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

23,000 篇 会议
126 册 图书
92 篇 期刊文献

馆藏范围

23,217 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,623 篇 工学
- 11,107 篇 计算机科学与技术...
- 3,479 篇 软件工程
- 2,444 篇 机械工程
- 1,717 篇 光学工程
- 1,076 篇 电气工程
- 1,014 篇 控制科学与工程
- 784 篇 信息与通信工程
- 411 篇 仪器科学与技术
- 352 篇 生物工程
- 251 篇 生物医学工程（可授...
- 196 篇 电子科学与技术（可...
- 114 篇 化学工程与技术
- 107 篇 安全科学与工程
- 100 篇 测绘科学与技术
- 88 篇 建筑学
- 86 篇 交通运输工程
- 84 篇 土木工程
3,493 篇 医学
- 3,480 篇 临床医学
- 81 篇 基础医学(可授医学...
3,241 篇 理学
- 1,939 篇 物理学
- 1,640 篇 数学
- 563 篇 统计学（可授理学、...
- 500 篇 生物学
- 249 篇 系统科学
- 106 篇 化学
521 篇 管理学
- 311 篇 图书情报与档案管...
- 223 篇 管理科学与工程(可...
- 76 篇 工商管理
276 篇 艺术学
- 276 篇 设计学（可授艺术学...
66 篇 法学
- 63 篇 社会学
38 篇 农学
28 篇 教育学
22 篇 经济学
10 篇 军事学
3 篇 文学

主题

10,187 篇 computer vision
3,967 篇 pattern recognit...
3,005 篇 training
2,007 篇 computational mo...
1,818 篇 visualization
1,816 篇 cameras
1,515 篇 feature extracti...
1,481 篇 shape
1,455 篇 three-dimensiona...
1,438 篇 image segmentati...
1,287 篇 robustness
1,205 篇 computer archite...
1,155 篇 semantics
1,147 篇 conferences
1,107 篇 layout
1,093 篇 computer science
1,088 篇 object detection
1,025 篇 benchmark testin...
970 篇 codes
922 篇 face recognition

机构

136 篇 univ sci & techn...
121 篇 univ chinese aca...
118 篇 chinese univ hon...
107 篇 carnegie mellon ...
101 篇 tsinghua univers...
101 篇 microsoft resear...
95 篇 swiss fed inst t...
93 篇 zhejiang univ pe...
82 篇 university of sc...
81 篇 zhejiang univers...
80 篇 university of ch...
77 篇 shanghai ai lab ...
72 篇 shanghai jiao to...
69 篇 national laborat...
67 篇 microsoft res as...
67 篇 alibaba grp peop...
64 篇 adobe research
61 篇 tsinghua univ pe...
60 篇 peking univ peop...
59 篇 univ oxford oxfo...

作者

81 篇 van gool luc
72 篇 timofte radu
64 篇 zhang lei
47 篇 luc van gool
40 篇 yang yi
40 篇 li stan z.
37 篇 loy chen change
34 篇 chen chen
33 篇 xiaoou tang
32 篇 liu yang
32 篇 qi tian
31 篇 tian qi
31 篇 sun jian
30 篇 murino vittorio
30 篇 pascal fua
29 篇 darrell trevor
29 篇 li fei-fei
28 篇 li xin
28 篇 ying shan
27 篇 vasconcelos nuno

语言

23,023 篇 英文
166 篇 其他
22 篇 中文
5 篇 土耳其文
2 篇 日文

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

共 23218 条记录，以下是1251-1260 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：

OCTET: Object-aware Counterfactual Explanations

OCTET: Object-aware Counterfactual Explanations

引用

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

作者： Zemni, Mehdi Chen, Mickael Zablocki, Eloi Ben-Younes, Hedi Perez, Patrick Cord, Matthieu Valeo Ai Paris France Sorbonne Univ Paris France

ISBN: (纸本)9798350301298

Nowadays, deep vision models are being widely deployed in safety-critical applications, e.g., autonomous driving, and explainability of such models is becoming a pressing concern. Among explanation methods, counterfactual explanations aim to find minimal and interpretable changes to the input image that would also change the output of the model to be explained. Such explanations point end-users at the main factors that impact the decision of the model. However, previous methods struggle to explain decision models trained on images with many objects, e.g., urban scenes, which are more difficult to work with but also arguably more critical to explain. In this work, we propose to tackle this issue with an object-centric framework for counterfactual explanation generation. Our method, inspired by recent generative modeling works, encodes the query image into a latent space that is structured in a way to ease object-level manipulations. Doing so, it provides the end-user with control over which search directions (e.g., spatial displacement of objects, style modification, etc.) are to be explored during the counterfactual generation. We conduct a set of experiments on counterfactual explanation benchmarks for driving scenes, and we show that our method can be adapted beyond classification, e.g., to explain semantic segmentation models. To complete our analysis, we design and run a user study that measures the usefulness of counterfactual explanations in understanding a decision model. Code is available at https://***/valeoai/OCTET.

关键词： Explainable computer vision

来源：评论

学校读者我要写书评

暂无评论

CrowdCLIP: Unsupervised Crowd Counting via vision-Language Model

CrowdCLIP: Unsupervised Crowd Counting via Vision-Language M...

引用

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

作者： Liang, Dingkang Xie, Jiahao Zou, Zhikang Ye, Xiaoqing Xu, Wei Bai, Xiang Huazhong Univ Sci & Technol Wuhan Peoples R China Beijing Univ Posts & Telecommun Beijing Peoples R China Baidu Inc Beijing Peoples R China

ISBN: (纸本)9798350301298

Supervised crowd counting relies heavily on costly manual labeling, which is difficult and expensive, especially in dense scenes. To alleviate the problem, we propose a novel unsupervised framework for crowd counting, named CrowdCLIP. The core idea is built on two observations: 1) the recent contrastive pre-trained vision-language model (CLIP) has presented impressive performance on various downstream tasks;2) there is a natural mapping between crowd patches and count text. To the best of our knowledge, CrowdCLIP is the first to investigate the vision-language knowledge to solve the counting problem. Specifically, in the training stage, we exploit the multi-modal ranking loss by constructing ranking text prompts to match the size-sorted crowd patches to guide the image encoder learning. In the testing stage, to deal with the diversity of image patches, we propose a simple yet effective progressive filtering strategy to first select the highly potential crowd patches and then map them into the language space with various counting intervals. Extensive experiments on five challenging datasets demonstrate that the proposed CrowdCLIP achieves superior performance compared to previous unsupervised state-of-the-art counting methods. Notably, CrowdCLIP even surpasses some popular fully-supervised methods under the cross-dataset setting. The source code will be available at https:// ***/dk-liang/CrowdCLIP.

关键词： body gesture Humans: Face movement pose

来源：评论

学校读者我要写书评

暂无评论

Visual Atoms: Pre-training vision Transformers with Sinusoidal Waves

Visual Atoms: Pre-training Vision Transformers with Sinusoid...

引用

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

作者： Takashima, Sora Hayamizu, Ryo Inoue, Nakamasa Kataoka, Hirokatsu Yokota, Rio Natl Inst Adv Ind Sci & Technol Tokyo Japan Tokyo Inst Technol Tokyo Japan

ISBN: (纸本)9798350301298

Formula-driven supervised learning (FDSL) has been shown to be an effective method for pre-training vision transformers, where ExFractalDB-21k was shown to exceed the pre-training effect of ImageNet-21k. These studies also indicate that contours mattered more than textures when pre-training vision transformers. However, the lack of a systematic investigation as to why these contour-oriented synthetic datasets can achieve the same accuracy as real datasets leaves much room for skepticism. In the present work, we develop a novel methodology based on circular harmonics for systematically investigating the design space of contour-oriented synthetic datasets. This allows us to efficiently search the optimal range of FDSL parameters and maximize the variety of synthetic images in the dataset, which we found to be a critical factor. When the resulting new dataset VisualAtom-21k is used for pre-training ViTBase, the top-1 accuracy reached 83.7% when fine-tuning on ImageNet-1k. This is only 0.5% difference from the top-1 accuracy (84.2%) achieved by the JFT-300M pre-training, even though the scale of images is 1/14. Unlike JFT-300M which is a static dataset, the quality of synthetic datasets will continue to improve, and the current work is a testament to this possibility. FDSL is also free of the common issues associated with real images, e.g. privacy/copyright issues, labeling costs/errors, and ethical biases.

关键词： Datasets and evaluation

来源：评论

学校读者我要写书评

暂无评论

Neural Congealing: Aligning Images to a Joint Semantic Atlas

Neural Congealing: Aligning Images to a Joint Semantic Atlas

引用

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

作者： Ofri-Amar, Dolev Geyer, Michal Kasten, Yoni Dekel, Tali Weizmann Inst Sci Rehovot Israel NVIDIA Res Tel Aviv Israel

ISBN: (纸本)9798350301298

We present Neural Congealing - a zero-shot self-supervised framework for detecting and jointly aligning semantically-common content across a given set of images. Our approach harnesses the power of pre-trained DINO-ViT features to learn: (i) a joint semantic atlas - a 2D grid that captures the mode of DINO-ViT features in the input set, and (ii) dense mappings from the unified atlas to each of the input images. We derive a new robust self-supervised framework that optimizes the atlas representation and mappings per image set, requiring only a few real-world images as input without any additional input information (e.g., segmentation masks). Notably, we design our losses and training paradigm to account only for the shared content under severe variations in appearance, pose, background clutter or other distracting objects. We demonstrate results on a plethora of challenging image sets including sets of mixed domains (e.g., aligning images depicting sculpture and artwork of cats), sets depicting related yet different object categories (e.g., dogs and tigers), or domains for which large-scale training data is scarce (e.g., coffee mugs). We thoroughly evaluate our method and show that our test-time optimization approach performs favorably compared to a state-of-the-art method that requires extensive training on large-scale datasets. Project webpage: https://***/

关键词： vision + graphics

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

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

Comprehensive Visual Features and Pseudo Labeling for Robust Natural Language-based Vehicle Retrieval

Comprehensive Visual Features and Pseudo Labeling for Robust...

引用

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

作者： Ngo, Bach Hoang Nguyen, Dat Thanh Do-Tran, Nhat-Tuong Huy Thien, Phuc Pham An, Minh-Hung Nguyen, Tuan-Ngoc Hoang, Loi Nguyen Dinh Nguyen, Vinh Dinh, Quang-Vinh Ai Vietnam Research Viet Nam Fpt Telecom Viet Nam Ho Chi Minh City University of Technology Faculty of Computer Science and Engineering Viet Nam Eastern International University School of Computing and Information Technology Viet Nam

ISBN: (纸本)9798350302493

Vehicle retrieval has become crucial for public transportation and intelligent transportation systems due to the exponential development of large-scale transportation videos. Vehicle re-identification and vehicle tracking are the main components of most vision-based vehicle recovery systems. Unfortunately, the limited amount of information provided by traffic video feeds limits the vision-based vehicle retrieval algorithm's efficacy. Therefore, this article proposes a contrastive cross-modal vehicle retrieval approach to maximize the complementarity of natural language and visual representations. An efficient method to fuse multiple input image features is also proposed to extract comprehensive information from various vehicles along with pseudo labeling and efficient post-processing techniques to enhance retrieval accuracy. The proposed method achieved the 3rd ranking of Mean Reciprocal Rank (MRR) score of 0.4795 on the test set for the Challenge Track 2: Tracked-Vehicle Retrieval by Natural Language Descriptions 2023. Source code for the proposed approaches is openly accessible at https://***/anminhhung/AICity-2023-Track2. © 2023 ieee.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detection

itKD: Interchange Transfer-based Knowledge Distillation for ...

引用

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

作者： Cho, Hyeon Choi, Junyong Baek, Geonwoo Hwang, Wonjun Ajou Univ Suwon South Korea Hyundai Motor Co Seoul South Korea Naver AI Lab Seongnam South Korea

ISBN: (纸本)9798350301298

Point-cloud based 3D object detectors recently have achieved remarkable progress. However, most studies are limited to the development of network architectures for improving only their accuracy without consideration of the computational efficiency. In this paper, we first propose an autoencoder-style framework comprising channel-wise compression and decompression via interchange transfer-based knowledge distillation. To learn the map-view feature of a teacher network, the features from teacher and student networks are independently passed through the shared autoencoder;here, we use a compressed representation loss that binds the channel-wised compression knowledge from both student and teacher networks as a kind of regularization. The decompressed features are transferred in opposite directions to reduce the gap in the interchange reconstructions. Lastly, we present an head attention loss to match the 3D object detection information drawn by the multi-head self-attention mechanism. Through extensive experiments, we verify that our method can train the lightweight model that is well-aligned with the 3D point cloud detection task and we demonstrate its superiority using the well-known public datasets;e.g., Waymo and nuScenes.(1)

关键词： Efficient and scalable vision

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

ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal

ShadowDiffusion: When Degradation Prior Meets Diffusion Mode...

引用

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

作者： Guo, Lanqing Wang, Chong Yang, Wenhan Huang, Siyu Wang, Yufei Pfister, Hanspeter Wen, Bihan Nanyang Technol Univ Singapore Singapore Peng Cheng Lab Shenzhen Peoples R China Harvard Univ Cambridge MA 02138 USA

ISBN: (纸本)9798350301298

Recent deep learning methods have achieved promising results in image shadow removal. However, their restored images still suffer from unsatisfactory boundary artifacts, due to the lack of degradation prior embedding and the deficiency in modeling capacity. Our work addresses these issues by proposing a unified diffusion framework that integrates both the image and degradation priors for highly effective shadow removal. In detail, we first propose a shadow degradation model, which inspires us to build a novel unrolling diffusion model, dubbed ShandowDiffusion. It remarkably improves the model's capacity in shadow removal via progressively refining the desired output with both degradation prior and diffusive generative prior, which by nature can serve as a new strong baseline for image restoration. Furthermore, ShadowDiffusion progressively refines the estimated shadow mask as an auxiliary task of the diffusion generator, which leads to more accurate and robust shadow-free image generation. We conduct extensive experiments on three popular public datasets, including ISTD, ISTD+, and SRD, to validate our method's effectiveness. Compared to the state-of-the-art methods, our model achieves a significant improvement in terms of PSNR, increasing from 31.69dB to 34.73dB over SRD dataset.(1)

关键词： Low-level 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 << < 122 123 124 125 126 127 128 129 130 131 > >>

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：