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

22,998 篇 会议
107 册 图书
93 篇 期刊文献

馆藏范围

23,197 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,621 篇 工学
- 11,107 篇 计算机科学与技术...
- 3,478 篇 软件工程
- 2,445 篇 机械工程
- 1,715 篇 光学工程
- 1,076 篇 电气工程
- 1,013 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
- 85 篇 交通运输工程
- 84 篇 土木工程
3,494 篇 医学
- 3,481 篇 临床医学
- 81 篇 基础医学(可授医学...
3,240 篇 理学
- 1,939 篇 物理学
- 1,639 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

10,186 篇 computer vision
3,967 篇 pattern recognit...
3,005 篇 training
2,007 篇 computational mo...
1,817 篇 visualization
1,815 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
62 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

23,131 篇 英文
38 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 23198 条记录，以下是4921-4930 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：

Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos

Bridge-Prompt: Towards Ordinal Action Understanding in Instr...

引用

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

作者： Li, Muheng Chen, Lei Duan, Yueqi Hu, Zhilan Feng, Jianjiang Zhou, Jie Lu, Jiwen Tsinghua Univ Dept Automat Beijing Peoples R China Tsinghua Univ Dept Elect Engn Beijing Peoples R China Huawei Technol Co Ltd Media Technol Inst Shenzhen Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Action recognition models have shown a promising capability to classify human actions in short video clips. In a real scenario, multiple correlated human actions commonly occur in particular orders, forming semantically meaningful human activities. Conventional action recognition approaches focus on analyzing single actions. However, they fail to fully reason about the contextual relations between adjacent actions, which provide potential temporal logic for understanding long videos. In this paper, we propose a prompt-based framework, Bridge-Prompt (Br-Prompt), to model the semantics across adjacent actions, so that it simultaneously exploits both out-of-context and contextual information from a series of ordinal actions in instructional videos. More specifically, we reformulate the individual action labels as integrated text prompts for supervision, which bridge the gap between individual action semantics. The generated text prompts are paired with corresponding video clips, and together co-train the text encoder and the video encoder via a contrastive approach. The learned vision encoder has a stronger capability for ordinal-action-related downstream tasks, e.g. action segmentation and human activity recognition. We evaluate the performances of our approach on several video datasets: Georgia Tech Egocentric Activities (GTEA), 50Salads, and the Breakfast dalaset. Br-Prompt achieves state-of-the-art on multiple benchmarks.

关键词： computer vision Codes Semantics Benchmark testing pattern recognition Task analysis Context modeling

来源：评论

学校读者我要写书评

暂无评论

Orthogonal Over-Parameterized Training

Orthogonal Over-Parameterized Training

引用

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

作者： Liu, Weiyang Lin, Rongmei Liu, Zhen Rehg, James M. Paull, Liam Xiong, Li Song, Le Weller, Adrian Univ Cambridge Cambridge England Max Planck Inst Intelligent Syst Stuttgart Germany Emory Univ Atlanta GA 30322 USA Univ Montreal Mila Montreal PQ Canada Georgia Inst Technol Atlanta GA 30332 USA Alan Turing Inst London England

ISBN: (纸本)9781665445092

The inductive bias of a neural network is largely determined by the architecture and the training algorithm. To achieve good generalization, how to effectively train a neural network is of great importance. We propose a novel orthogonal over-parameterized training (OPT) framework that can provably minimize the hyperspherical energy which characterizes the diversity of neurons on a hypersphere. By maintaining the minimum hyperspherical energy during training, OPT can greatly improve the empirical generalization. Specifically, OPT fixes the randomly initialized weights of the neurons and learns an orthogonal transformation that applies to these neurons. We consider multiple ways to learn such an orthogonal transformation, including unrolling orthogonalization algorithms, applying orthogonal parameterization, and designing orthogonality-preserving gradient descent. For better scalability, we propose the stochastic OPT which performs orthogonal transformation stochastically for partial dimensions of neurons. Interestingly, OPT reveals that learning a proper coordinate system for neurons is crucial to generalization. We provide some insights on why OPT yields better generalization. Extensive experiments validate the superiority of OPT over the standard training.

关键词： Training computer vision Scalability Neurons Optimized production technology computer architecture pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation with the Reused Teacher Classifier

Knowledge Distillation with the Reused Teacher Classifier

引用

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

作者： Chen, Defang Mei, Jian-Ping Zhang, Hailin Wang, Can Feng, Yan Chen, Chun Zhejiang Univ Hangzhou Zhejiang Peoples R China Zhejiang Univ Shanghai Inst Adv Study Hangzhou Zhejiang Peoples R China ZJU Bangsun Joint Res Ctr Hangzhou Zhejiang Peoples R China Zhejiang Univ Technol Hangzhou Zhejiang Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance. For this purpose, various approaches have been proposed over the past few years, generally with elaborately designed knowledge representations, which in turn increase the difficulty of model development and interpretation. In contrast, we empirically show that a simple knowledge distillation technique is enough to significantly narrow down the teacher-student performance gap. We directly reuse the discriminative classifier from the pre-trained teacher model for student inference and train a student encoder through feature alignment with a single l(2) loss. In this way, the student model is able to achieve exactly the same performance as the teacher model provided that their extracted features are perfectly aligned. An additional projector is developed to help the student encoder match with the teacher classifier, which renders our technique applicable to various teacher and student architectures. Extensive experiments demonstrate that our technique achieves state-of-the-art results at the modest cost of compression ratio due to the added projector.

关键词： computer vision Costs Computational modeling computer architecture Feature extraction pattern recognition

来源：评论

学校读者我要写书评

暂无评论

SViTT: Temporal Learning of Sparse Video-Text Transformers

SViTT: Temporal Learning of Sparse Video-Text Transformers

引用

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

作者： Li, Yi Min, Kyle Tripathi, Subarna Vasconcelos, Nuno Univ Calif San Diego La Jolla CA 92093 USA Intel Labs Santa Clara CA USA

ISBN: (纸本)9798350301298

Do video-text transformers learn to model temporal relationships across frames? Despite their immense capacity and the abundance of multimodal training data, recent work has revealed the strong tendency of video-text models towards frame-based spatial representations, while temporal reasoning remains largely unsolved. In this work, we identify several key challenges in temporal learning of video-text transformers: the spatiotemporal trade-off from limited network size;the curse of dimensionality for multi-frame modeling;and the diminishing returns of semantic information by extending clip length. Guided by these findings, we propose SViTT, a sparse video-text architecture that performs multi-frame reasoning with significantly lower cost than naive transformers with dense attention. Analogous to graph-based networks, SViTT employs two forms of sparsity: edge sparsity that limits the query-key communications between tokens in self-attention, and node sparsity that discards uninformative visual tokens. Trained with a curriculum which increases model sparsity with the clip length, SViTT outperforms dense transformer baselines on multiple video-text retrieval and question answering benchmarks, with a fraction of computational cost. Project page: http://***/projects/svitt.

关键词： and reasoning language vision

来源：评论

学校读者我要写书评

暂无评论

UnOS: Unified Unsupervised Optical-flow and Stereo-depth Estimation by Watching Videos 32

UnOS: Unified Unsupervised Optical-flow and Stereo-depth Est...

引用

32nd ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Wang, Yang Wang, Peng Yang, Zhenheng Luo, Chenxu Yang, Yi Xu, Wei Baidu Res Sunnyvale CA 94089 USA Univ Southern Calif Los Angeles CA 90007 USA Johns Hopkins Univ Baltimore MD 21218 USA

ISBN: (纸本)9781728132938

In this paper, we propose UnOS, an unified system for unsupervisedopticalflow and stereo depth estimation using convolutional neural network (CNN) by taking advantages of theirinherentgeometricalconsistency based on the rigidscene assumption [31]. UnOS significantly outperforms other state-of-the-art(SOTA) unsupervisedapproachesthat treatedthe two tasks independently. Specifically, given two consecutive stereo image pairsfrom a video, UnOS estimates per-pixel stereo depth images, camera ego-motion and opticalflow with three parallelCNNs. Based on these quantities, UnOS computes rigid optical flow and compares it againstthe opticalflow estimatedfrom the FlowNet, yielding pixels satisfying the rigid-sceneassumption. Then, we encourage geometricalconsistency between the two estimated flows within rigid regions, from which we derive a rigid-aware direct visual odometry (RDVO) module. We also propose rigid and occlusion-awareflow-consistency losses for the learning of UnOS. We evaluated our results on the popularKITTI datasetover 4 related tasks, i.e. stereo depth, opticalflow, visual odometry and motion segmentation.

关键词： Deep Learning Image and Video Synthesis Low-level vision Motion and Tracking Robotics + Driving

来源：评论

学校读者我要写书评

暂无评论

Recurrent Neural Networks with Intra-Frame Iterations for Video Deblurring 32

Recurrent Neural Networks with Intra-Frame Iterations for Vi...

引用

32nd ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Nah, Seungjun Son, Sanghyun Lee, Kyoung Mu Seoul Natl Univ Dept ECE ASRI Seoul South Korea

ISBN: (纸本)9781728132938

Recurrent neural networks (RNNs) are widely used for sequential data processing. Recent state-of-the-art video deblurringmethods bank on convolutionalrecurrentneural network architectures to exploit the temporal relationship between neighboringframes. In this work, we aim to improve the accuracy of recurrentmodels by adaptingthe hidden states transferredfrom pastframes to the frame being processed so that the relationsbetween video frames could be better used. We iteratively update the hidden state via reusing RNN cell parametersbefore predictingan output deblurredframe. Since we use existing parametersto update the hidden state, our method improves accuracy withoutadditionalmodules. As the architectureremains the same regardless of iteration number fewer iterationmodels can be considered as a partial computationalpath of the models with more *** take advantage of this property, we employ a stochasticmethod to optimize our iterative models better. At training time, we randomly choose the iteration number on the fly and apply a regularizationloss that favors less computation unless there are considerable reconstructiongains. We show that our method exhibits stateof-the-art video deblurringperformance while operatingin real-time speed.

关键词： Computational Photography Deep Learning Low-level vision

来源：评论

学校读者我要写书评

暂无评论

Situational Awareness Matters in 3D vision Language Reasoning

Situational Awareness Matters in 3D Vision Language Reasonin...

引用

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

作者： Man, Yunze Gui, Liang-Yan Wang, Yu-Xiong Univ Illinois Urbana IL 61801 USA

ISBN: (纸本)9798350353006

Being able to carry out complicated vision language reasoning tasks in 3D space represents a significant milestone in developing household robots and human-centered embodied AI. In this work, we demonstrate that a critical and distinct challenge in 3D vision language reasoning is the situational awareness, which incorporates two key components: (1) The autonomous agent grounds its self-location based on a language prompt. (2) The agent answers open-ended questions from the perspective of its calculated position. To address this challenge, we introduce SIG3D, an end-to-end Situation-Grounded model for 3D vision language reasoning. We tokenize the 3D scene into sparse voxel representation, and propose a language-grounded situation estimator, followed by a situated question answering module. Experiments on the SQA3D and ScanQA datasets show that SIG3D outperforms state-of-the-art models in situational estimation and question answering by a large margin (e.g., an enhancement of over 30% on situation accuracy). Subsequent analysis corroborates our architectural design choices, explores the distinct functions of visual and textual tokens, and highlights the importance of situational awareness in the domain of 3D question-answering. Project page is available at https://***/situation3d.

关键词： vision-Language Multi-modal 3D Reasoning

来源：评论

学校读者我要写书评

暂无评论

OCSampler: Compressing Videos to One Clip with Single-step Sampling

OCSampler: Compressing Videos to One Clip with Single-step S...

引用

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

作者： Lin, Jintao Duan, Haodong Chen, Kai Lin, Dahua Wang, Limin Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China SenseTime Res Shanghai Peoples R China Shanghai AI Lab Shanghai Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Videos incorporate rich semantics as well as redundant information. Seeking a compact yet effective video representation, e.g., sample informative frames from the entire video, is critical to efficient video recognition. There have been works that formulate frame sampling as a sequential decision task by selecting frames one by one according to their importance. In this paper, we present a more efficient framework named OCSampler, which explores such a representation with one short clip. OCSampler designs a new paradigm of learning instance-specific video condensation policies to select frames only in a single step. Rather than picking up frames sequentially like previous methods, we simply process a whole sequence at once. Accordingly, these policies are derived from a light-weighted skim network together with a simple yet effective policy network. Moreover, we extend the proposed method with a frame number budget, enabling the framework to produce correct predictions in high confidence with as few frames as possible. Experiments on various benchmarks demonstrate the effectiveness of OCSampler over previous methods in terms of accuracy and efficiency. Specifically, it achieves 76.9% mAP and 21.7 GFLOPs on ActivityNet with an impressive throughput: 123.9 Video/s on a single TITAN Xp GPU.

关键词： computer vision Semantics Graphics processing units Benchmark testing Throughput Sampling methods pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Defocus Map Estimation using Domain Adaptation 32

Deep Defocus Map Estimation using Domain Adaptation

引用

32nd ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Lee, Junyong Lee, Sungkil Cho, Sunghyun Lee, Seungyong POSTECH Pohang South Korea Sungkyunkwan Univ Seoul South Korea DGIST Daegu South Korea

ISBN: (纸本)9781728132938

In this paper, we propose the first end-to-end convolutional neural network (CNN) architecture, Defocus Map Estimation Network (DMENet), for spatially varying defocus map estimation. To train the network, we produce a novel depth-of-field (DOF) dataset, SYNDOF, where each image is synthetically blurred with a ground-truth depth map. Due to the synthetic nature of SYNDOF, the feature characteristics of images in SYNDOF can differ from those of real defocused photos. To address this gap, we use domain adaptation that transfers the features of real defocused photos into those of synthetically blurred ones. Our DMENet consists of four subnetworks: blur estimation, domain adaptation, content preservation, and sharpness calibration networks. The subnetworks are connected to each other and jointly trained with their corresponding supervisions in an end-to end manner Our method is evaluated on publicly available blur detection and blur estimation datasets and the results show the state-of-the-art performance.

关键词： Computational Photography Low-level vision

来源：评论

学校读者我要写书评

暂无评论

Automatic High Resolution Wire Segmentation and Removal

Automatic High Resolution Wire Segmentation and Removal

引用

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

作者： Chiu, Mang Tik Zhang, Xuaner Wei, Zijun Zhou, Yuqian Shechtman, Eli Barnes, Connelly Lin, Zhe Kainz, Florian Amirghodsi, Sohrab Shi, Humphrey UIUC Champaign IL 61801 USA Adobe San Jose CA USA Univ Oregon Eugene OR USA

ISBN: (纸本)9798350301298

Wires and powerlines are common visual distractions that often undermine the aesthetics of photographs. The manual process of precisely segmenting and removing them is extremely tedious and may take up hours, especially on high-resolution photos where wires may span the entire space. In this paper, we present an automatic wire clean-up system that eases the process of wire segmentation and removal/inpainting to within a few seconds. We observe several unique challenges: wires are thin, lengthy, and sparse. These are rare properties of subjects that common segmentation tasks cannot handle, especially in high-resolution images. We thus propose a two-stage method that leverages both global and local contexts to accurately segment wires in high-resolution images efficiently, and a tile-based inpainting strategy to remove the wires given our predicted segmentation masks. We also introduce the first wire segmentation benchmark dataset, WireSegHR. Finally, we demonstrate quantitatively and qualitatively that our wire clean-up system enables fully automated wire removal with great generalization to various wire appearances.

关键词： vision applications and systems

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 << < 489 490 491 492 493 494 495 496 497 498 > >>

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：