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

4,653 篇 会议
2 篇 期刊文献

馆藏范围

4,655 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,715 篇 工学
- 1,623 篇 计算机科学与技术...
- 182 篇 软件工程
- 142 篇 机械工程
- 133 篇 光学工程
- 41 篇 生物工程
- 29 篇 信息与通信工程
- 18 篇 电气工程
- 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 控制科学与工程
- 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
173 篇 理学
- 135 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
- 2 篇 大气科学
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
10 篇 医学
- 10 篇 临床医学
5 篇 法学
- 3 篇 社会学
- 2 篇 法学
3 篇 教育学
- 3 篇 教育学
2 篇 农学
1 篇 经济学

主题

2,867 篇 computer vision
1,227 篇 training
1,038 篇 pattern recognit...
870 篇 computational mo...
794 篇 conferences
693 篇 visualization
593 篇 three-dimensiona...
469 篇 codes
460 篇 benchmark testin...
422 篇 semantics
420 篇 computer archite...
349 篇 accuracy
301 篇 adaptation model...
282 篇 feature extracti...
267 篇 transformers
242 篇 cameras
225 篇 diffusion models
223 篇 solid modeling
214 篇 pipelines
210 篇 measurement

机构

72 篇 tsinghua univers...
69 篇 zhejiang univers...
58 篇 university of sc...
57 篇 shanghai jiao to...
52 篇 google research
47 篇 nanyang technolo...
44 篇 national univers...
40 篇 shanghai ai labo...
39 篇 university of ch...
37 篇 adobe research
37 篇 the university o...
37 篇 the chinese univ...
35 篇 stanford univers...
34 篇 harbin institute...
34 篇 shanghai artific...
34 篇 carnegie mellon ...
33 篇 university of el...
30 篇 peng cheng labor...
30 篇 sun yat-sen univ...
29 篇 s-lab nanyang te...

作者

75 篇 timofte radu
24 篇 yu qiao
22 篇 luc van gool
19 篇 ying shan
16 篇 van gool luc
15 篇 radu timofte
14 篇 xin li
13 篇 li xin
12 篇 chen chen
12 篇 zhang zhao
12 篇 boxin shi
11 篇 lizhuang ma
11 篇 fan haoqiang
11 篇 loy chen change
11 篇 zheng-jun zha
11 篇 liu shuaicheng
11 篇 kai zhang
11 篇 marcos v. conde
11 篇 chen wei-ting
11 篇 ziwei liu

语言

4,654 篇 英文
1 篇 中文

检索条件"任意字段=2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024"

共 4655 条记录，以下是701-710 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：

Unpaired Real-World Super-Resolution with Pseudo Controllable Restoration

Unpaired Real-World Super-Resolution with Pseudo Controllabl...

引用

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

作者： Romero, Andres Van Gool, Luc Timofte, Radu Swiss Fed Inst Technol Comp Vis Lab Zurich Switzerland Katholieke Univ Leuven Leuven Belgium Univ Wurzburg Wurzburg Germany

ISBN: (纸本)9781665487399

Current super-resolution methods rely on the bicubic down-sampling assumption in order to develop the ill-posed reconstruction of the low-resolution image. Not surprisingly, these approaches fail when using real-world low-resolution images due to the presence of artifacts and intrinsic noise absent in the bicubic setup. Consequently, attention is increasingly paid to techniques that alleviate this problem and super-resolve real-world images. As acquiring paired real-world datasets is a challenging problem, real-world super-resolution solutions are traditionally tackled as a blind problem or as an unpaired data-driven problem. The former makes assumptions about the down-sampling operations, the latter uses unpaired training to learn the real distributions. Recently, blind approaches have dominated this problem by assuming a diverse bank of degradations, whereas the unpaired solutions have shown under-performance due to the two-staged training. In this paper, we propose an unpaired real-world super-resolution method that performs on par, or even better than blind paired approaches by introducing a pseudo-controllable restoration module in a fully end-to-end system.

关键词： Training Degradation computer vision conferences Superresolution Image restoration pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Video Action Detection: Analysing Limitations and Challenges

Video Action Detection: Analysing Limitations and Challenges

引用

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

作者： Modi, Rajat Rana, Aayush Jung Kumar, Akash Tirupattur, Praveen Vyas, Shruti Rawat, Yogesh Singh Shah, Mubarak Univ Cent Florida Ctr Res Comp Vis Orlando FL 32816 USA

ISBN: (纸本)9781665487399

Beyond possessing large enough size to feed data hungry machines (eg, transformers), what attributes measure the quality of a dataset? Assuming that the definitions of such attributes do exist, how do we quantify among their relative existences? Our work attempts to explore these questions for video action detection. The task aims to spatio-temporally localize an actor and assign a relevant action class. We first analyze the existing datasets on video action detection and discuss their limitations. Next, we propose a new dataset, Multi Actor Multi Action (MAMA) which overcomes these limitations and is more suitable for real world applications. In addition, we perform a biasness study which analyzes a key property differentiating videos from static images: the temporal aspect. This reveals if the actions in these datasets really need the motion information of an actor, or whether they predict the occurrence of an action even by looking at a single frame. Finally, we investigate the widely held assumptions on the importance of temporal ordering: is temporal ordering important for detecting these actions? Such extreme experiments show existence of biases which have managed to creep into existing methods inspite of careful modeling.

关键词： pattern recognition conferences computer vision

来源：评论

学校读者我要写书评

暂无评论

PEA: Improving the Performance of ReLU Networks for Free by Using Progressive Ensemble Activations

PEA: Improving the Performance of ReLU Networks for Free by ...

引用

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

作者： Utasi, Akos Continental AI Dev Ctr Budapest Hungary

ISBN: (纸本)9781665487399

In recent years novel activation functions have been proposed to improve the performance of neural networks, and they show superior performance compared to the ReLU counterpart. However, there are environments, where the availability of complex activations is limited, and usually only the ReLU is supported. In this paper we propose methods that can be used to improve the performance of ReLU networks by using these efficient novel activations during model training. More specifically, we propose ensemble activations that are composed of the ReLU and one of these novel activations. Furthermore, the coefficients of the ensemble are neither fixed nor learned, but are progressively updated during the training process in a way that by the end of the training only the ReLU activations remain active in the network and the other activations can be removed. This means that in inference time the network contains ReLU activations only. We perform extensive evaluations on the ImageNet classification task using various compact network architectures and various novel activation functions. Results show 0.2-0.8% top-1 accuracy gain, which confirms the applicability of the proposed methods. Furthermore, we demonstrate the proposed methods on semantic segmentation and we boost the performance of a compact segmentation network by 0.34% mIOU on the Cityscapes dataset.

关键词： Training Image segmentation computer vision conferences Semantics Neural networks Network architecture

来源：评论

学校读者我要写书评

暂无评论

Analysis and Extensions of Adversarial Training for Video Classification

Analysis and Extensions of Adversarial Training for Video Cl...

引用

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

作者： Kinfu, Kaleab A. Vidal, Rene Johns Hopkins Univ Math Inst Data Sci Baltimore MD 21218 USA

ISBN: (纸本)9781665487399

Adversarial training (AT) is a simple yet effective defense against adversarial attacks to image classification systems, which is based on augmenting the training set with attacks that maximize the loss. However, the effectiveness of AT as a defense for video classification has not been thoroughly studied. Our first contribution is to show that generating optimal attacks for video requires carefully tuning the attack parameters, especially the step size. Notably, we show that the optimal step size varies linearly with the attack budget. Our second contribution is to show that using a smaller (sub-optimal) attack budget at training time leads to a more robust performance at test time. Based on these findings, we propose three defenses against attacks with variable attack budgets. The first one, Adaptive AT, is a technique where the attack budget is drawn from a distribution that is adapted as training iterations proceed. The second, Curriculum AT, is a technique where the attack budget is increased as training iterations proceed. The third, Generative AT, further couples AT with a denoising generative adversarial network to boost robust performance. Experiments on the UCF101 dataset demonstrate that the proposed methods improve adversarial robustness against multiple attack types.

关键词： Training computer vision conferences Noise reduction Generative adversarial networks Robustness pattern recognition

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

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

Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network

Towards Scalable 3D Anomaly Detection and Localization: A Be...

引用

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

作者： Li, Wenqiao Xu, Xiaohao Gu, Yao Zheng, Bozhong Gao, Shenghua Wu, Yingna ShanghaiTech Univ Shanghai Peoples R China Univ Michigan Ann Arbor MI USA

ISBN: (纸本)9798350353006

Recently, 3D anomaly detection, a crucial problem involving fine-grained geometry discrimination, is getting more attention. However, the lack of abundant real 3D anomaly data limits the scalability of current models. To enable scalable anomaly data collection, we propose a 3D anomaly synthesis pipeline to adapt existing large-scale 3D models for 3D anomaly detection. Specifically, we construct a synthetic dataset, i.e., Anomaly-ShapeNet, based on ShapeNet. Anomaly-ShapeNet consists of 1600 point cloud samples under 40 categories, which provides a rich and varied collection of data, enabling efficient training and enhancing adaptability to industrial scenarios. Meanwhile, to enable scalable representation learning for 3D anomaly localization, we propose a self-supervised method, i.e., Iterative Mask Reconstruction Network (IMRNet). During training, we propose a geometry-aware sample module to preserve potentially anomalous local regions during point cloud down-sampling. Then, we randomly mask out point patches and sent the visible patches to a transformer for reconstruction-based self-supervision. During testing, the point cloud repeatedly goes through the Mask Reconstruction Network, with each iteration's output becoming the next input. By merging and contrasting the final reconstructed point cloud with the initial input, our method successfully locates anomalies. Experiments show that IMRNet outperforms previous state-of-the-art methods, achieving 66.1% in I-AUC on our Anomaly-ShapeNet dataset and 72.5% in I-AUC on Real3D-AD dataset. Our benchmark will be released at https://***/Chopper-233/Anomaly-ShapeNet.

关键词： Anomaly Detection 3D vision Self-Supervised

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

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

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466页 << < 67 68 69 70 71 72 73 74 75 76 > >>

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：