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

20,994 篇 会议
99 册 图书
86 篇 期刊文献
1 篇 学位论文

馆藏范围

21,179 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,604 篇 工学
- 11,179 篇 计算机科学与技术...
- 2,631 篇 机械工程
- 2,542 篇 软件工程
- 990 篇 光学工程
- 850 篇 电气工程
- 676 篇 控制科学与工程
- 487 篇 信息与通信工程
- 242 篇 仪器科学与技术
- 215 篇 测绘科学与技术
- 159 篇 生物医学工程（可授...
- 150 篇 生物工程
- 139 篇 电子科学与技术（可...
- 69 篇 安全科学与工程
- 67 篇 化学工程与技术
- 55 篇 建筑学
- 53 篇 土木工程
- 43 篇 力学（可授工学、理...
- 41 篇 航空宇航科学与技...
3,462 篇 医学
- 3,452 篇 临床医学
- 41 篇 基础医学(可授医学...
2,483 篇 理学
- 1,247 篇 数学
- 1,213 篇 物理学
- 446 篇 统计学（可授理学、...
- 418 篇 生物学
- 269 篇 系统科学
- 67 篇 化学
424 篇 管理学
- 218 篇 管理科学与工程(可...
- 217 篇 图书情报与档案管...
- 43 篇 工商管理
144 篇 艺术学
- 142 篇 设计学（可授艺术学...
41 篇 法学
31 篇 农学
12 篇 经济学
10 篇 教育学
6 篇 文学
3 篇 军事学

主题

8,072 篇 computer vision
2,878 篇 pattern recognit...
2,859 篇 training
1,809 篇 computational mo...
1,712 篇 visualization
1,484 篇 cameras
1,379 篇 shape
1,370 篇 face recognition
1,367 篇 three-dimensiona...
1,340 篇 feature extracti...
1,277 篇 image segmentati...
1,156 篇 robustness
1,117 篇 semantics
978 篇 object detection
976 篇 layout
961 篇 benchmark testin...
953 篇 computer archite...
928 篇 codes
924 篇 object recogniti...
899 篇 computer science

机构

174 篇 univ sci & techn...
149 篇 univ chinese aca...
147 篇 carnegie mellon ...
143 篇 chinese univ hon...
110 篇 microsoft resear...
104 篇 zhejiang univ pe...
100 篇 swiss fed inst t...
92 篇 tsinghua univers...
90 篇 microsoft res as...
89 篇 tsinghua univ pe...
88 篇 shanghai ai lab ...
83 篇 zhejiang univers...
75 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

83 篇 van gool luc
71 篇 zhang lei
59 篇 timofte radu
51 篇 luc van gool
49 篇 yang yi
48 篇 xiaoou tang
44 篇 tian qi
43 篇 darrell trevor
43 篇 sun jian
42 篇 loy chen change
42 篇 qi tian
42 篇 li fei-fei
40 篇 li stan z.
37 篇 vasconcelos nuno
37 篇 liu yang
37 篇 chen xilin
36 篇 liu xiaoming
36 篇 shan shiguang
36 篇 torralba antonio
36 篇 tao dacheng

语言

21,134 篇 英文
31 篇 中文
8 篇 其他
5 篇 土耳其文
2 篇 日文

检索条件"任意字段=2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011"

共 21180 条记录，以下是1011-1020 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：

ResFormer: Scaling ViTs with Multi-Resolution Training

ResFormer: Scaling ViTs with Multi-Resolution Training

引用

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

作者： Tian, Rui Wu, Zuxuan Dai, Qi Hu, Han Qiao, Yu Jiang, Yu-Gang Fudan Univ Sch CS Shanghai Key Lab Intell Info Proc Shanghai Peoples R China Shanghai Collaborat Innovat Ctr Intelligent Visua Shanghai Peoples R China Microsoft Res Asia Beijing Peoples R China Shanghai AI Lab Shanghai Peoples R China

ISBN: (纸本)9798350301298

vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We introduce, ResFormer, a framework that is built upon the seminal idea of multi-resolution training for improved performance on a wide spectrum of, mostly unseen, testing resolutions. In particular, ResFormer operates on replicated images of different resolutions and enforces a scale consistency loss to engage interactive information across different scales. More importantly, to alternate among varying resolutions effectively, especially novel ones in testing, we propose a global-local positional embedding strategy that changes smoothly conditioned on input sizes. We conduct extensive experiments for image classification on ImageNet. The results provide strong quantitative evidence that ResFormer has promising scaling abilities towards a wide range of resolutions. For instance, ResFormer-B-MR achieves a Top-1 accuracy of 75.86% and 81.72% when evaluated on relatively low and high resolutions respectively (i.e., 96 and 640), which are 48% and 7.49% better than DeiT-B. We also demonstrate, moreover, ResFormer is flexible and can be easily extended to semantic segmentation, object detection and video action recognition.

关键词： Efficient and scalable vision

来源：评论

学校读者我要写书评

暂无评论

Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed recognition

Class-Conditional Sharpness-Aware Minimization for Deep Long...

引用

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

作者： Zhou, Zhipeng Li, Lanqing Zhao, Peilin Heng, Pheng-Ann Gong, Wei Univ Sci & Technol China Hefei Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Tencent AI Lab Shenzhen Peoples R China Zhejiang Lab Hangzhou Peoples R China

ISBN: (纸本)9798350301298

It's widely acknowledged that deep learning models with flatter minima in its loss landscape tend to generalize better. However, such property is under-explored in deep long-tailed recognition (DLTR), a practical problem where the model is required to generalize equally well across all classes when trained on highly imbalanced label distribution. In this paper, through empirical observations, we argue that sharp minima are in fact prevalent in deep longtailed models, whereas naive integration of existing flattening operations into long-tailed learning algorithms brings little improvement. Instead, we propose an effective two-stage sharpness-aware optimization approach based on the decoupling paradigm in DLTR. In the first stage, both the feature extractor and classifier are trained under parameter perturbations at a class-conditioned scale, which is theoretically motivated by the characteristic radius of flat minima under the PAC-Bayesian framework. In the second stage, we generate adversarial features with class-balanced sampling to further robustify the classifier with the backbone frozen. Extensive experiments on multiple longtailed visual recognition benchmarks show that, our proposed Class-Conditional Sharpness-Aware Minimization (CC-SAM), achieves competitive performance compared to the state-of-the-arts. Code is available at https://***/zzpustc/CC-SAM.

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

Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection

Bridging Precision and Confidence: A Train-Time Loss for Cal...

引用

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

作者： Munir, Muhammad Akhtar Khan, Muhammad Haris Khan, Salman Khan, Fahad Shahhaz Mohamed Bin Zayed Univ AI Abu Dhabi U Arab Emirates Informat Technol Univ Lahore Pakistan Australian Natl Univ Canberra ACT Australia Linkoping Univ Linkoping Sweden

ISBN: (纸本)9798350301298

Deep neural networks (DNNs) have enabled astounding progress in several vision-based problems. Despite showing high predictive accuracy, recently, several works have revealed that they tend to provide overconfident predictions and thus are poorly calibrated. The majority of the works addressing the miscalibration of DNNs fall under the scope of classification and consider only in-domain predictions. However, there is little to no progress in studying the calibration of DNN-based object detection models, which are central to many vision-based safety-critical applications. In this paper, inspired by the train-time calibration methods, we propose a novel auxiliary loss formulation that explicitly aims to align the class confidence of bounding boxes with the accurateness of predictions (i.e. precision). Since the original formulation of our loss depends on the counts of true positives and false positives in a mini-batch, we develop a differentiable proxy of our loss that can be used during training with other application-specific loss functions. We perform extensive experiments on challenging in-domain and out-domain scenarios with six benchmark datasets including MS-COCO, Cityscapes, Sim10k, and BDD100k. Our results reveal that our train-time loss surpasses strong calibration baselines in reducing calibration error for both in and out-domain scenarios. Our source code and pre-trained models are available at https://***/akhtarvision/bpc_calibration

关键词： vision applications and systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Channel Sparsity for Federated Learning under System Heterogeneity

Adaptive Channel Sparsity for Federated Learning under Syste...

引用

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

作者： Liao, Dongping Gao, Xitong Zhao, Yiren Xu, Chengzhong Univ Macau State Key Lab IoTSC CIS Dept Taipa Macau Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China Imperial Coll London London England

ISBN: (纸本)9798350301298

Owing to the non-i.i.d. nature of client data, channel neurons in federated-learned models may specialize to distinct features for different clients. Yet, existing channel-sparse federated learning (FL) algorithms prescribe fixed sparsity strategies for client models, and may thus prevent clients from training channel neurons collaboratively. To minimize the impact of sparsity on FL convergence, we propose Flado to improve the alignment of client model update trajectories by tailoring the sparsities of individual neurons in each client. Empirical results show that while other sparse methods are surprisingly impactful to convergence, Flado can not only attain the highest task accuracies with unlimited budget across a range of datasets, but also significantly reduce the amount of floating-point operations (FLOPs) required for training more than by 10 x under the same communications budget, and push the Pareto frontier of communication/computation trade-off notably further than competing FL algorithms.

关键词： Efficient and scalable vision

来源：评论

学校读者我要写书评

暂无评论

Q: How to Specialize Large vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images

Q: How to Specialize Large Vision-Language Models to Data-Sc...

引用

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

作者： Khan, Zaid Kumar, Vijay B. G. Schulter, Samuel Yu, Xiang Fu, Yun Chandraker, Manmohan Northeastern Univ Boston MA 02115 USA NEC Labs Amer Irving TX USA Amazon Seattle WA USA Univ Calif San Diego San Diego CA USA

ISBN: (纸本)9798350301298

Finetuning a large vision language model (VLM) on a target dataset after large scale pretraining is a dominant paradigm in visual question answering (VQA). Datasets for specialized tasks such as knowledge-based VQA or VQA in non natural-image domains are orders of magnitude smaller than those for general-purpose VQA. While collecting additional labels for specialized tasks or domains can be challenging, unlabeled images are often available. We introduce SelTDA (Self-Taught Data Augmentation), a strategy for finetuning large VLMs on small-scale VQA datasets. SelTDA uses the VLM and target dataset to build a teacher model that can generate question-answer pseudolabels directly conditioned on an image alone, allowing us to pseudolabel unlabeled images. SelTDA then finetunes the initial VLM on the original dataset augmented with freshly pseudolabeled images. We describe a series of experiments showing that our self-taught data augmentation increases robustness to adversarially searched questions, counterfactual examples and rephrasings, improves domain generalization, and results in greater retention of numerical reasoning skills. The proposed strategy requires no additional annotations or architectural modifications, and is compatible with any modern encoder-decoder multimodal transformer. Code available at https://***/codezakh/SelTDA.

关键词： and reasoning language vision

来源：评论

学校读者我要写书评

暂无评论

Learning to Detect Mirrors from Videos via Dual Correspondences

Learning to Detect Mirrors from Videos via Dual Corresponden...

引用

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

作者： Lin, Jiaying Tan, Xin Lau, Rynson W. H. City Univ Hong Kong Hong Kong Peoples R China East China Normal Univ Shanghai Peoples R China

ISBN: (纸本)9798350301298

Detecting mirrors from static images has received significant research interest recently. However, detecting mirrors over dynamic scenes is still under-explored due to the lack of a high-quality dataset and an effective method for video mirror detection (VMD). To the best of our knowledge, this is the first work to address the VMD problem from a deep-learning-based perspective. Our observation is that there are often correspondences between the contents inside (reflected) and outside (real) of a mirror, but such correspondences may not always appear in every frame, e.g., due to the change of camera pose. This inspires us to propose a video mirror detection method, named VMD-Net, that can tolerate spatially missing correspondences by considering the mirror correspondences at both the intra-frame level as well as inter-frame level via a dual correspondence module that looks over multiple frames spatially and temporally for correlating correspondences. We further propose a first large-scale dataset for VMD (named VMD-D), which contains 14,987 image frames from 269 videos with corresponding manually annotated masks. Experimental results show that the proposed method outperforms SOTA methods from relevant fields. To enable real-time VMD, our method efficiently utilizes the backbone features by removing the redundant multi-level module design and gets rid of post-processing of the output maps commonly used in existing methods, making it very efficient and practical for real-time video-based applications. Code, dataset, and models are available at https://***/cvpr2023-vmd/

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior

Video Dehazing via a Multi-Range Temporal Alignment Network ...

引用

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

作者： Xu, Jiaqi Hu, Xiaowei Zhu, Lei Dou, Qi Dai, Jifeng Qiao, Yu Heng, Pheng-Ann Chinese Univ Hong Kong Hong Kong Peoples R China Shanghai Artificial Intelligence Lab Shanghai Peoples R China Hong Kong Univ Sci & Technol Guangzhou Guangzhou Peoples R China Hong Kong Univ Sci & Technol Hong Kong Peoples R China Tsinghua Univ Beijing Peoples R China

ISBN: (纸本)9798350301298

Video dehazing aims to recover haze-free frames with high visibility and contrast. This paper presents a novel framework to effectively explore the physical haze priors and aggregate temporal information. Specifically, we design a memory-based physical prior guidance module to encode the prior-related features into long-range memory. Besides, we formulate a multi-range scene radiance recovery module to capture space-time dependencies in multiple space-time ranges, which helps to effectively aggregate temporal information from adjacent frames. Moreover, we construct the first large-scale outdoor video dehazing benchmark dataset, which contains videos in various real-world scenarios. Experimental results on both synthetic and real conditions show the superiority of our proposed method.

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

Semantic-Conditional Diffusion Networks for Image Captioning

Semantic-Conditional Diffusion Networks for Image Captioning

引用

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

作者： Luo, Jianjie Li, Yehao Pan, Yingwei Yao, Ting Feng, Jianlin Chao, Hongyang Mei, Tao Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China HiDream Ai Inc Beijing Peoples R China

ISBN: (纸本)9798350301298

Recent advances on text-to-image generation have witnessed the rise of diffusion models which act as powerful generative models. Nevertheless, it is not trivial to exploit such latent variable models to capture the dependency among discrete words and meanwhile pursue complex visual-language alignment in image captioning. In this paper, we break the deeply rooted conventions in learning Transformer-based encoder-decoder, and propose a new diffusion model based paradigm tailored for image captioning, namely Semantic-Conditional Diffusion Networks (SCD-Net). Technically, for each input image, we first search the semantically relevant sentences via cross-modal retrieval model to convey the comprehensive semantic information. The rich semantics are further regarded as semantic prior to trigger the learning of Diffusion Transformer, which produces the output sentence in a diffusion process. In SCD-Net, multiple Diffusion Transformer structures are stacked to progressively strengthen the output sentence with better visional-language alignment and linguistical coherence in a cascaded manner. Furthermore, to stabilize the diffusion process, a new self-critical sequence training strategy is designed to guide the learning of SCD-Net with the knowledge of a standard autoregressive Transformer model. Extensive experiments on COCO dataset demonstrate the promising potential of using diffusion models in the challenging image captioning task. Source code is available at https://***/YehLi/xmodaler/tree/master/configs/image_caption/scdnet.

关键词： language reasoning vision

来源：评论

学校读者我要写书评

暂无评论

OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution

OPE-SR: Orthogonal Position Encoding for Designing a Paramet...

引用

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

作者： Song, Gaochao Sun, Qian Zhang, Luo Su, Ran Shi, Jianfeng He, Ying Tianjin Univ Tianjin Peoples R China Nanjing Univ Informat Sci & Technol Nanjing Peoples R China Nanyang Technol Univ Singapore Singapore

ISBN: (纸本)9798350301298

Arbitrary-scale image super-resolution (SR) is often tackled using the implicit neural representation (INR) approach, which relies on a position encoding scheme to improve its representation ability. In this paper, we introduce orthogonal position encoding (OPE), an extension of position encoding, and an OPE-Upscale module to replace the INR-based upsampling module for arbitrary-scale image super-resolution. Our OPE-Upscale module takes 2D coordinates and latent code as inputs, just like INR, but does not require any training parameters. This parameter-free feature allows the OPE-Upscale module to directly perform linear combination operations, resulting in continuous image reconstruction and achieving arbitrary-scale image reconstruction. As a concise SR framework, our method is computationally efficient and consumes less memory than state-of-the-art methods, as confirmed by extensive experiments and evaluations. In addition, our method achieves comparable results with state-of-the-art methods in arbitrary-scale image super-resolution. Lastly, we show that OPE corresponds to a set of orthogonal basis, validating our design principle.

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation

MAIR: Multi-view Attention Inverse Rendering with 3D Spatial...

引用

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

作者： Choi, JunYong Lee, SeokYeong Park, Haesol Jung, Seung-Won Kim, Ig-Jae Cho, Junghyun Korea Inst Sci & Technol KIST Seoul South Korea Korea Univ Seoul South Korea Univ Sci & Technol KIST Sch AI Robot Koto City Japan Yonsei Univ Yonsei KIST Convergence Res Inst Seoul South Korea

ISBN: (纸本)9798350301298

We propose a scene-level inverse rendering framework that uses multi-view images to decompose the scene into geometry, a SVBRDF, and 3D spatially-varying lighting. Because multi-view images provide a variety of information about the scene, multi-view images in object-level inverse rendering have been taken for granted. However, owing to the absence of multi-view HDR synthetic dataset, scene-level inverse rendering has mainly been studied using single-view image. We were able to successfully perform scene-level inverse rendering using multi-view images by expanding OpenRooms dataset and designing efficient pipelines to handle multi-view images, and splitting spatially-varying lighting. Our experiments show that the proposed method not only achieves better performance than single-view-based methods, but also achieves robust performance on unseen real-world scene. Also, our sophisticated 3D spatially-varying lighting volume allows for photorealistic object insertion in any 3D location.

关键词： vision + graphics

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 << < 98 99 100 101 102 103 104 105 106 107 > >>

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：