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

11,884 篇 会议
5 篇 期刊文献

馆藏范围

11,889 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,055 篇 工学
- 7,613 篇 计算机科学与技术...
- 796 篇 机械工程
- 688 篇 电气工程
- 356 篇 软件工程
- 225 篇 控制科学与工程
- 40 篇 光学工程
- 19 篇 生物工程
- 17 篇 信息与通信工程
- 12 篇 生物医学工程（可授...
- 6 篇 电子科学与技术（可...
- 6 篇 建筑学
- 6 篇 交通运输工程
- 5 篇 仪器科学与技术
- 5 篇 化学工程与技术
- 5 篇 安全科学与工程
- 4 篇 土木工程
3,344 篇 医学
- 3,343 篇 临床医学
- 4 篇 基础医学(可授医学...
- 4 篇 公共卫生与预防医...
250 篇 理学
- 198 篇 系统科学
- 29 篇 物理学
- 21 篇 生物学
- 15 篇 数学
- 9 篇 统计学（可授理学、...
- 4 篇 化学
17 篇 管理学
- 12 篇 管理科学与工程(可...
- 7 篇 图书情报与档案管...
- 5 篇 工商管理
3 篇 法学
- 3 篇 社会学
3 篇 教育学
- 3 篇 教育学
2 篇 农学
1 篇 经济学
1 篇 军事学

主题

5,633 篇 computer vision
2,668 篇 training
2,203 篇 pattern recognit...
1,747 篇 computational mo...
1,502 篇 visualization
1,360 篇 three-dimensiona...
1,074 篇 semantics
999 篇 benchmark testin...
986 篇 codes
959 篇 computer archite...
891 篇 deep learning
777 篇 conferences
754 篇 task analysis
700 篇 feature extracti...
561 篇 transformers
533 篇 face recognition
527 篇 neural networks
495 篇 object detection
490 篇 image segmentati...
468 篇 cameras

机构

174 篇 univ sci & techn...
145 篇 carnegie mellon ...
144 篇 univ chinese aca...
144 篇 tsinghua univ pe...
134 篇 chinese univ hon...
110 篇 zhejiang univ pe...
109 篇 peng cheng lab p...
99 篇 swiss fed inst t...
91 篇 tsinghua univers...
90 篇 shanghai ai lab ...
87 篇 sensetime res pe...
86 篇 shanghai jiao to...
83 篇 zhejiang univers...
82 篇 tech univ munich...
79 篇 university of sc...
79 篇 stanford univ st...
78 篇 univ hong kong p...
77 篇 australian natl ...
76 篇 alibaba grp peop...
75 篇 peng cheng labor...

作者

75 篇 timofte radu
64 篇 van gool luc
50 篇 zhang lei
43 篇 yang yi
37 篇 loy chen change
36 篇 tao dacheng
32 篇 zhou jie
31 篇 chen chen
30 篇 liu yang
30 篇 tian qi
29 篇 sun jian
29 篇 zha zheng-jun
28 篇 li xin
27 篇 qi tian
26 篇 vasconcelos nuno
25 篇 liu xiaoming
25 篇 darrell trevor
24 篇 zheng wei-shi
24 篇 luo ping
24 篇 ying shan

语言

11,863 篇 英文
25 篇 其他
1 篇 中文

检索条件"任意字段=2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024"

共 11889 条记录，以下是4911-4920 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：

Boosting Self-Supervised Learning via Knowledge Transfer 31

Boosting Self-Supervised Learning via Knowledge Transfer

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Noroozi, Mehdi Vinjimoor, Ananth Favaro, Paolo Pirsiavash, Hamed Univ Bern Bern Switzerland Univ Maryland Baltimore Cty Baltimore MD 21228 USA

ISBN: (纸本)9781538664209

In self-supervised learning, one trains a model to solve a so-called pretext task on a dataset without the need for human annotation. The main objective, however, is to transfer this model to a target domain and task. Currently, the most effective transfer strategy is fine-tuning, which restricts one to use the same model or parts thereof for both pretext and target tasks. In this paper, we present a novel framework for self-supervised learning that overcomes limitations in designing and comparing different tasks, models, and data domains. In particular, our framework decouples the structure of the self-supervised model from the final task-specific fine-tuned model. This allows us to: 1) quantitatively assess previously incompatible models including handcrafted features;2) show that deeper neural network models can learn better representations from the same pretext task;3) transfer knowledge learned with a deep model to a shallower one and thus boost its learning. We use this framework to design a novel self-supervised task, which achieves state-of-the-art performance on the common benchmarks in PASCAL VOC 2007, ILSVRC12 and Places by a significant margin. Our learned features shrink the mAP gap between models trained via self-supervised learning and supervised learning from 5.9% to 2.6% in object detection on PASCAL VOC 2007.

关键词： Task analysis computer architecture Computational modeling Training Feature extraction Data models Measurement

来源：评论

学校读者我要写书评

暂无评论

Balanced Product of Calibrated Experts for Long-Tailed recognition

Balanced Product of Calibrated Experts for Long-Tailed Recog...

引用

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

作者： Aimar, Emanuel Sanchez Jonnarth, Arvi Felsberg, Michael Kuhlmann, Marco Linkoping Univ Dept Elect Engn Linkoping Sweden Linkoping Univ Dept Comp & Informat Sci Linkoping Sweden Husqvarna Grp Huskvarna Sweden Univ KwaZulu Natal Durban South Africa

ISBN: (纸本)9798350301298

Many real-world recognition problems are characterized by long-tailed label distributions. These distributions make representation learning highly challenging due to limited generalization over the tail classes. If the test distribution differs from the training distribution, e.g. uniform versus long-tailed, the problem of the distribution shift needs to be addressed. A recent line of work proposes learning multiple diverse experts to tackle this issue. Ensemble diversity is encouraged by various techniques, e.g. by specializing different experts in the head and the tail classes. In this work, we take an analytical approach and extend the notion of logit adjustment to ensembles to form a Balanced Product of Experts (BalPoE). BalPoE combines a family of experts with different test-time target distributions, generalizing several previous approaches. We show how to properly define these distributions and combine the experts in order to achieve unbiased predictions, by proving that the ensemble is Fisher-consistent for minimizing the balanced error. Our theoretical analysis shows that our balanced ensemble requires calibrated experts, which we achieve in practice using mixup. We conduct extensive experiments and our method obtains new state-of-the-art results on three long-tailed datasets: CIFAR-100-LT, ImageNet-LT, and iNaturalist-2018. Our code is available at https://***/emasa/BalPoE-CalibratedLT.

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

Bias Mimicking: A Simple Sampling Approach for Bias Mitigation

Bias Mimicking: A Simple Sampling Approach for Bias Mitigati...

引用

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

作者： Qraitem, Maan Saenko, Kate Plummer, Bryan A. Boston Univ Boston MA 02215 USA MIT IBM Watson Lab Cambridge MA USA

ISBN: (纸本)9798350301298

Prior work has shown that Visual recognition datasets frequently underrepresent bias groups B (e.g. Female) within class labels Y (e.g. Programmers). This dataset bias can lead to models that learn spurious correlations between class labels and bias groups such as age, gender, or race. Most recent methods that address this problem require significant architectural changes or additional loss functions requiring more hyper-parameter tuning. Alternatively, data sampling baselines from the class imbalance literature (e.g. Undersampling, Upweighting), which can often be implemented in a single line of code and often have no hyper-parameters, offer a cheaper and more efficient solution. However, these methods suffer from significant shortcomings. For example, Undersampling drops a significant part of the input distribution per epoch while Oversampling repeats samples, causing overfitting. To address these shortcomings, we introduce a new class-conditioned sampling method: Bias Mimicking. The method is based on the observation that if a class c bias distribution, i.e. PD(B| Y = c) is mimicked across every c ' not equal c, then Y and B are statistically independent. Using this notion, BM, through a novel training procedure, ensures that the model is exposed to the entire distribution per epoch without repeating samples. Consequently, Bias Mimicking improves underrepresented groups' accuracy of sampling methods by 3% over four benchmarks while maintaining and sometimes improving performance over nonsampling methods. Code: https: //***/mqraitem/Bias-Mimicking

关键词： accountability accountability ethics in vision fairness privacy Transparency

来源：评论

学校读者我要写书评

暂无评论

Generalizing Face Forgery Detection with High-frequency Features

Generalizing Face Forgery Detection with High-frequency Feat...

引用

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

作者： Luo, Yuchen Zhang, Yong Yan, Junchi Liu, Wei Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai Peoples R China Shanghai Jiao Tong Univ MoE Key Lab Artificial Intelligence AI Inst Shanghai Peoples R China Tencent AI Lab Bellevue WA USA Tencent Data Platform Shenzhen Peoples R China

ISBN: (纸本)9781665445092

Current face forgery detection methods achieve high accuracy under the within-database scenario where training and testing forgeries are synthesized by the same algorithm. However, few of them gain satisfying performance under the cross-database scenario where training and testing forgeries are synthesized by different algorithms. In this paper, we find that current CNN-based detectors tend to overfit to method-specific color textures and thus fail to generalize. Observing that image noises remove color textures and expose discrepancies between authentic and tampered regions, we propose to utilize the high-frequency noises for face forgery detection. We carefully devise three functional modules to take full advantage of the high-frequency features. The first is the multi-scale high-frequency feature extraction module that extracts high-frequency noises at multiple scales and composes a novel modality. The second is the residual-guided spatial attention module that guides the low-level RGB feature extractor to concentrate more on forgery traces from a new perspective. The last is the cross-modality attention module that leverages the correlation between the two complementary modalities to promote feature learning for each other. Comprehensive evaluations on several benchmark databases corroborate the superior generalization performance of our proposed method.

关键词： Training Correlation Image color analysis Databases Face recognition Detectors Feature extraction

来源：评论

学校读者我要写书评

暂无评论

ArtEmis: Affective Language for Visual Art

ArtEmis: Affective Language for Visual Art

引用

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

作者： Achlioptas, Panos Ovsjanikov, Maks Haydarov, Kilichbek Elhoseiny, Mohamed Guibas, Leonidas Stanford Univ Stanford CA 94305 USA IP Paris Ecole Polytech LIX Paris France King Abdullah Univ Sci & Technol KAUST Thuwal Saudi Arabia

ISBN: (纸本)9781665445092

We present a novel large-scale dataset and accompanying machine learning models aimed at providing a detailed understanding of the interplay between visual content, its emotional effect, and explanations for the latter in language. In contrast to most existing annotation datasets in computer vision, we focus on the affective experience triggered by visual artworks and ask the annotators to indicate the dominant emotion they feel for a given image and, crucially, to also provide a grounded verbal explanation for their emotion choice. As we demonstrate below, this leads to a rich set of signals for both the objective content and the affective impact of an image, creating associations with abstract concepts (e.g., "freedom" or "love"), or references that go beyond what is directly visible, including visual similes and metaphors, or subjective references to personal experiences. We focus on visual art (e.g., paintings, artistic photographs) as it is a prime example of imagery created to elicit emotional responses from its viewers. Our dataset, termed ArtEmis, contains 455K emotion attributions and explanations from humans, on 80K artworks from WikiArt. Building on this data, we train and demonstrate a series of captioning systems capable of expressing and explaining emotions from visual stimuli. Remarkably, the captions produced by these systems often succeed in reflecting the semantic and abstract content of the image, going well beyond systems trained on existing datasets.

关键词： Visualization computer vision Art Computational modeling Semantics Machine learning Transformers

来源：评论

学校读者我要写书评

暂无评论

Scene Representation in Bird's-Eye View from Surrounding Cameras with Transformers

Scene Representation in Bird's-Eye View from Surrounding Cam...

引用

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

作者： Zhao, Yun Zhang, Yu Gong, Zhan Zhu, Hong Inspur Elect Informat Ind Co Ltd Dept AI & HPC Beijing Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Scene representation in the bird's-eye-view (BEV) coordinate frame provides a succinct and effective way to understand surrounding environments for autonomous vehicles and robotics. In this work, we present an end-to-end architecture to generate the BEV representation from surrounding cameras. To generate the BEV representation, we propose a transformer-based encoder-decoder structure to translate the image features from different cameras into the BEV frame, which takes advantage of the context information in the individual image and the relationship between images in different views. We perform multiple semantic segmentation tasks using the BEV features. Experimental results show that our model outperforms the competitive baseline [20], which demonstrates the effectiveness and efficiency of our method.

关键词： Image segmentation Image coding Computational modeling Semantics Robot vision systems Predictive models Cameras

来源：评论

学校读者我要写书评

暂无评论

Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos

Motion-from-Blur: 3D Shape and Motion Estimation of Motion-b...

引用

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

作者： Rozumnyi, Denys Oswald, Martin R. Ferrari, Vittorio Pollefeys, Marc Swiss Fed Inst Technol Dept Comp Sci Zurich Switzerland Univ Amsterdam Amsterdam Netherlands Google Res Mountain View CA USA Czech Tech Univ Prague Czech Republic

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We propose a method for jointly estimating the 3D motion, 3D shape, and appearance of highly motion-blurred objects from a video. To this end, we model the blurred appearance of a fast moving object in a generative fashion by parametrizing its 3D position, rotation, velocity, acceleration, bounces, shape, and texture over the duration of a predefined time window spanning multiple frames. Using differentiable rendering, we are able to estimate all parameters by minimizing the pixel-wise reprojection error to the input video via backpropagating through a rendering pipeline that accounts for motion blur by averaging the graphics output over short time intervals. For that purpose, we also estimate the camera exposure gap time within the same optimization. To account for abrupt motion changes like bounces, we model the motion trajectory as a piece-wise polynomial, and we are able to estimate the specific time of the bounce at sub frame accuracy. Experiments on established benchmark datasets demonstrate that our method outperforms previous methods for fast moving object deblurring and 3D reconstruction.

关键词： Solid modeling Three-dimensional displays Shape Motion estimation Pipelines Rendering (computer graphics) Cameras

来源：评论

学校读者我要写书评

暂无评论

Scale-Equivalent Distillation for Semi-Supervised Object Detection

Scale-Equivalent Distillation for Semi-Supervised Object Det...

引用

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

作者： Guo, Qiushan Mu, Yao Chen, Jianyu Wang, Tianqi Yu, Yizhou Luo, Ping Univ Hong Kong Hong Kong Peoples R China Tsinghua Univ Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, i.e., generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. Although they achieved certain success, the limited labeled data in semi-supervised learning scales up the challenges of object detection. We analyze the challenges these methods meet with the empirical experiment results. We find that the massive False Negative samples and inferior localization precision lack consideration. Besides, the large variance of object sizes and class imbalance (i.e., the extreme ratio between background and object) hinder the performance of prior arts. Further, we overcome these challenges by introducing a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance. SED has several appealing benefits compared to the previous works. (1) SED imposes a consistency regularization to handle the large scale variance problem. (2) SED alleviates the noise problem from the False Negative samples and inferior localization precision. (3) A re-weighting strategy can implicitly screen the potential foreground regions of the unlabeled data to reduce the effect of class imbalance. Extensive experiments show that SED consistently outperforms the recent state-of-the-art methods on different datasets with significant margins. For example, it surpasses the supervised counterpart by more than 10 mAP when using 5% and 10% labeled data on MS-COCO.

关键词： Location awareness Estimation Object detection Detectors Semisupervised learning Data models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

X-MAN: Explaining multiple sources of anomalies in video

X-MAN: Explaining multiple sources of anomalies in video

引用

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

作者： Szymanowicz, Stanislaw Charles, James Cipolla, Roberto Univ Cambridge Cambridge England

ISBN: (纸本)9781665448994

Our objective is to detect anomalies in video while also automatically explaining the reason behind the detector's response. In a practical sense, explainability is crucial for this task as the required response to an anomaly depends on its nature and severity. However, most leading methods (based on deep neural networks) are not interpretable and hide the decision making process in uninterpretable feature representations. In an effort to tackle this problem we make the following contributions: (1) we show how to build interpretable feature representations suitable for detecting anomalies with state of the art performance, (2) we propose an interpretable probabilistic anomaly detector which can describe the reason behind it's response using high level concepts, (3) we are the first to directly consider object interactions for anomaly detection and (4) we propose a new task of explaining anomalies and release a large dataset for evaluating methods on this task. Our method competes well with the state of the art on public datasets while also providing anomaly explanation based on objects and their interactions.

关键词： Training Deep learning Decision making Detectors Probabilistic logic Feature extraction pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Feature Erasing and Diffusion Network for Occluded Person Re-Identification

Feature Erasing and Diffusion Network for Occluded Person Re...

引用

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

作者： Wang, Zhikang Zhu, Feng Tang, Shixiang Zhao, Rui He, Lihuo Song, Jiangning Monash Univ Clayton Vic Australia SenseTime Res Hong Kong Peoples R China Univ Sydney Sydney NSW Australia Shanghai Jiao Tong Univ Qing Yuan Res Inst Shanghai Peoples R China Xidian Univ Xian Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Occluded person re-identification (ReID) aims at matching occluded person images to holistic ones across different camera views. Target Pedestrians (TP) are often disturbed by Non-Pedestrian Occlusions (NPO) and Non-Target Pedestrians (NTP). Previous methods mainly focus on increasing the model's robustness against NPO while ignoring feature contamination from NTP. In this paper, we propose a novel Feature Erasing and Diffusion Network (FED) to simultaneously handle challenges from NPO and NTP. Specifically, aided by the NPO augmentation strategy that simulates NPO on holistic pedestrian images and generates precise occlusion masks, NPO features are explicitly eliminated by our proposed Occlusion Erasing Module (OEM). Subsequently, we diffuse the pedestrian representations with other memorized features to synthesize the NTP characteristics in the feature space through the novel Feature Diffusion Module (FDM). With the guidance of the occlusion scores from OEM, the feature diffusion process is conducted on visible body parts, thereby improving the quality of the synthesized NTP characteristics. We can greatly improve the model's perception ability towards TP and alleviate the influence of NPO and NTP by jointly optimizing OEM and FDM. Furthermore, the proposed FDM works as an auxiliary module for training and will not be engaged in the inference phase, thus with high flexibility. Experiments on occluded and holistic person ReID benchmarks demonstrate the superiority of FED over state-of-the-art methods.

关键词： Training Representation learning Deep learning computer vision Diffusion processes Benchmark testing Robustness

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 << < 488 489 490 491 492 493 494 495 496 497 > >>

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：