolar geometry of an input image pair. We show that our refinement network significantly improves the performance of correspondence networks on image matching, homography estimation, and localization tasks. In addition, we show that our learned refinement generalizes to fully-supervised methods without retraining, which leads us to state-of-the-art localization performance.

关键词： Location awareness Geometry Visualization Semantics Pipelines Predictive models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Learning to Segment the Tail

Learning to Segment the Tail

引用

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

作者： Hu, Xinting Jiang, Yi Tang, Kaihua Chen, Jingyuan Miao, Chunyan Zhang, Hanwang Nanyang Technol Univ Singapore Singapore Alibaba Grp Hangzhou Zhejiang Peoples R China Alibaba Grp Damo Acad Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781728171685

Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data. We propose a "divide&conquer" strategy for the challenging LVIS task: divide the whole data into balanced parts and then apply incremental learning to conquer each one. This derives a novel learning paradigm: class-incremental fewshot learning, which is especially effective for the challenge evolving over time: 1) the class imbalance among the oldclass knowledge review and 2) the few-shot data in new class learning. We call our approach Learning to Segment the Tail (LST). In particular, we design an instance-level balanced replay scheme, which is a memory-efficient approximation to balance the instance-level samples from the old-class images. We also propose to use a meta-module for new-class learning, where the module parameters are shared across incremental phases, gaining the learning-to learn knowledge incrementally, from the data-rich head to the data-poor tail. We empirically show that: at the expense of a little sacrifice of head-class forgetting, we can gain a significant 8.3% AP improvement for the tail classes with less than 10 instances, achieving an overall 2.0% AP boost for the whole 1,230 classes'.

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 << < 483 484 485 486 487 488 489 490 491 492 > >>

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：