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

283 篇 会议
41 册 图书
3 篇 期刊文献

馆藏范围

327 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

171 篇 工学
- 152 篇 计算机科学与技术...
- 93 篇 软件工程
- 47 篇 光学工程
- 35 篇 信息与通信工程
- 28 篇 生物工程
- 22 篇 电气工程
- 16 篇 控制科学与工程
- 9 篇 电子科学与技术（可...
- 8 篇 化学工程与技术
- 8 篇 生物医学工程（可授...
- 6 篇 网络空间安全
- 5 篇 机械工程
- 5 篇 安全科学与工程
- 3 篇 仪器科学与技术
- 3 篇 材料科学与工程（可...
- 3 篇 建筑学
- 3 篇 农业工程
78 篇 理学
- 48 篇 物理学
- 30 篇 生物学
- 25 篇 数学
- 11 篇 统计学（可授理学、...
- 8 篇 化学
21 篇 医学
- 16 篇 临床医学
- 4 篇 公共卫生与预防医...
- 3 篇 基础医学(可授医学...
- 3 篇 特种医学
18 篇 管理学
- 10 篇 管理科学与工程(可...
- 9 篇 图书情报与档案管...
- 5 篇 工商管理
4 篇 农学
- 4 篇 作物学
2 篇 法学
2 篇 教育学

主题

37 篇 computer vision
25 篇 image processing...
21 篇 artificial intel...
20 篇 pattern recognit...
20 篇 computer imaging...
17 篇 machine learning
14 篇 computer applica...
13 篇 computer systems...
12 篇 signal, image an...
11 篇 deep learning
8 篇 image processing
6 篇 computers and ed...
5 篇 vision transform...
5 篇 low-level vision
4 篇 image enhancemen...
4 篇 object detection
4 篇 cell microscopy
4 篇 image segmentati...
4 篇 graphics process...
4 篇 stereo image pro...

机构

17 篇 microsoft resear...
17 篇 microsoft res as...
12 篇 tsinghua univers...
7 篇 university of sc...
7 篇 univ sci & techn...
6 篇 national key lab...
6 篇 shanghai collabo...
6 篇 shanghai key lab...
5 篇 university of te...
5 篇 dalian universit...
5 篇 university of sy...
5 篇 institute of aut...
5 篇 shenzhen univers...
4 篇 key laboratory o...
4 篇 national enginee...
4 篇 university of ud...
4 篇 tsinghua univ pe...
4 篇 microsoft cloud ...
4 篇 university of yo...
4 篇 vision and image...

作者

8 篇 han hu
7 篇 hu han
6 篇 zuxuan wu
6 篇 min xu
5 篇 hui huang
5 篇 jing dong
5 篇 yu-gang jiang
5 篇 jiwen lu
5 篇 risheng liu
5 篇 wanli ouyang
5 篇 huchuan lu
4 篇 gian luca forest...
4 篇 qi dai
4 篇 zhiguo cao
4 篇 dongdong chen
4 篇 edwin hancock
4 篇 boxin shi
4 篇 jean-jacques rou...
4 篇 zheng zhang
4 篇 andrea fusiello

语言

322 篇 英文
5 篇 其他
3 篇 中文

检索条件"任意字段=2023 Asia Conference on Computer Vision, Image Processing and Pattern Recognition, CVIPPR 2023"

共 327 条记录，以下是31-40 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：

Learning Distortion Invariant Representation for image Restoration from A Causality Perspective

Learning Distortion Invariant Representation for Image Resto...

引用

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

作者： Li, Xin Li, Bingchen Jin, Xin Lan, Cuiling Chen, Zhibo Univ Sci & Technol China Hefei Peoples R China Eastern Inst Adv Study Ningbo Peoples R China Microsoft Res Asia Beijing Peoples R China

ISBN: (纸本)9798350301298

In recent years, we have witnessed the great advancement of Deep neural networks (DNNs) in image restoration. However, a critical limitation is that they cannot generalize well to real-world degradations with different degrees or types. In this paper, we are the first to propose a novel training strategy for image restoration from the causality perspective, to improve the generalization ability of DNNs for unknown degradations. Our method, termed Distortion Invariant representation Learning (DIL), treats each distortion type and degree as one specific confounder, and learns the distortion-invariant representation by eliminating the harmful confounding effect of each degradation. We derive our DIL with the back-door criterion in causality by modeling the interventions of different distortions from the optimization perspective. Particularly, we introduce counterfactual distortion augmentation to simulate the virtual distortion types and degrees as the confounders. Then, we instantiate the intervention of each distortion with a virtual model updating based on corresponding distorted images, and eliminate them from the meta-learning perspective. Extensive experiments demonstrate the generalization capability of our DIL on unseen distortion types and degrees. Our code will be available at https://***/lixinustc/Causal-IR-DIL.

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping

Bootstrapping Objectness from Videos by Relaxed Common Fate ...

引用

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

作者： Lian, Long Wu, Zhirong Yu, Stella X. Univ Calif Berkeley Berkeley CA 94720 USA Microsoft Res Asia Beijing Peoples R China Univ Michigan Ann Arbor MI USA

ISBN: (纸本)9798350301298

We study learning object segmentation from unlabeled videos. Humans can easily segment moving objects without knowing what they are. The Gestalt law of common fate, i.e., what move at the same speed belong together, has inspired unsupervised object discovery based on motion segmentation. However, common fate is not a reliable indicator of objectness: Parts of an articulated / deformable object may not move at the same speed, whereas shadows / reflections of an object always move with it but are not part of it. Our insight is to bootstrap objectness by first learning image features from relaxed common fate and then refining them based on visual appearance grouping within the image itself and across images statistically. Specifically, we learn an image segmenter first in the loop of approximating optical flow with constant segment flow plus small within-segment residual flow, and then by refining it for more coherent appearance and statistical figure-ground relevance. On unsupervised video object segmentation, using only ResNet and convolutional heads, our model surpasses the state-of-the-art by absolute gains of 7/9/5% on DAVIS16 / STv2 / FBMS59 respectively, demonstrating the effectiveness of our ideas. Our code is publicly available.

关键词： motion tracking Video: Low-level analysis

来源：评论

学校读者我要写书评

暂无评论

Learning to Exploit Temporal Structure for Biomedical vision-Language processing

Learning to Exploit Temporal Structure for Biomedical Vision...

引用

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

作者： Bannur, Shruthi Hyland, Stephanie Liu, Qianchu Perez-Garcia, Fernando Ilse, Maximilian Castro, Daniel C. Boecking, Benedikt Sharma, Harshita Bouzid, Kenza Thieme, Anja Schwaighofer, Anton Wetscherek, Maria Lungren, Matthew P. Nori, Aditya Alvarez-Valle, Javier Oktay, Ozan Microsoft Hlth Futures Redmond WA 98052 USA

ISBN: (纸本)9798350301298

Self-supervised learning in vision-language processing (VLP) exploits semantic alignment between imaging and text modalities. Prior work in biomedical VLP has mostly relied on the alignment of single image and report pairs even though clinical notes commonly refer to prior images. This does not only introduce poor alignment between the modalities but also a missed opportunity to exploit rich self-supervision through existing temporal content in the data. In this work, we explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model. It is designed to be versatile to arising challenges such as pose variations and missing input images across time. The resulting model excels on downstream tasks both in single- and multi-image setups, achieving state-of-the-art (SOTA) performance on (I) progression classification, (II) phrase grounding, and (III) report generation, whilst offering consistent improvements on disease classification and sentence-similarity tasks. We release a novel multi-modal temporal benchmark dataset, MS-CXR-T, to quantify the quality of vision-language representations in terms of temporal semantics. Our experimental results show the advantages of incorporating prior images and reports to make most use of the data.

关键词： cell microscopy Medical and biological vision

来源：评论

学校读者我要写书评

暂无评论

Learning to Exploit the Sequence-Specific Prior Knowledge for image processing Pipelines Optimization

Learning to Exploit the Sequence-Specific Prior Knowledge fo...

引用

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

作者： Qin, Haina Han, Longfei Xiong, Weihua Wang, Juan Ma, Wentao Li, Bing Hu, Weiming Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Beijing Technol & Business Univ Beijing Peoples R China Zeku Technol Shanghai Peoples R China

ISBN: (纸本)9798350301298

The hardware image signal processing (ISP) pipeline is the intermediate layer between the imaging sensor and the downstream application, processing the sensor signal into an RGB image. The ISP is less programmable and consists of a series of processing modules. Each processing module handles a subtask and contains a set of tunable hyperparameters. A large number of hyperparameters form a complex mapping with the ISP output. The industry typically relies on manual and time-consuming hyperparameter tuning by image experts, biased towards human perception. Recently, several automatic ISP hyperparameter optimization methods using downstream evaluation metrics come into sight. However, existing methods for ISP tuning treat the high-dimensional parameter space as a global space for optimization and prediction all at once without inducing the structure knowledge of ISP. To this end, we propose a sequential ISP hyperparameter prediction framework that utilizes the sequential relationship within ISP modules and the similarity among parameters to guide the model sequence process. We validate the proposed method on object detection, image segmentation, and image quality tasks.

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

MaskCLIP: Masked Self-Distillation Advances Contrastive Language-image Pretraining

MaskCLIP: Masked Self-Distillation Advances Contrastive Lang...

引用

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

作者： Dong, Xiaoyi Bao, Jianmin Zheng, Yinglin Zhang, Ting Chen, Dongdong Yang, Hao Zeng, Ming Zhang, Weiming Yuan, Lu Chen, Dong Wen, Fang Yu, Nenghai Univ Sci & Technol China Hefei Anhui Peoples R China Microsoft Res Asia Beijing Peoples R China Xiamen Univ Xiamen Peoples R China Microsoft Cloud AI Orlando FL USA

ISBN: (纸本)9798350301298

This paper presents a simple yet effective framework MaskCLIP, which incorporates a newly proposed masked self-distillation into contrastive language-image pretraining. The core idea of masked self-distillation is to distill representation from a full image to the representation predicted from a masked image. Such incorporation enjoys two vital benefits. First, masked self-distillation targets local patch representation learning, which is complementary to vision-language contrastive focusing on text-related representation. Second, masked self-distillation is also consistent with vision-language contrastive from the perspective of training objective as both utilize the visual encoder for feature aligning, and thus is able to learn local semantics getting indirect supervision from the language. We provide specially designed experiments with a comprehensive analysis to validate the two benefits. Symmetrically, we also introduce the local semantic supervision into the text branch, which further improves the pretraining performance. With extensive experiments, we show that MaskCLIP, when applied to various challenging downstream tasks, achieves superior results in linear probing, finetuning, and zero-shot performance with the guidance of the language encoder. Code will be release at https://***/LightDXY/MaskCLIP.

关键词： detection recognition: Categorization retrieval

来源：评论

学校读者我要写书评

暂无评论

Single target tracking method in low illumination video based on computer vision 3

Single target tracking method in low illumination video base...

引用

3rd asia-Pacific conference on Communications Technology and computer Science (ACCTCS)

作者： Yin, Yanlin Han, Rui Song, Yingjie Sun, Shiguang Heilongjiang Univ Technol Sch Elect & Informat Engn Jixi 158100 Heilongjiang Peoples R China Heilongjiang Univ Technol Sch Int Educ Jixi 158100 Heilongjiang Peoples R China

ISBN: (纸本)9798350310801

Aiming at the problem that the single target tracking effect of low illumination video is poor, a low illumination video single target tracking method based on computer vision is proposed. The computer vision processing algorithm is used to enhance the video image, and the sharpening components in the images at all levels are controlled by parameters to suppress the high-frequency noise of low illumination video. In order to better expand the dynamic range of the overall gray level of the enhanced image, this paper adopts an improved computer vision method to adjust the contrast of the video image, so as to achieve the requirements of low illumination video but target tracking. Finally, from the simulation results, it can be seen that the low illumination video single target tracking method based on computer vision has better integrity and accuracy, and the short-term occlusion of moving targets can achieve a better tracking effect.

关键词： computer vision Low illumination video Single target tracking

来源：评论

学校读者我要写书评

暂无评论

On Data Scaling in Masked image Modeling

On Data Scaling in Masked Image Modeling

引用

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

作者： Xie, Zhenda Zhang, Zheng Cao, Yue Lin, Yutong Wei, Yixuan Dai, Qi Hu, Han Tsinghua Univ Beijing Peoples R China Xi An Jiao Tong Univ Xian Shaanxi Peoples R China Microsoft Res Asia Beijing Peoples R China

ISBN: (纸本)9798350301298

Scaling properties have been one of the central issues in self-supervised pre-training, especially the data scalability, which has successfully motivated the large-scale self-supervised pre-trained language models and endowed them with significant modeling capabilities. However, scaling properties seem to be unintentionally neglected in the recent trending studies on masked image modeling (MIM), and some arguments even suggest that MIM cannot benefit from large-scale data. In this work, we try to break down these preconceptions and systematically study the scaling behaviors of MIM through extensive experiments, with data ranging from 10% of imageNet-1K to full imageNet-22K, model parameters ranging from 49-million to one-billion, and training length ranging from 125K to 500K iterations. And our main findings can be summarized in two folds: 1) masked image modeling remains demanding large-scale data in order to scale up computes and model parameters;2) masked image modeling cannot benefit from more data under a non-overfitting scenario, which diverges from the previous observations in self-supervised pre-trained language models or supervised pre-trained vision models. In addition, we reveal several intriguing properties in MIM, such as high sample efficiency in large MIM models and strong correlation between pre-training validation loss and transfer performance. We hope that our findings could deepen the understanding of masked image modeling and facilitate future developments on large-scale vision models. Code and models will be available at https://***/microsoft/SimMIM.

关键词： Self-supervised or unsupervised representation learning

来源：评论

学校读者我要写书评

暂无评论

Structural Multiplane image: Bridging Neural View Synthesis and 3D Reconstruction

Structural Multiplane Image: Bridging Neural View Synthesis ...

引用

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

作者： Zhang, Mingfang Wang, Jinglu Li, Xiao Huang, Yifei Sato, Yoichi Lu, Yan Univ Tokyo Tokyo Japan Microsoft Res Asia Beijing Peoples R China

ISBN: (纸本)9798350301298

The Multiplane image (MPI), containing a set of fronto-parallel RGBa layers, is an effective and efficient representation for view synthesis from sparse inputs. Yet, its fixed structure limits the performance, especially for surfaces imaged at oblique angles. We introduce the Structural MPI (SMPI), where the plane structure approximates 3D scenes concisely. Conveying RGBa contexts with geometrically-faithful structures, the S-MPI directly bridges view synthesis and 3D reconstruction. It can not only overcome the critical limitations of MPI, i.e., discretization artifacts from sloped surfaces and abuse of redundant layers, and can also acquire planar 3D reconstruction. Despite the intuition and demand of applying S-MPI, great challenges are introduced, e.g., high-fidelity approximation for both RGBa layers and plane poses, multi-view consistency, non-planar regions modeling, and efficient rendering with intersected planes. Accordingly, we propose a transformer-based network based on a segmentation model [4]. It predicts compact and expressive S-MPI layers with their corresponding masks, poses, and RGBa contexts. Non-planar regions are inclusively handled as a special case in our unified framework. Multi-view consistency is ensured by sharing global proxy embeddings, which encode plane-level features covering the complete 3D scenes with aligned coordinates. Intensive experiments show that our method outperforms both previous state-of-the-art MPI-based view synthesis methods and planar reconstruction methods.

关键词： image and video synthesis and generation

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Neural Memory Network for Low Latency Event processing

Hierarchical Neural Memory Network for Low Latency Event Pro...

引用

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

作者： Hamaguchi, Ryuhei Furukawa, Yasutaka Onishi, Masaki Sakurada, Ken Natl Inst Adv Ind Sci & Technol Tokyo Japan Simon Fraser Univ Burnaby BC Canada

ISBN: (纸本)9798350301298

This paper proposes a low latency neural network architecture for event-based dense prediction tasks. Conventional architectures encode entire scene contents at a fixed rate regardless of their temporal characteristics. Instead, the proposed network encodes contents at a proper temporal scale depending on its movement speed. We achieve this by constructing temporal hierarchy using stacked latent memories that operate at different rates. Given low latency event steams, the multi-level memories gradually extract dynamic to static scene contents by propagating information from the fast to the slow memory modules. The architecture not only reduces the redundancy of conventional architectures but also exploits long-term dependencies. Furthermore, an attention-based event representation efficiently encodes sparse event streams into the memory cells. We conduct extensive evaluations on three event-based dense prediction tasks, where the proposed approach outperforms the existing methods on accuracy and latency, while demonstrating effective event and image fusion capabilities. The code is available at https://***/hmnet/.

关键词： Deep learning architectures and techniques

来源：评论

学校读者我要写书评

暂无评论

Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement

Gated Multi-Resolution Transfer Network for Burst Restoratio...

引用

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

作者： Mehta, Nancy Dudhane, Akshay Murala, Subrahmanyam Zamir, Syed Waqas Khan, Salman Khan, Fahad Shahbaz Indian Inst Technol Ropar CVPR Lab Rupnagar India Mohamed Bin Zayed Univ AI Abu Dhabi U Arab Emirates Incept Inst AI Abu Dhabi U Arab Emirates Australian Natl Univ Canberra ACT Australia Linkoping Univ Linkoping Sweden

ISBN: (纸本)9798350301298

Burst image processing is becoming increasingly popular in recent years. However, it is a challenging task since individual burst images undergo multiple degradations and often have mutual misalignments resulting in ghosting and zipper artifacts. Existing burst restoration methods usually do not consider the mutual correlation and non-local contextual information among burst frames, which tends to limit these approaches in challenging cases. Another key challenge lies in the robust up-sampling of burst frames. The existing up-sampling methods cannot effectively utilize the advantages of single-stage and progressive up-sampling strategies with conventional and/or recent up-samplers at the same time. To address these challenges, we propose a novel Gated Multi-Resolution Transfer Network (GMTNet) to reconstruct a spatially precise high-quality image from a burst of low-quality raw images. GMT-Net consists of three modules optimized for burst processing tasks: Multi-scale Burst Feature Alignment (MBFA) for feature denoising and alignment, Transposed-Attention Feature Merging (TAFM) for multi-frame feature aggregation, and Resolution Transfer Feature Up-sampler (RTFU) to up-scale merged features and construct a high-quality output image. Detailed experimental analysis on five datasets validate our approach and sets a state-of-the-art for burst super-resolution, burst denoising, and low-light burst enhancement. Our codes and models are available at https://***/nanmehta/GMTNet.

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33页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：