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
- 11,180 篇 计算机科学与技术...
- 2,631 篇 机械工程
- 2,543 篇 软件工程
- 990 篇 光学工程
- 848 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...
2,484 篇 理学
- 1,248 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
2,880 篇 pattern recognit...
2,859 篇 training
1,808 篇 computational mo...
1,718 篇 visualization
1,477 篇 cameras
1,381 篇 shape
1,374 篇 face recognition
1,364 篇 three-dimensiona...
1,342 篇 feature extracti...
1,269 篇 image segmentati...
1,156 篇 robustness
1,109 篇 semantics
982 篇 layout
977 篇 object detection
953 篇 computer archite...
952 篇 benchmark testin...
931 篇 codes
918 篇 object recogniti...
898 篇 computer science

机构

174 篇 univ sci & techn...
154 篇 carnegie mellon ...
149 篇 univ chinese aca...
144 篇 chinese univ hon...
110 篇 microsoft resear...
104 篇 zhejiang univ pe...
98 篇 swiss fed inst t...
93 篇 tsinghua univ pe...
92 篇 tsinghua univers...
90 篇 microsoft res as...
88 篇 shanghai ai lab ...
83 篇 zhejiang univers...
76 篇 alibaba grp peop...
74 篇 hong kong univ s...
73 篇 university of sc...
72 篇 peking univ peop...
68 篇 shanghai jiao to...
68 篇 university of ch...
66 篇 google res mount...
66 篇 univ oxford oxfo...

作者

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

语言

21,138 篇 英文
31 篇 中文
5 篇 土耳其文
4 篇 其他
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471-480 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：

RGB no more: Minimally-decoded JPEG vision Transformers

RGB no more: Minimally-decoded JPEG Vision Transformers

引用

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

作者： Park, Jeongsoo Johnson, Justin Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9798350301298

Most neural networks for computer vision are designed to infer using RGB images. However, these RGB images are commonly encoded in JPEG before saving to disk;decoding them imposes an unavoidable overhead for RGB networks. Instead, our work focuses on training vision Transformers (ViT) directly from the encoded features of JPEG. This way, we can avoid most of the decoding overhead, accelerating data load. Existing works have studied this aspect but they focus on CNNs. Due to how these encoded features are structured, CNNs require heavy modification to their architecture to accept such data. Here, we show that this is not the case for ViTs. In addition, we tackle data augmentation directly on these encoded features, which to our knowledge, has not been explored in-depth for training in this setting. With these two improvements - ViT and data augmentation - we show that our ViT-Ti model achieves up to 39.2% faster training and 17.9% faster inference with no accuracy loss compared to the RGB counterpart. (1)

关键词： and reasoning language vision

来源：评论

学校读者我要写书评

暂无评论

DeiT-LT: Distillation Strikes Back for vision Transformer Training on Long-Tailed Datasets

DeiT-LT: Distillation Strikes Back for Vision Transformer Tr...

引用

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

作者： Rangwani, Harsh Mondal, Pradipto Mishra, Mayank Asokan, Ashish Ramayee Babu, R. Venkatesh Indian Inst Sci Bangalore Karnataka India Indian Inst Technol Kharagpur W Bengal India

ISBN: (纸本)9798350353006

vision Transformer (ViT) has emerged as a prominent architecture for various computer vision tasks. In ViT, we divide the input image into patch tokens and process them through a stack of self-attention blocks. However, unlike Convolutional Neural Network (CNN), ViT's simple architecture has no informative inductive bias (e.g., locality, etc.). Due to this, ViT requires a large amount of data for pre-training. Various data-efficient approaches (DeiT) have been proposed to train ViT on balanced datasets effectively. However, limited literature discusses the use of ViT for datasets with long-tailed imbalances. In this work, we introduce DeiT-LT to tackle the problem of training ViTs from scratch on long-tailed datasets. In DeiT-LT, we introduce an efficient and effective way of distillation from CNN via distillation DIST token by using out-of-distribution images and re-weighting the distillation loss to enhance focus on tail classes. This leads to the learning of local CNN-like features in early ViT blocks, improving generalization for tail classes. Further, to mitigate overfitting, we propose distilling from a flat CNN teacher, which leads to learning low-rank generalizable features for DIST tokens across all ViT blocks. With the proposed DeiT-LT scheme, the distillation DIST token becomes an expert on the tail classes, and the classifier CLS token becomes an expert on the head classes. The experts help to effectively learn features corresponding to both the majority and minority classes using a distinct set of tokens within the same ViT architecture. We show the effectiveness of DeiT-LT for training ViT from scratch on datasets ranging from small-scale CIFAR-10 LT to large-scale iNaturalist-2018. Project Page: https://***/DeiT-LT.

关键词： distillation long-tail-learning vision transformers vit

来源：评论

学校读者我要写书评

暂无评论

Improving Image recognition by Retrieving from Web-Scale Image-Text Data

Improving Image Recognition by Retrieving from Web-Scale Ima...

引用

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

作者： Iscen, Ahmet Fathi, Alireza Schmid, Cordelia Google Res Mountain View CA 94043 USA

ISBN: (纸本)9798350301298

Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar examples for the visual input from an external memory set. In this work, we introduce an attention-based memory module, which learns the importance of each retrieved example from the memory. Compared to existing approaches, our method removes the influence of the irrelevant retrieved examples, and retains those that are beneficial to the input query. We also thoroughly study various ways of constructing the memory dataset. Our experiments show the benefit of using a massive-scale memory dataset of 1B image-text pairs, and demonstrate the performance of different memory representations. We evaluate our method in three different classification tasks, namely long-tailed recognition, learning with noisy labels, and fine-grained classification, and show that it achieves state-of-the-art accuracies in ImageNet-LT, Places-LT and Webvision datasets.

关键词： detection recognition: Categorization retrieval

来源：评论

学校读者我要写书评

暂无评论

FairCLIP: Harnessing Fairness in vision-Language Learning

FairCLIP: Harnessing Fairness in Vision-Language Learning

引用

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

作者： Luol, Yan Shil, Min Khan, Muhammad Osama Afzal, Muhammad Muneeb Huang, Hao Yuan, Shuaihang Tian, Yu Song, Luo Kouhana, Ava Elze, Tobias Fang, Yi Wang, Mengyu Harvard Univ Harvard Ophthalmol AI Lab Cambridge MA 02138 USA NYU Tandon Sch Engn New York NY USA New York Univ Abu Dhabi Multimedia & Visual Comp Lab Abu Dhabi U Arab Emirates

ISBN: (纸本)9798350353006

Fairness is a critical concern in deep learning, especially in healthcare, where these models influence diagnoses and treatment decisions. Although fairness has been investigated in the vision-only domain, the fairness of medical vision-language (VL) models remains unexplored due to the scarcity of medical VL datasets for studying fairness. To bridge this research gap, we introduce the first fair vision-language medical dataset (Harvard-FairVLMed) that provides detailed demographic attributes, ground-truth labels, and clinical notes to facilitate an in-depth examination of fairness within VL foundation models. Using Harvard-FairVLMed, we conduct a comprehensive fairness analysis of two widely-used VL models (CLIP and BLIP2), pre-trained on both natural and medical domains, across four different protected attributes. Our results highlight significant biases in all VL models, with Asian, Male, Non-Hispanic, and Spanish being the preferred subgroups across the protected attributes of race, gender, ethnicity, and language, respectively. In order to alleviate these biases, we propose FairCLIP, an optimal-transport-based approach that achieves a favorable trade-off between performance and fairness by reducing the Sinkhorn distance between the overall sample distribution and the distributions corresponding to each demographic group. As the first VL dataset of its kind, Harvard-FairVLMed holds the potential to catalyze advancements in the development of machine learning models that are both ethically aware and clinically effective. Our dataset and code are available at https://***/datasets/

关键词： AI for Medicine Equitable Deep Learning Fairness Learning Large Language Models Medical AI Ophthalmology Optimal Transport vision-Language Learning

来源：评论

学校读者我要写书评

暂无评论

OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning

OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contr...

引用

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

作者： Ying, Haiyang Yin, Yixuan Zhang, Jinzhi Wang, Fan Yu, Tao Huang, Ruqi Fang, Lu Tsinghua Univ Beijing Peoples R China Alibaba Grp Beijing Peoples R China

ISBN: (纸本)9798350353006

Towards holistic understanding of 3D scenes, a general 3D segmentation method is needed that can segment diverse objects without restrictions on object quantity or categories, while also reflecting the inherent hierarchical structure. To achieve this, we propose OmniSeg3D, an omniversal segmentation method aims for segmenting anything in 3D all at once. The key insight is to lift multi-view inconsistent 2D segmentations into a consistent 3D feature field through a hierarchical contrastive learning framework, which is accomplished by two steps. Firstly, we design a novel hierarchical representation based on category-agnostic 2D segmentations to model the multi-level relationship among pixels. Secondly, image features rendered from the 3D feature field are clustered at different levels, which can be further drawn closer or pushed apart according to the hierarchical relationship between different levels. In tackling the challenges posed by inconsistent 2D segmentations, this framework yields a global consistent 3D feature field, which further enables hierarchical segmentation, multi-object selection, and global discretization. Extensive experiments demonstrate the effectiveness of our method on high-quality 3D segmentation and accurate hierarchical structure understanding. A graphical user interface further facilitates flexible interaction for omniversal 3D segmentation.

关键词： 3D Segmentation 3D vision Contrastive Learning Differentiable Rendering Hierarchical Understanding Neural Radiance Field

来源：评论

学校读者我要写书评

暂无评论

Enhancing Emotion recognition with Pre-trained Masked Autoencoders and Sequential Learning

Enhancing Emotion Recognition with Pre-trained Masked Autoen...

引用

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

作者： Zhou, Weiwei Lu, Jiada Ling, Chenkun Wang, Weifeng Liu, Shaowei Chinatelecom Cloud Chengdu Peoples R China

ISBN: (纸本)9798350365474

Human emotion recognition plays a pivotal role in facilitating seamless interactions between humans and computers. This paper delineates our methodology in tackling the Valence-Arousal (VA) Estimation Challenge, Expression (Expr) recognition Challenge, and Action Unit (AU) Detection Challenge within the ambit of the 6th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW). Our study advocates a novel approach aimed at refining continuous emotion recognition. We achieve this by first pre-training with Masked Autoencoders (MAE) on facial datasets and then fine-tuning the model on the affwild2 dataset, which is annotated with expression (Expr) labels. The pre-trained model serves as an adept visual feature extractor, thereby enhancing the model's robustness. Furthermore, we bolster the performance of continuous emotion recognition by integrating Temporal Convolutional Network (TCN) modules and Transformer Encoder modules into our framework. Our model excels beyond baseline performance, securing a commendable 3rd place in the Valence-Arousal Estimation Challenge, while also achieving an impressive 2nd place in both the Expression recognition Challenge and the Action Unit Detection Challenge.

关键词： Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

BEHAVIOR vision Suite: Customizable Dataset Generation via Simulation

BEHAVIOR Vision Suite: Customizable Dataset Generation via S...

引用

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

作者： Ge, Yunhao Tang, Yihe Xu, Jiashu Gokmen, Cem Li, Chengshu Ai, Wensi Martinez, Benjamin Jose Aydin, Arman Anvari, Mona Chakravarthy, Ayush K. Yu, Hong-Xing Wong, Josiah Srivastava, Sanjana Lee, Sharon Zhang, Shengxin Itti, Laurent Li, Yunzhu Martin-Martins, Roberto Liu, Miao Zhang, Pengchuan Zhang, Ruohan Fei-Fei, Li Wu, Jiajun Stanford Univ Stanford CA 94305 USA Univ Southern Calif Los Angeles CA 90007 USA Harvard Univ Cambridge MA 02138 USA Meta GenAI Menlo Pk CA USA Meta FAIR Menlo Pk CA USA Univ Texas Austin Austin TX USA Univ Illinois Urbana IL USA

ISBN: (纸本)9798350353006

The systematic evaluation and understanding of computer vision models under varying conditions require large amounts of data with comprehensive and customized labels, which real-world vision datasets rarely satisfy. While current synthetic data generators offer a promising alternative, particularly for embodied AI tasks, they often fall short for computer vision tasks due to low asset and rendering quality, limited diversity, and unrealistic physical properties. We introduce the BEHAVIOR vision Suite (BVS), a set of tools and assets to generate fully customized synthetic data for systematic evaluation of computer vision models, based on the newly developed embodied AI benchmark, BEHAVIOR-1K. BVS supports a large number of adjustable parameters at the scene level (e.g., lighting, object placement), the object level (e.g., joint configuration, attributes such as "filled" and "folded"), and the camera level (e.g., field of view, focal length). Researchers can arbitrarily vary these parameters during data generation to perform controlled experiments. We showcase three example application scenarios: systematically evaluating the robustness of models across different continuous axes of domain shift, evaluating scene understanding models on the same set of images, and training and evaluating simulation-to-real transfer for a novel vision task: unary and binary state prediction. Project website: https://***/

关键词： benchmarking embodied AI simulation synthetic data generation

来源：评论

学校读者我要写书评

暂无评论

Purposeful Regularization with Reinforcement Learning for Facial Expression recognition In-the-Wild

Purposeful Regularization with Reinforcement Learning for Fa...

引用

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

作者： Hong, SangHwa Seoul Natl Univ Sci & Technol Dept Ind Engn Gongreung Ro 232 Seoul South Korea

ISBN: (纸本)9798350365474

Facial Expression recognition (FER), an essential aspect of emotion analysis through artificial intelligence, is a crucial research area. Although traditional approaches utilizing Convolutional Neural Networks (CNNs) for analyzing human emotions from facial expressions achieve superior accuracy over conventional machine learning methods, overfitting -especially arising severely from data collected in uncontrolled, In-the-wild settings -significantly impedes CNNs performance. This is due to the data scarcity and inherent noise inside In-the-wild data. To address this challenge, this paper introduces a novel regularization method that employs Reinforcement Learning (RL) to adaptively apply regularization hyperparameters appropriate for the evolving state of trained CNNs. Through experiments on various datasets such as CIFAR100, FER2013, and Affect-Net datasets including diverse perspective analysis such as graphical, Grad-CAM and numerical analysis, it is demonstrated that the suggested method can alleviate memorization of noise in training data and promote learning of essential features. The significance of the suggested method lies in its demonstrated remarkable effectiveness in enhancing CNNs' generalization and reducing overfitting.

关键词： FER Overfitting Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

GLaMM: Pixel Grounding Large Multimodal Model

GLaMM: Pixel Grounding Large Multimodal Model

引用

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

作者： Rasheed, Hanoona Maaz, Muhammad Shaji, Sahal Shaker, Abdelrahman Khan, Salman Cholakkal, Hisham Anwer, Rao M. Xing, Eric Yang, Ming-Hsuan Khan, Fahad S. Mohamed Bin Zayed Univ AI Abu Dhabi U Arab Emirates Australian Natl Univ Canberra ACT Australia Aalto Univ Espoo Finland Carnegie Mellon Univ Pittsburgh PA 15213 USA Univ Calif Merced Merced CA USA Linkoping Univ Linkoping Sweden Google Res Mountain View CA USA

ISBN: (纸本)9798350353006

Large Multimodal Models (LMMs) extend Large Language Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses. Recently, region-level LMMs have been used to generate visually grounded responses. However, they are limited to only referring to a single object cate-gory at a time, require users to specify the regions, or can-not offer dense pixel-wise object grounding. In this work, we present Grounding LMM (GLaMM), the first model that can generate natural language responses seamlessly intertwined with corresponding object segmentation masks. GLaMM not only grounds objects appearing in the conversations but is flexible enough to accept both textual and optional visual prompts (region of interest) as input. This empowers users to interact with the model at various levels of granularity, both in textual and visual domains. Due to the lack of standard benchmarks for the novel setting of visually Grounded Conversation Generation (GCG), we introduce a comprehensive evaluation protocol with our cu-rated grounded conversations. Our proposed GCG task requires densely grounded concepts in natural scenes at a large-scale. To this end, we propose a densely annotated Grounding-anything Dataset (GranD) using our proposed automated annotation pipeline that encompasses 7.5M unique concepts grounded in a total of 810M regions available with segmentation masks. Besides GCG, GLaMM also performs effectively on several downstream tasks, e. g., referring expression segmentation, image and region-level captioning and vision-language conversations.

关键词： automated dataset annotation LMM MLMM multimodal foundation models Multimodal LMM vision and language vision-language VLM

来源：评论

学校读者我要写书评

暂无评论

Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data

Good at captioning, bad at counting: Benchmarking GPT-4V on ...

引用

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

作者： Zhang, Chenhui Wang, Sherrie MIT Inst Data Syst & Soc 77 Massachusetts Ave Cambridge MA 02139 USA

ISBN: (纸本)9798350365474

Large vision-Language Models (VLMs) have demonstrated impressive performance on complex tasks involving visual input with natural language instructions. However, it remains unclear to what extent capabilities on natural images transfer to Earth observation (EO) data, which are predominantly satellite and aerial images less common in VLM training data. In this work, we propose a comprehensive benchmark to gauge the progress of VLMs toward being useful tools for EO data by assessing their abilities on scene understanding, localization and counting, and change detection. Motivated by real-world applications, our benchmark includes scenarios like urban monitoring, disaster relief, land use, and conservation. We discover that, although state-of-the-art VLMs like GPT-4V possess world knowledge that leads to strong performance on location understanding and image captioning, their poor spatial reasoning limits usefulness on object localization and counting. Our benchmark is publicly available on this website. A full version of this paper can be found here.

关键词： benchmark Earth observation foundation model vision-language model

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 << < 44 45 46 47 48 49 50 51 52 53 > >>

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：