检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Li, Moran Gao, Yuan Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Tencent AI Lab United States

In this paper, we propose to estimate 3D hand pose by recovering the 3D coordinates of joints in a group-wise manner, where less-related joints are automatically categorized into different groups and exhibit different features. This is different from the previous methods where all the joints are considered holistically and share the same feature. The benefits of our method are illustrated by the principle of multi-task learning (MTL), i.e., by separating less-related joints into different groups (as different tasks), our method learns different features for each of them, therefore efficiently avoids the negative transfer (among less related tasks/groups of joints). The key of our method is a novel binary selector that automatically selects related joints into the same group. We implement such a selector with binary values stochastically sampled from a Concrete distribution, which is constructed using Gumbel softmax on trainable parameters. This enables us to preserve the differentiable property of the whole network. We further exploit features from those less-related groups by carrying out an additional feature fusing scheme among them, to learn more discriminative features. This is realized by implementing multiple 1x1 convolutions on the concatenated features, where each joint group contains a unique 1x1 convolution for feature fusion. The detailed ablation analysis and the extensive experiments on several benchmark datasets demonstrate the promising performance of the proposed method over the state-of-the-art (SOTA) methods. Besides, our method achieves top-1 among all the methods that do not exploit the dense 3D shape lab.ls on the most recently released FreiHAND competition at the submission date. The source code and models are availab.e at https://***/moranli-aca/LearnableGroups-Hand. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Selective Bokeh Effect Transformation

Selective Bokeh Effect Transformation

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Juewen Peng Zhiyu Pan Chengxin Liu Xianrui Luo Huiqiang Sun Liao Shen Ke Xian Zhiguo Cao Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology S-Lab Nanyang Technological University

Bokeh effect transformation is a novel task in computer vision and computational photography. It aims to convert bokeh effects from one camera lens to another. To this end, we introduce a new concept of blur ratio, which represents the ratio of the blur amount of a target image to that of a source image, and propose a novel framework SBTNet based on this concept. For cat-eye simulation and lens type transformation, a two-channel coordinate map and a two-channel one-hot map are added as extra inputs. The core of the framework is a sequence of parallel FeaNets, along with a feature selection and integration strategy, which aims to transform the blur amount with arbitrary blur ratio. The effectiveness of the proposed framework is demonstrated through extensive experiments, and our solution has achieved the top LPIPS metric in NTIRE 2023 Bokeh Effect Transformation Challenge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A fractal image coding method combined with compressed sensing algorithm

Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu

引用

Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu 2016年第4期 78-83页

作者： Guo, Hui He, Jie Hu, Defa Jiang, Weijin Guangxi Colleges and Universities Key Lab. of Image Processing and Intelligent Information System Wuzhou University Wuzhou Guangxi China School of Computer and Information Engineering Hunan University of Commerce Changsha Hunan China

Purpose. Since fractal image coding is time-consuming and is prone to causing "blocking artifact", the article aims to combine fractal image coding, wavelet transform and compressed sensing to put forward a method which can shorten the coding time effectively and improve the quality of a reconstructed image. Methodology. The compressed sensing algorithm can quickly compress and highly restore sparse matrixes. The paper made use of this feature to conduct fractal coding for a low-frequency sub-image after wavelet transform, followed by recoding the samples of low-frequency differential sub-graphs and high-frequency sub-images by means of the compressed sensing algorithm for the purpose of compensating the quality of reconstructed images. Findings. Compared to the traditional fractal coding method, the algorithm in the paper (hereinafter referred to as "this Algorithm") can shorten the time considerably and get a maximum speed-up ratio by up to 6.45 times. Compared to the compressed sensing coding method, the quality of the reconstructed images is improved significantly. Originality. The innovation of the paper lies in applying the compressed sensing theory to the fractal coding algorithm to compensate the quality of the reconstructed images obtained by means of fractal coding based on wavelet transform. Practical value. This Algorithm can shorten the coding time on the basis of ensuring the quality of a reconstructed image, and has certain significance for promoting the fractal coding method. © Hui Guo, Jie He, Defa Hu, Weijin Jiang, 2016.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A Combining Method for Tumors Detection from Near-infrared Breast Imaging

A Combining Method for Tumors Detection from Near-infrared B...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Zhicheng Wang Jian Liu Jinwen Tian Zeping Xie State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong Univ. of Sci. & Tech. Wuhan 430074 China Key Lab. for Image Process. & Intelligent Control State Educ. Comm. School of Life Science & Technology Huazhong University of Science and Technology Wuhan China

This paper introduces the new qualitative and quantitative methods, which can diagnose breast tumors. Qualitative methods include blood vessel display inside and outside of pathological changes part of breast, display of equivalent pixel curves at the part of pathological changes and display of breast tumor image edge. Accordingly, three feature extraction operators are proposed, i.e. the combination operators of anisotropic gradient and smoothing operator, an improved Sobel operator and an edge sharpening operator. Furthermore, quantitative diagnostic approaches are discussed based on blood and oxygen contents according to abundant clinical data and pathological mechanism of breast tumors. The results of clinic show that the methods of combining qualitative and quantitative diagnose are effective for breast tumor images, especially for early and potential breast cancer

关键词： Breast tumors Displays Pathology Blood vessels Biomedical imaging Pixel Feature extraction Anisotropic magnetoresistance Smoothing methods Breast cancer

来源：评论

学校读者我要写书评

暂无评论

Multi-homed VPN architecture based on extended SOCKS+TLS protocols

引用

Journal of Shanghai Jiaotong University (Science) 2005年第3期10 E卷 250-255页

作者： Zhang, Bao-Liang Hu, Han-Ping Chen, Xiang State Education Ministry Key Lab. of Image Information and Intelligent Control Inst. of Pattern Recognition and Artificial Intelligence Huazhong Univ. of Science and Technology Wuhan 430074 China

A multi-homed VPN architecture based on extended SOCKSv5 and TLS was proposed. The architecture employs a dynamic connection mechanism for multiple proxies in the end system, in which the security-demanded transmission connections can switch smoothly among the multiple proxies by maintaining a coherent connection context. The mechanism is transparent to application programs and can support the building of VPN. With the cooperation of some other security components, the mechanism guarantees the resource availab.lity and reliability of the end system against some attacks to the specific ports or hosts.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Weakly-supervised temporal action localization through local-global background modeling

arXiv

引用

arXiv 2021年

作者： Wang, Xiang Qing, Zhiwu Huang, Ziyuan Feng, Yutong Zhang, Shiwei Jiang, Jianwen Tang, Mingqian Shao, Yuanjie Sang, Nong Key Lab. of Image Proc. and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China

Weakly-Supervised Temporal Action Localization (WSTAL) task aims to recognize and localize temporal starts and ends of action instances in an untrimmed video with only video-level lab.l supervision. Due to lack of negative samples of background category, it is difficult for the network to separate foreground and background, resulting in poor detection performance. In this report, we present our 2021 HACS Challenge-Weakly-supervised Learning Track [24] solution that based on BaSNet [10] to address above problem. Specifically, we first adopt pre-trained CSN [17], Slowfast [5], TDN [19], and ViViT [1] as feature extractors to get feature sequences. Then our proposed Local-Global Background Modeling Network (LGBM-Net) is trained to localize instances by using only video-level lab.ls based on Multi-Instance Learning (MIL). Finally, we ensemble multiple models to get the final detection results and reach 22.45% mAP on the test set. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

AN IKONOS image FUSION PROCESS USING SUPPORT VALUE TRANSFORM

AN IKONOS IMAGE FUSION PROCESS USING SUPPORT VALUE TRANSFORM

引用

2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

作者： SHENG ZHENG WENZHONG SHI JIAN LIU Institute of Intelligent Vision and Image Information Best College of Electrical Engineering and In Advanced Research Center for Spatial Information Technology Department of Land Surveying and Geo-In State Education Commission Key Lab for Image Processing and Intelligent Control HUST Wuhan 430074

Panchromatic (Pan)-sharpening of multispectral (MS) bands is an important technique in various applications of satellite remote *** this paper, we apply the support value transform (SVT) to Ikonos image *** fused saliency features are represented by support values and extracted by *** low-resolution MS bands are resampled to the fine scale of the Pan image and sharpened by injecting the detailed features extracted from the high-resolution Pan *** fusing results on Ikonos MS + Pan data demonstrate that the proposed image fusion method is effective and efficient.

关键词： Mapped least squares support vector machine (mapped LS-SVM) support value transform (SVT) Ikonos image fusion

来源：评论

学校读者我要写书评

暂无评论

Multifeature distance map based detection of small infrared targets with low contrast in image sequences

Multifeature distance map based detection of small infrared ...

引用

International Conference on Space Information Technology

作者： Wang, Zhicheng Gao, Chenqiang Tian, Jinwen Liu, Jian Chen, Xiangping State Education Commission Key Lab for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan Hubei 430074 China Inst. for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan Hubei 430074 China Electronic and Engineering Department Huazhong University of Science and Technology Wuhan Hubei 430074 China

Target detection techniques play an important role in automatic target recognition (ATR) systems because overall ATR performance depends closely on detection results. In this paper, a novel method for fusion detection of infrared weak targets based on multifeature distance map (MFDM) in image sequences is proposed. As for small weak targets, there are many features, such as local entropy, average gradient strength. These features depict the characteristics of small infrared targets and can be extracted. Multifeature-based fusion techniques are applied to detect such weak targets. The problem of detecting small targets is converted to search peak values in specified feature space where multifeature vectors space (MFVS) is considered. Distance map (DM) can be derived according to feature vectors and target detection is performed in DM. In order to accumulate energy of targets deeply and suppress background and clutters to a great extent, five distance maps obtained by corresponding five consecutive frames are utilized to fuse with average weight, which results in the fact that the contrast between targets and background including clutters are enlarged and that the feature peaks of targets are obvious different from background and clutters. After these steps, a contrast segmentation method is used to extract targets from complicated background on the fused DM. Actual infrared image sequences in background of sea and sky are applied to validate the proposed approach. Experimental results demonstrate the robustness of the proposed method with high performance.

关键词： Automatic target recognition

来源：评论

学校读者我要写书评

暂无评论

An Ikonos image fusion process using support value transform

An Ikonos image fusion process using support value transform

引用

6th International Conference on Machine Learning and Cybernetics

作者： Zheng, Sheng Shi, Wenzhong Liu, Jian China Three Gorges Univ Inst Intelligent Vis & Image Informat Best Coll Elect Engn & Informat Technol Yichang 443002 Peoples R China Huazhong Univ Sci & Technol Elect & Informat Engn Dept Wuhan 430074 Peoples R China Hong Kong Polytech Univ Adv Res Ctr Spatial Informat Technol Dept Land Surveying & Geo Informat Hong Kong Peoples R China Huazhong Univ Sci & Technol State Educ Commiss Key Lab Image Processing & Intelligent Control Wuhan 430074 Peoples R China

ISBN: (纸本)9781424409723

Panchromatic (Pan)-sharpening of multispectral (MS) bands is an important technique in various applications of satellite remote sensing. In this paper, We apply the support value transform (SVT) to Ikonos image fusion. The fused saliency features are represented by support values and extracted by SVT. The low-resolution MS bands are resampled to the fine scale of the Pan image and sharpened by injecting the detailed features extracted from the high-resolution Pan image. The fusing results on Ikonos MS + Pan data demonstrate that the proposed image fusion method is effective and efficient.

关键词： mapped least squares support vector machine (mapped LS-SVM) support value transform (SVT) Ikonos image fusion

来源：评论

学校读者我要写书评

暂无评论

Do not disturb me: Person re-identification under the interference of other pedestrians

arXiv

引用

arXiv 2020年

作者： Zhao, Shizhen Gao, Changxin Zhang, Jun Cheng, Hao Han, Chuchu Jiang, Xinyang Guo, Xiaowei Zheng, Wei-Shi Sang, Nong Sun, Xing Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Tencent Youtu Lab Sun Yat-sen University China

In the conventional person Re-ID setting, it is widely assumed that cropped person images are for each individual. However, in a crowded scene, off-shelf-detectors may generate bounding boxes involving multiple people, where the large proportion of background pedestrians or human occlusion exists. The representation extracted from such cropped images, which contain both the target and the interference pedestrians, might include distractive information. This will lead to wrong retrieval results. To address this problem, this paper presents a novel deep network termed Pedestrian-Interference Suppression Network (PISNet). PISNet leverages a Query-Guided Attention Block (QGAB) to enhance the feature of the target in the gallery, under the guidance of the query. Furthermore, the involving Guidance Reversed Attention Module and the Multi-Person Separation Loss promote QGAB to suppress the interference of other pedestrians. Our method is evaluated on two new pedestrian-interference datasets and the results show that the proposed method performs favorably against existing Re-ID methods. Our project is availab.e at https://***/X-Brainlab.PI-ReID. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：