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

3,310 篇 会议
3 篇 期刊文献

馆藏范围

3,313 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,936 篇 工学
- 1,843 篇 计算机科学与技术...
- 201 篇 软件工程
- 147 篇 机械工程
- 134 篇 光学工程
- 41 篇 生物工程
- 28 篇 信息与通信工程
- 18 篇 电气工程
- 13 篇 控制科学与工程
- 9 篇 电子科学与技术（可...
- 9 篇 化学工程与技术
- 9 篇 交通运输工程
- 8 篇 生物医学工程（可授...
- 7 篇 安全科学与工程
- 4 篇 材料科学与工程（可...
- 4 篇 建筑学
- 3 篇 土木工程
- 3 篇 农业工程
360 篇 医学
- 359 篇 临床医学
- 3 篇 基础医学(可授医学...
178 篇 理学
- 137 篇 物理学
- 42 篇 生物学
- 30 篇 数学
- 16 篇 统计学（可授理学、...
- 10 篇 化学
- 3 篇 系统科学
14 篇 管理学
- 7 篇 管理科学与工程(可...
- 7 篇 图书情报与档案管...
- 3 篇 工商管理
5 篇 法学
- 3 篇 社会学
- 2 篇 法学
2 篇 教育学
2 篇 农学
1 篇 经济学

主题

1,738 篇 computer vision
900 篇 training
802 篇 conferences
643 篇 pattern recognit...
482 篇 computational mo...
431 篇 computer archite...
430 篇 task analysis
426 篇 visualization
350 篇 feature extracti...
317 篇 semantics
308 篇 three-dimensiona...
243 篇 neural networks
227 篇 benchmark testin...
222 篇 cameras
183 篇 image segmentati...
177 篇 estimation
168 篇 deep learning
156 篇 measurement
154 篇 object detection
151 篇 data models

机构

40 篇 univ sci & techn...
31 篇 peng cheng lab p...
29 篇 swiss fed inst t...
29 篇 sensetime res pe...
27 篇 university of sc...
27 篇 zhejiang univ pe...
26 篇 univ chinese aca...
26 篇 swiss fed inst t...
25 篇 university of ch...
24 篇 tsinghua univ pe...
24 篇 univ chinese aca...
24 篇 nanyang technol ...
24 篇 sun yat sen univ...
22 篇 peng cheng labor...
20 篇 shanghai ai lab ...
20 篇 korea adv inst s...
19 篇 chinese univ hon...
19 篇 yonsei univ
18 篇 peking univ peop...
18 篇 tsinghua univers...

作者

65 篇 timofte radu
21 篇 loy chen change
18 篇 van gool luc
18 篇 radu timofte
16 篇 zha zheng-jun
14 篇 sun jian
12 篇 fan haoqiang
12 篇 chen wei-ting
12 篇 lei lei
12 篇 qiao yu
11 篇 zheng wei-shi
11 篇 zheng-jun zha
11 篇 liu shuaicheng
11 篇 qi tian
11 篇 luc van gool
11 篇 marcos v. conde
11 篇 liu shuai
11 篇 van de weijer jo...
10 篇 danelljan martin
10 篇 kim seon joo

语言

3,311 篇 英文
2 篇 其他

检索条件"任意字段=2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020"

共 3313 条记录，以下是311-320 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：

Sparse Multimodal vision Transformer for Weakly Supervised Semantic Segmentation

Sparse Multimodal Vision Transformer for Weakly Supervised S...

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Hanna, Joëlle Mommert, Michael Borth, Damian University of St.Gallen AIML Lab School of Computer Science Switzerland

ISBN: (纸本)9798350302493

vision Transformers have proven their versatility and utility for complex computer vision tasks, such as land cover segmentation in remote sensing applications. While performing on par or even outperforming other methods like Convolutional Neural Networks (CNNs), Transformers tend to require even larger datasets with fine-grained annotations (e.g., pixel-level labels for land cover segmentation). To overcome this limitation, we propose a weakly-supervised vision Transformer that leverages image-level labels to learn a semantic segmentation task to reduce the human annotation load. We achieve this by slightly modifying the architecture of the vision Transformer through the use of gating units in each attention head to enforce sparsity during training and thereby retaining only the most meaningful heads. This allows us to directly infer pixel-level labels from image-level labels by post-processing the un-pruned attention heads of the model and refining our predictions by iteratively training a segmentation model with high fidelity. Training and evaluation on the DFC2020 dataset show that our method1 not only generates high-quality segmentation masks using image-level labels, but also performs on par with fully-supervised training relying on pixel-level labels. Finally, our results show that our method is able to perform weakly-supervised semantic segmentation even on small-scale datasets. © 2023 ieee.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Integrating Pose and Mask Predictions for Multi-person in Videos

Integrating Pose and Mask Predictions for Multi-person in Vi...

引用

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

作者： Heo, Miran Hwang, Sukjun Oh, Seoung Wug Lee, Joon-Young Kim, Seon Joo Yonsei Univ Seoul South Korea Adobe Res San Jose CA USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

In real-world applications for video editing, humans are arguably the most important objects. When editing videos of humans, the efficient tracking of fine-grained masks and body joints is the fundamental requirement. In this paper, we propose a simple and efficient system for jointly tracking pose and segmenting high-quality masks for all humans in the video. We design a pipeline that globally tracks pose and locally segments fine-grained masks. Specifically, CenterTrack is first employed to track human poses by viewing the whole scene, and then the proposed local segmentation network leverages the pose information as a powerful query to carry out high-quality segmentation. Furthermore, we adopt a highly light-weight MLP-Mixer layer within the segmentation network that can efficiently propagate the query pose throughout the region of interest with minimal overhead. For the evaluation, we collect a new benchmark called KineMask which includes various appearances and actions. The experimental results demonstrate that our method has superior fine-grained segmentation performance. Moreover, it runs at 33 fps, achieving a great balance of speed and accuracy compared to the prevailing online Video Instance Segmentation methods.

关键词： computer vision conferences Computational modeling Pipelines Benchmark testing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

SqueezeNeRF: Further factorized FastNeRF for memory-efficient inference

SqueezeNeRF: Further factorized FastNeRF for memory-efficien...

引用

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

作者： Wadhwani, Krishna Kojima, Tamaki Sony Grp Corp Nihonbashi Tokyo Japan

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Neural Radiance Fields (NeRF) has emerged as the state-of-the-art method for novel view generation of complex scenes, but is very slow during inference. Recently, there have been multiple works on speeding up NeRF inference, but the state of the art methods for real-time NeRF inference rely on caching the neural network output, which occupies several giga-bytes of disk space that limits their real-world applicability. As caching the neural network of original NeRF network is not feasible, Garbin et al. proposed "FastNeRF" which factorizes the problem into 2 subnetworks - one which depends only on the 3D coordinate of a sample point and one which depends only on the 2D camera viewing direction. Although this factorization enables them to reduce the cache size and perform inference at over 200 frames per second, the memory overhead is still substantial. In this work, we propose SqueezeNeRF, which is more than 60 times memory-efficient than the sparse cache of FastNeRF and is still able to render at more than 190 frames per second on a high spec GPU during inference.

关键词： computer vision Three-dimensional displays conferences Neural networks Graphics processing units Cameras Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Linear Combination Approximation of Feature for Channel Pruning

Linear Combination Approximation of Feature for Channel Prun...

引用

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

作者： Joo, Donggyu Kim, Doyeon Yi, Eojindl Kim, Junmo Korea Adv Inst Sci & Technol KAIST Daejeon South Korea

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Network pruning is an effective method that reduces the computation of neural networks while maintaining high performance. This enables the operation of deep neural networks in resource-limited environments. In a general large network, the roles of each channel often inevitably overlap with those of others. Therefore, for more effective pruning, it is important to observe the correlation between features in the network. In this paper, we propose a novel channel pruning method, namely, the linear combination approximation of features (LCAF). We approximate each feature map by a linear combination of other feature maps in the same layer, and then remove the most approximated one. Additionally, by exploiting the linearity of the convolution operation, we propose a supporting method called weight modification, to further reduce the loss change that occurs during pruning. Extensive experiments show that LCAF achieves state-of-the-art performance in several benchmarks. Furthermore, ablations on the LCAF demonstrate the effectiveness of our approach in a variety of ways.

关键词： Deep learning computer vision Correlation Convolution conferences Neural networks Linearity

来源：评论

学校读者我要写书评

暂无评论

On Improving Cross-dataset Generalization of Deepfake Detectors

On Improving Cross-dataset Generalization of Deepfake Detect...

引用

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

作者： Nadimpalli, Aakash Varma Rattani, Ajita Wichita State Univ Sch Comp Wichita KS 67260 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Facial manipulation by deep fake has caused major security risks and raised severe societal concerns. As a countermeasure, a number of deep fake detection methods have been proposed recently. Most of them model deep fake detection as a binary classification problem using a backbone convolutional neural network (CNN) architecture pretrained for the task. These CNN-based methods have demonstrated very high efficacy in deep fake detection with the Area under the Curve (AUC) as high as 0.99. However, the performance of these methods degrades significantly when evaluated across datasets. In this paper, we formulate deep fake detection as a hybrid combination of supervised and reinforcement learning (RL) to improve its cross-dataset generalization performance. The proposed method chooses the top-k augmentations for each test sample by an RL agent in an image-specific manner. The classification scores, obtained using CNN, of all the augmentations of each test image are averaged together for final real or fake classification. Through extensive experimental validation, we demonstrate the superiority of our method over existing published research in cross-dataset generalization of deep fake detectors, thus obtaining state-of-the-art performance.

关键词： Deepfakes computer vision conferences Detectors Reinforcement learning computer architecture pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Supervised Prototype Alignment for Pedestrian Detection on Fisheye Images

Few-Shot Supervised Prototype Alignment for Pedestrian Detec...

引用

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

作者： Wiedemer, Thaddaeus Wolf, Stefan Schumann, Arne Ma, Kaisheng Beyerer, Juergen Tsinghua Univ Beijing Peoples R China Karlsruhe Inst Technol Karlsruhe Germany Fraunhofer IOSB Karlsruhe Germany Fraunhofer Ctr Machine Learning St Augustin Germany

ISBN: (纸本)9781665487399

Complete and pre-trained models are readily available for download for object detection and can perform well on datasets containing everyday images. Domain adaptation is used to transfer models to more specific datasets with characteristics not present in pre-training. We propose the novel adaptation setting of pedestrian detection in fisheye images, where target samples are scarce but annotated. Our setting provides interesting new challenges for adaptation due to global perspective changes and geometric distortions not found in existing adaptation tasks. To this end, we introduce loss coupling for unsupervised adversarial adaptation and boost prototype-based adaptation with ground-truth information. We additionally propose a novel supervised adaptation head for features in the bounding box regressor. Our method leads to more stable adversarial training and outperforms supervised and unsupervised baselines. Our method requires half the amount of training samples for small datasets to achieve the same performance as supervised fine-tuning.

关键词： Training Couplings Adaptation models Schedules Surveillance Prototypes computer architecture

来源：评论

学校读者我要写书评

暂无评论

Momentum Contrastive Pruning

Momentum Contrastive Pruning

引用

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

作者： Pan, Siyuan Qin, Yiming Li, Tingyao Li, Xiaoshuang Hou, Liang Shanghai Jiao Tong Univ Shanghai Peoples R China Chinese Acad Sci Inst Comp Technol Beijing Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Momentum contrast [16] (MoCo) for unsupervised visual representation learning has a close performance to supervised learning, but it sometimes possesses excess parameters. Extracting a subnetwork from an over-parameterized unsupervised network without sacrificing performance is of particular interest to accelerate inference speed. Typical pruning methods are not applicable for MoCo, because in the fine-tune stage after pruning, the slow update of the momentum encoder will undermine the pretrained encoder. In this paper, we propose a Momentum Contrastive Pruning (MCP) method, which prunes the momentum encoder instead to obtain a momentum subnet. It maintains an unpruned momentum encoder as a smooth transition scheme to alleviate the representation gap between the encoder and momentum subnet. To fulfill the sparsity requirements of the encoder, alternating direction method of multipliers [40] (ADMM) is adopted. Experiments prove that our MCP method can obtain a momentum subnet that has almost equal performance as the over-parameterized MoCo when transferred to downstream tasks, meanwhile has much less parameters and float operations per second (FLOPs).

关键词： Representation learning Visualization computer vision conferences Computational modeling Supervised learning Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

SphereGlue: Learning Keypoint Matching on High Resolution Spherical Images

SphereGlue: Learning Keypoint Matching on High Resolution Sp...

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Gava, Christiano Mukunda, Vishal Habtegebrial, Tewodros Raue, Federico Palacio, Sebastian Dengel, Andreas Dfki Germany University of Kaiserslautern-Landau Germany

ISBN: (纸本)9798350302493

Traditionally, spherical keypoint matching has been performed using greedy algorithms, such as Nearest Neighbors (NN) search. NN based algorithms often lead to erroneous or insufficient matches as they fail to leverage global keypoint neighborhood information. Inspired by a recent learned perspective matching approach [53] we introduce SphereGlue: a Graph Neural Network based feature matching for high-resolution spherical images. The proposed model naturally handles the severe distortions resulting from geometric transformations. Rigorous evaluations demonstrate the efficacy of SphereGlue in matching both learned and handcrafted keypoints, on synthetic and real high-resolution spherical images. Moreover, SphereGlue generalizes well to previously unseen real-world and synthetic scenes. Results on camera pose estimation show that SphereGlue can directly replace state-of-the-art matching algorithms, in downstream tasks. © 2023 ieee.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Learning Generalized Feature for Temporal Action Detection: Application for Natural Driving Action recognition Challenge

Learning Generalized Feature for Temporal Action Detection: ...

引用

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

作者： Chuong Nguyen Ngoc Nguyen Su Huynh Vinh Nguyen Son Nguyen CyberCore AI Morioka Iwate Japan

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

This paper reports our approach for the 2022 AI City Challenge - Naturalistic Driving Action recognition (Track 3), where the objective is to detect when and what kinds of actions that a driver performs in a long, untrimmed video. Our solution is built upon the single stage ActionFormer detector, in which temporal location and classification are predicted simultaneously for efficiency. The input feature for the detector is extracted offline using our proposed backbone, which we named "ConvNext-Video". However, due to the small size of the dataset, training the model to avoid over-fitting becomes challenging. To address this problem, we focus on training techniques that can improve the generalization of underlying features. Specifically, we utilize two methods: "learning without forgetting" and semi-weak supervised learning on the unlabeled data A2. Finally, we also add a second-stage classifier (SSC) using our ConvNeXt-Video backbone. The SSC Classifer is designed to combine information from multi-clips and multi-view cameras to improve the prediction precision. Our best result achieves 29.1 F1 score on the public test set. Our source code is released at link.

关键词： Training conferences Urban areas Supervised learning Detectors Feature extraction pattern recognition

来源：评论

学校读者我要写书评

暂无评论

SpiderNet: Hybrid Differentiable-Evolutionary Architecture Search via Train-Free Metrics

SpiderNet: Hybrid Differentiable-Evolutionary Architecture S...

引用

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

作者： Geada, Rob McGough, Andrew Stephen Red Hat Newcastle Upon Tyne Tyne & Wear England Newcastle Univ Newcastle Upon Tyne Tyne & Wear England

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Neural Architecture Search (NAS) algorithms are intended to remove the burden of manual neural network design, and have shown to be capable of designing excellent models for a variety of well-known problems. However, these algorithms require a variety of design parameters in the form of user configuration or hard-coded decisions which limit the variety of networks that can be discovered. This means that NAS algorithms do not eliminate model design tuning, they instead merely shift the burden of where that tuning needs to be applied. In this paper, we present SpiderNet, a hybrid differentiable-evolutionary and hardware-aware algorithm that rapidly and efficiently produces state-of-the-art networks. More importantly, SpiderNet is a proof-of-concept of a minimally-configured NAS algorithm;the majority of design choices seen in other algorithms are incorporated into SpiderNet's dynamically-evolving search space, minimizing the number of user choices to just two: reduction cell count and initial channel count. SpiderNet produces models highly-competitive with the state-of-the-art, and outperforms random search in accuracy, runtime, memory size, and parameter count.

关键词： Measurement Runtime Heuristic algorithms Microprocessors Neural networks computer architecture Manuals

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332页 << < 28 29 30 31 32 33 34 35 36 37 > >>

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：