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 labels on the most recently released FreiHAND competition at the submission date. The source code and models are available 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

Context-Sensitive Human Activity Classification in Collaborative Learning Environments

Context-Sensitive Human Activity Classification in Collabora...

引用

IEEE Southwest Symposium on image Analysis and Interpretation

作者： Abigail Ruth Jacoby Marios S. Pattichis Sylvia Celedón-Pattichis Carlos LópezLeiva image and video Processing and Communications Lab (ivpcl.unm.edu) University of New Mexico United States Dept. of Language Literacy and Sociocultural Studies University of New Mexico United States

Human activity classification remains challenging due to the strong need to eliminate structural noise, the multitude of possible activities, and the strong variations in video acquisition. The current paper explores the study of human activity classification in a collaborative learning *** paper explores the use of color based object detection in conjunction with contextualization of object interaction to isolate motion vectors specific to each human activity. The basic approach is to make use of separate classifiers for each activity. Here, we consider the detection of typing, writing, and talking activities in raw *** method was tested using 43 uncropped video clips with 620 video frames for writing, 1050 for typing, and 1755 frames for talking. Using simple KNN classifiers, the method gave accuracies of 72.6% for writing, 71% for typing and 84.6% for talking. Classification accuracy improved to 92.5% (writing), 82.5% (typing) and 99.7% (talking) with the use of Deep Neural Networks.

关键词： Writing keyboards Feature extraction image color analysis Neural networks Collaborative work Monitoring

来源：评论

学校读者我要写书评

暂无评论

Selection of Cancer Biomarkers from Microarray Gene Expression Data Utilizing the Bi-Objective Optimization Method

Selection of Cancer Biomarkers from Microarray Gene Expressi...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Jiang, Hanjing Lin, Jianqing Zhu, Huachao Huang, Yabing Huazhong University of Science and Technology Key Lab. of Image Information Processing and Intelligent Control of Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Wuhan430074 China Wuhan University School of Computer Science Wuhan430064 China Renmin Hospital of Wuhan University Department of Pathology Wuhan430060 China

ISBN: (纸本)9798350337488

Cancer-associated biomarker genes play an indispensable role in the intricate tapestry of cancer development and manifestation. The expression of biomarkers in different types of tumor cells has beneficial implications for shedding light on the development of various cancers, guiding clinical diagnosis, and treatment. Microarray technology enables the expression levels of thousands of genes in samples to be sequenced simultaneously. However, sparse and high-dimensional microarray data present a formidable challenge in identifying biomarker genes. This study presents EREF-NSGA2, a novel method for cancer biomarker selection from microarray data, employing a hybrid gene selection approach. Firstly, the combination of the wrapper and embedded gene selection methods is proposed to filter the microarray data, which efficiently decreases the search space of the algorithm. After that, the improved NSGA-II algorithm is used to search the genes subset obtained from the previous step to reach the optimal subset of cancer biomarker genes. The proposed EREF-NSGA2 is compared with other reported methods on six cancer benchmark gene expression datasets. A detailed biological analysis is performed to analyze the relationship between the selected genes and the cancer data sets they belong to. To summarize, EREF-NSGA2 proves its effectiveness in selecting a feature subset comprising the fewest genes while maintaining the highest classification accuracy. © 2023 IEEE.

关键词： Bi-objective optimization Cancer biomarker Gene selection NSGA-II

来源：评论

学校读者我要写书评

暂无评论

Robust Head Detection in Collaborative Learning Environments Using AM-FM Representations

Robust Head Detection in Collaborative Learning Environments...

引用

IEEE Southwest Symposium on image Analysis and Interpretation

作者： Wenjing Shi Marios S. Pattichis Sylvia Celedón-Pattichis Carlos LópezLeiva image and video Processing and Communications Lab (ivpcl.unm.edu) University of New Mexico United States Dept. of Language Literacy and Sociocultural Studies University of New Mexico United States

The paper introduces the problem of robust head detection in collaborative learning environments. In such environments, the camera remains fixed while the students are allowed to sit at different parts of a table. Example challenges include the fact that students may be facing away from the camera or exposing different parts of their face to the camera. To address these issues, the paper proposes the development of two new methods based on Amplitude Modulation-Frequency Modulation (AM-FM) models. First, a combined approach based on color and FM texture is developed for robust face detection. Secondly, a combined approach based on processing the AM and FM components is developed for robust, back of the head detection. The results of the two approaches are also combined to detect all of the students sitting at each table. The robust face detector achieved 79% accuracy on a set of 1000 face image examples. The back of the head detector achieved 91% accuracy on a set of 363 test image examples.

关键词： Hair Frequency modulation Face Detectors Robustness image color analysis

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

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

A Multiple Attributes image Quality Database for Smartphone Camera Photo Quality Assessment

A Multiple Attributes Image Quality Database for Smartphone ...

引用

IEEE International Conference on image processing

作者： Wenhan Zhu Guangtao Zhai Zongxi Han Xiongkuo Min Tao Wang Zicheng Zhang Xiaokang Yangand MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Institute of Image Communication and Information Processing Shanghai Jiao Tong University China

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

Smartphone is the superstar product in digital device market and the quality of smartphone camera photos (SCPs) is becoming one of the dominant considerations when consumers purchase smartphones. How to evaluate the quality of smartphone cameras and the taken photos is urgent issue to be solved. To bridge the gap between academic research accomplishment and industrial needs, in this paper, we establish a new Smartphone Camera Photo Quality Database (SCPQD2020) including 1800 images with 120 scenes taken by 15 smartphones. Exposure, color, noise and texture which are four dominant factors influencing the quality of SCP are evaluated in the subjective study, respectively. Ten popular no-reference (NR) image quality assessment (IQA) algorithms are tested and analyzed on our database. Experimental results demonstrate that the current objective models are not suitable for SCPs, and quality metrics having high correlation with human visual perception are highly needed.

关键词： Cameras image color analysis Databases Colored noise Measurement Quality assessment image quality

来源：评论

学校读者我要写书评

暂无评论

Evolutionary neural architecture search for retinal vessel segmentation

arXiv

引用

arXiv 2020年

作者： Fan, Zhun Wei, Jiahong Zhu, Guijie Mo, Jiajie Li, Wenji Department of Electronic and Information Engineering Shantou University Shantou515063 China Key Lab of Digital Signal and Image Processing of Guangdong Province Shantou University Shantou515063 China

The accurate retinal vessel segmentation (RVS) is of great significance to assist doctors in the diagnosis of ophthalmology diseases and other systemic diseases. Manually designing a valid neural network architecture for retinal vessel segmentation requires high expertise and a large workload. In order to improve the performance of vessel segmentation and reduce the workload of manually designing neural network, we propose novel approach which applies neural architecture search (NAS) to optimize an encoder-decoder architecture for retinal vessel segmentation. A modified evolutionary algorithm is used to evolve the architectures of encoder-decoder framework with limited computing resources. The evolved model obtained by the proposed approach achieves top performance among all compared methods on the three datasets, namely DRIVE, STARE and CHASE_DB1, but with much fewer parameters. Moreover, the results of cross-training show that the evolved model is with considerable scalability, which indicates a great potential for clinical disease diagnosis. Copyright © 2020, The Authors. All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

A multiple attributes image quality database for smartphone camera photo quality assessment

arXiv

引用

arXiv 2020年

作者： Zhu, Wenhan Zhai, Guangtao Han, Zongxi Min, Xiongkuo Wang, Tao Zhang, Zicheng Yang, Xiaokang MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Institute of Image Communication and Information Processing Shanghai Jiao Tong University China

关键词： Database systems

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：