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

11,745 篇 会议
8 篇 期刊文献

馆藏范围

11,753 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,139 篇 工学
- 7,674 篇 计算机科学与技术...
- 804 篇 机械工程
- 580 篇 软件工程
- 376 篇 电气工程
- 252 篇 控制科学与工程
- 208 篇 光学工程
- 85 篇 生物工程
- 83 篇 信息与通信工程
- 29 篇 生物医学工程（可授...
- 23 篇 电子科学与技术（可...
- 21 篇 化学工程与技术
- 15 篇 交通运输工程
- 14 篇 安全科学与工程
- 10 篇 网络空间安全
- 8 篇 仪器科学与技术
- 6 篇 材料科学与工程（可...
- 6 篇 动力工程及工程热...
3,194 篇 医学
- 3,190 篇 临床医学
- 11 篇 基础医学(可授医学...
- 7 篇 公共卫生与预防医...
481 篇 理学
- 216 篇 物理学
- 203 篇 系统科学
- 88 篇 生物学
- 55 篇 数学
- 29 篇 统计学（可授理学、...
- 24 篇 化学
55 篇 管理学
- 29 篇 图书情报与档案管...
- 28 篇 管理科学与工程(可...
- 12 篇 工商管理
17 篇 法学
- 15 篇 社会学
6 篇 农学
4 篇 教育学
2 篇 经济学
1 篇 军事学
1 篇 艺术学

主题

5,434 篇 computer vision
2,516 篇 training
2,087 篇 pattern recognit...
1,621 篇 computational mo...
1,435 篇 visualization
1,306 篇 three-dimensiona...
1,060 篇 semantics
981 篇 codes
968 篇 benchmark testin...
898 篇 computer archite...
884 篇 deep learning
762 篇 task analysis
681 篇 feature extracti...
536 篇 face recognition
527 篇 conferences
515 篇 transformers
515 篇 neural networks
479 篇 object detection
466 篇 image segmentati...
454 篇 cameras

机构

168 篇 univ sci & techn...
144 篇 univ chinese aca...
144 篇 tsinghua univ pe...
143 篇 carnegie mellon ...
135 篇 chinese univ hon...
112 篇 peng cheng lab p...
108 篇 zhejiang univ pe...
97 篇 swiss fed inst t...
92 篇 tsinghua univers...
92 篇 sensetime res pe...
88 篇 shanghai ai lab ...
85 篇 zhejiang univers...
84 篇 shanghai jiao to...
78 篇 peng cheng labor...
77 篇 university of sc...
77 篇 alibaba grp peop...
76 篇 univ hong kong p...
76 篇 tech univ munich...
76 篇 stanford univ st...
73 篇 university of ch...

作者

76 篇 timofte radu
64 篇 van gool luc
50 篇 zhang lei
44 篇 yang yi
40 篇 loy chen change
34 篇 tao dacheng
32 篇 liu yang
32 篇 chen chen
30 篇 zhou jie
30 篇 tian qi
30 篇 sun jian
28 篇 zha zheng-jun
27 篇 qi tian
26 篇 li xin
26 篇 vasconcelos nuno
26 篇 ying shan
25 篇 liu xiaoming
25 篇 luc van gool
25 篇 boxin shi
24 篇 zheng wei-shi

语言

11,746 篇 英文
7 篇 其他

检索条件"任意字段=2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023"

共 11753 条记录，以下是261-270 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：

MAP: Multimodal Uncertainty-Aware vision-Language Pre-training Model

MAP: Multimodal Uncertainty-Aware Vision-Language Pre-traini...

引用

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

作者： Ji, Yatai Wang, Junjie Gong, Yuan Zhang, Lin Zhu, Yanru Wang, Hongfa Zhang, Jiaxing Sakai, Tetsuya Yang, Yujiu Tsinghua Univ Beijing Peoples R China Waseda Univ Tokyo Japan IDEA Gandhinagar India Tencent TEG Shenzhen Peoples R China

ISBN: (纸本)9798350301298

Multimodal semantic understanding often has to deal with uncertainty, which means the obtained messages tend to refer to multiple targets. Such uncertainty is problematic for our interpretation, including inter- and intra-modal uncertainty. Little effort has studied the modeling of this uncertainty, particularly in pre-training on unlabeled datasets and fine-tuning in task-specific downstream datasets. In this paper, we project the representations of all modalities as probabilistic distributions via a Probability Distribution Encoder (PDE) by utilizing sequence-level interactions. Compared to the existing deterministic methods, such uncertainty modeling can convey richer multimodal semantic information and more complex relationships. Furthermore, we integrate uncertainty modeling with popular pretraining frameworks and propose suitable pre-training tasks: Distribution-based vision-Language Contrastive learning (D-VLC), Distribution-based Masked Language Modeling (D-MLM), and Distribution-based Image-Text Matching (D-ITM). The fine-tuned models are applied to challenging downstream tasks, including image-text retrieval, visual question answering, visual reasoning, and visual entailment, and achieve state-of-the-art results.

关键词： Multi-modal learning

来源：评论

学校读者我要写书评

暂无评论

Angelic Patches for Improving Third-Party Object Detector Performance

Angelic Patches for Improving Third-Party Object Detector Pe...

引用

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

作者： Si, Wenwen Li, Shuo Park, Sangdon Lee, Insup Bastani, Osbert Univ Penn Dept Comp & Info Sci Philadelphia PA 19104 USA Georgia Inst Technol Sch Cybersecur & Privacy Atlanta GA 30332 USA

ISBN: (纸本)9798350301298

Deep learning models have shown extreme vulnerability to distribution shifts such as synthetic perturbations and spatial transformations. In this work, we explore whether we can adopt the characteristics of adversarial attack methods to help improve robustness of object detection to distribution shifts such as synthetic perturbations and spatial transformations. We study a class of realistic object detection settings wherein the target objects have control over their appearance. To this end, we propose a reversed Fast Gradient Sign Method (FGSM) to obtain these angelic patches that significantly increase the detection probability, even without pre-knowledge of the perturbations. In detail, we apply the patch to each object instance simultaneously, strengthening not only classification, but also bounding box accuracy. Experiments demonstrate the efficacy of the partial-covering patch in solving the complex bounding box problem. More importantly, the performance is also transferable to different detection models even under severe affine transformations and deformable shapes. To the best of our knowledge, we are the first object detection patch that achieves both cross-model efficacy and multiple patches. We observed average accuracy improvements of 30% in the real-world experiments. Our code is available at: https: //***/averysi224/angelic_patches.

关键词： computer vision for social good

来源：评论

学校读者我要写书评

暂无评论

Train-Once-for-All Personalization

Train-Once-for-All Personalization

引用

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

作者： Chen, Hong-You Li, Yandong Cui, Yin Zhang, Mingda Chao, Wei-Lun Zhang, Li Ohio State Univ Columbus OH 43210 USA Google Res Mountain View CA 94043 USA

ISBN: (纸本)9798350301298

We study the problem of how to train a "personalization-friendly" model such that given only the task descriptions, the model can be adapted to different end-users' needs, e.g., for accurately classifying different subsets of objects. One baseline approach is to train a "generic" model for classifying a wide range of objects, followed by class selection. In our experiments, we however found it suboptimal, perhaps because the model's weights are kept frozen without being personalized. To address this drawback, we propose Train-once-for-All PERsonalization (TAPER), a framework that is trained just once and can later customize a model for different end-users given their task descriptions. TAPER learns a set of "basis" models and a mixer predictor, such that given the task description, the weights (not the predictions!) of the basis models can be on the fly combined into a single "personalized" model. Via extensive experiments on multiple recognition tasks, we show that TAPER consistently outperforms the baseline methods in achieving a higher personalized accuracy. Moreover, we show that TAPER can synthesize a much smaller model to achieve comparable performance to a huge generic model, making it "deployment-friendly" to resource-limited end devices. Interestingly, even without end-users' task descriptions, TAPER can still be specialized to the deployed context based on its past predictions, making it even more "personalization-friendly".

关键词： Efficient and scalable vision

来源：评论

学校读者我要写书评

暂无评论

Learning Discriminative Representations for Skeleton Based Action recognition

Learning Discriminative Representations for Skeleton Based A...

引用

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

作者： Zhou, Huanyu Liu, Qingjie Wang, Yunhong Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing Peoples R China Zhongguancun Lab Beijing Peoples R China Beihang Univ Hangzhou Innovat Inst Beijing Peoples R China

ISBN: (纸本)9798350301298

Human action recognition aims at classifying the category of human action from a segment of a video. Recently, people have dived into designing GCN-based models to extract features from skeletons for performing this task, because skeleton representations are much more efficient and robust than other modalities such as RGB frames. However, when employing the skeleton data, some important clues like related items are also discarded. It results in some ambiguous actions that are hard to be distinguished and tend to be misclassified. To alleviate this problem, we propose an auxiliary feature refinement head (FR Head), which consists of spatial-temporal decoupling and contrastive feature refinement, to obtain discriminative representations of skeletons. Ambiguous samples are dynamically discovered and calibrated in the feature space. Furthermore, FR Head could be imposed on different stages of GCNs to build a multi-level refinement for stronger supervision. Extensive experiments are conducted on NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets. Our proposed models obtain competitive results from state-of-the-art methods and can help to discriminate those ambiguous samples. Codes are available at https://***/zhysora/FR-Head.

关键词： Video: Action and event understanding

来源：评论

学校读者我要写书评

暂无评论

Dynamic Inference with Grounding Based vision and Language Models

Dynamic Inference with Grounding Based Vision and Language M...

引用

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

作者： Uzkent, Burak Garg, Amanmeet Zhu, Wentao Doshi, Keval Yi, Jingru Wang, Xiaolong Omar, Mohamed Amazon Prime Video Seattle WA 30439 USA

ISBN: (纸本)9798350301298

Transformers have been recently utilized for vision and language tasks successfully. For example, recent image and language models with more than 200M parameters have been proposed to learn visual grounding in the pre-training step and show impressive results on downstream vision and language tasks. On the other hand, there exists a large amount of computational redundancy in these large models which skips their run-time efficiency. To address this problem, we propose dynamic inference for grounding based vision and language models conditioned on the input imagetext pair. We first design an approach to dynamically skip multihead self-attention and feed forward network layers across two backbones and multimodal network. Additionally, we propose dynamic token pruning and fusion for two backbones. In particular, we remove redundant tokens at different levels of the backbones and fuse the image tokens with the language tokens in an adaptive manner. To learn policies for dynamic inference, we train agents using reinforcement learning. In this direction, we replace the CNN backbone in a recent grounding-based vision and language model, MDETR, with a vision transformer and call it ViTMDETR. Then, we apply our dynamic inference method to ViTMDETR, called D-ViTDMETR, and perform experiments on image-language tasks. Our results show that we can improve the run-time efficiency of the state-of-the-art models MDETR and GLIP by up to similar to 50% on Referring Expression Comprehension and Segmentation, and VQA with only maximum similar to 0.3% accuracy drop.

关键词： Efficient and scalable vision

来源：评论

学校读者我要写书评

暂无评论

Unbalanced Optimal Transport: A Unified Framework for Object Detection

Unbalanced Optimal Transport: A Unified Framework for Object...

引用

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

作者： De Plaen, Henri De Plaen, Pierre-Francois Suykens, Johan A. K. Proesmans, Marc Tuytelaars, Tinne Van Gool, Luc Katholieke Univ Leuven ESAT STADIUS Leuven Belgium Katholieke Univ Leuven ESAT PSI Leuven Belgium Swiss Fed Inst Technol Comp Vis Lab Zurich Switzerland

ISBN: (纸本)9798350301298

During training, supervised object detection tries to correctly match the predicted bounding boxes and associated classification scores to the ground truth. This is essential to determine which predictions are to be pushed towards which solutions, or to be discarded. Popular matching strategies include matching to the closest ground truth box (mostly used in combination with anchors), or matching via the Hungarian algorithm (mostly used in anchor-free methods). Each of these strategies comes with its own properties, underlying losses, and heuristics. We show how Unbalanced Optimal Transport unifies these different approaches and opens a whole continuum of methods in between. This allows for a finer selection of the desired properties. Experimentally, we show that training an object detection model with Unbalanced Optimal Transport is able to reach the state-of-the-art both in terms of Average Precision and Average Recall as well as to provide a faster initial convergence. The approach is well suited for GPU implementation, which proves to be an advantage for large-scale models.

关键词： computer vision theory

来源：评论

学校读者我要写书评

暂无评论

Real-time 6K Image Rescaling with Rate-distortion Optimization

Real-time 6K Image Rescaling with Rate-distortion Optimizati...

引用

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

作者： Qi, Chenyang Yang, Xin Cheng, Ka Leong Chen, Ying-Cong Chen, Qifeng Hong Kong Univ Sci & Technol Hong Kong Peoples R China

ISBN: (纸本)9798350301298

Contemporary image rescaling aims at embedding a high-resolution (HR) image into a low-resolution (LR) thumbnail image that contains embedded information for HR image reconstruction. Unlike traditional image super-resolution, this enables high-fidelity HR image restoration faithful to the original one, given the embedded information in the LR thumbnail. However, state-of-the-art image rescaling methods do not optimize the LR image file size for efficient sharing and fall short of real-time performance for ultra-high-resolution (e.g., 6K) image reconstruction. To address these two challenges, we propose a novel framework (HyperThumbnail) for real-time 6K rate-distortion-aware image rescaling. Our framework first embeds an HR image into a JPEG LR thumbnail by an encoder with our proposed quantization prediction module, which minimizes the file size of the embedding LR JPEG thumbnail while maximizing HR reconstruction quality. Then, an efficient frequency-aware decoder reconstructs a high-fidelity HR image from the LR one in real time. Extensive experiments demonstrate that our framework outperforms previous image rescaling baselines in rate-distortion performance and can perform 6K image reconstruction in real time.

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

DepGraph: Towards Any Structural Pruning

DepGraph: Towards Any Structural Pruning

引用

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

作者： Fang, Gongfan Ma, Xinyin Song, Mingli Mi, Michael Bi Wang, Xinchao Natl Univ Singapore Singapore Singapore Zhejiang Univ Hangzhou Peoples R China Huawei Technol Ltd Shenzhen Peoples R China

ISBN: (纸本)9798350301298

Structural pruning enables model acceleration by removing structurally-grouped parameters from neural networks. However, the parameter-grouping patterns vary widely across different models, making architecture-specific pruners, which rely on manually-designed grouping schemes, non-generalizable to new architectures. In this work, we study a highly-challenging yet barely-explored task, any structural pruning, to tackle general structural pruning of arbitrary architecture like CNNs, RNNs, GNNs and Transformers. The most prominent obstacle towards this goal lies in the structural coupling, which not only forces different layers to be pruned simultaneously, but also expects all removed parameters to be consistently unimportant, thereby avoiding structural issues and significant performance degradation after pruning. To address this problem, we propose a general and fully automatic method, Dependency Graph (DepGraph), to explicitly model the dependency between layers and comprehensively group coupled parameters for pruning. In this work, we extensively evaluate our method on several architectures and tasks, including ResNe(X)t, DenseNet, MobileNet and vision transformer for images, GAT for graph, DGCNN for 3D point cloud, alongside LSTM for language, and demonstrate that, even with a simple norm-based criterion, the proposed method consistently yields gratifying performances.

关键词： Efficient and scalable vision

来源：评论

学校读者我要写书评

暂无评论

Learning Customized Visual Models with Retrieval-Augmented Knowledge

Learning Customized Visual Models with Retrieval-Augmented K...

引用

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

作者： Liu, Haotian Son, Kilho Yang, Jianwei Liu, Ce Gao, Jianfeng Lee, Yong Jae Li, Chunyuan Univ Wisconsin Madison Madison WI 53706 USA Microsoft Redmond WA USA

ISBN: (纸本)9798350301298

Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept coverage, followed by expensive pre-training to feed all the knowledge into model weights. Alternatively, we propose REACT, REtrieval-Augmented CusTomization, a framework to acquire the relevant web knowledge to build customized visual models for target domains. We retrieve the most relevant image-text pairs (similar to 3% of CLIP pre-training data) from the web-scale database as external knowledge and propose to customize the model by only training new modularized blocks while freezing all the original weights. The effectiveness of REACT is demonstrated via extensive experiments on classification, retrieval, detection and segmentation tasks, including zero, few, and full-shot settings. Particularly, on the zero-shot classification task, compared with CLIP, it achieves up to 5.4% improvement on ImageNet and 3.7% on the ELEVATER benchmark (20 datasets).

关键词： and reasoning language vision

来源：评论

学校读者我要写书评

暂无评论

Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme Low-Light Photography

Physics-Guided ISO-Dependent Sensor Noise Modeling for Extre...

引用

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

作者： Cao, Yue Liu, Ming Liu, Shuai Wang, Xiaotao Lei, Lei Zuo, Wangmeng Harbin Inst Technol Sch Comp Sci & Technol Harbin Peoples R China Peng Cheng Lab Shenzhen Peoples R China

ISBN: (纸本)9798350301298

Although deep neural networks have achieved astonishing performance in many vision tasks, existing learning-based methods are far inferior to the physical model-based solutions in extreme low-light sensor noise modeling. To tap the potential of learning-based sensor noise modeling, we investigate the noise formation in a typical imaging process and propose a novel physics-guided ISO-dependent sensor noise modeling approach. Specifically, we build a normalizing flow-based framework to represent the complex noise characteristics of CMOS camera sensors. Each component of the noise model is dedicated to a particular kind of noise under the guidance of physical models. Moreover, we take into consideration of the ISO dependence in the noise model, which is not completely considered by the existing learning-based methods. For training the proposed noise model, a new dataset is further collected with paired noisy-clean images, as well as flat-field and bias frames covering a wide range of ISO settings. Compared to existing methods, the proposed noise model is equipped with a flexible structure and accurate modeling capabilities, which is beneficial for better denoising performance in extreme low-light scenes. The dataset and code are available at https://***/happycaoyue/LLD.

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 << < 23 24 25 26 27 28 29 30 31 32 > >>

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：