检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhu, Xiangyu Yu, Chang Huang, Di Lei, Zhen Wang, Hao Li, Stan Z. Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences 95 Zhongguancun Donglu Beijing100190 China Beijing100049 China Beijing Advanced Innovation Center for BDBC Beihang University Beijing China Beijing100049 China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong School of Engineering Westlake University Hangzhou China

3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori. However, previous reconstructed 3D faces suffer from degraded visual verisimilitude due to the loss of fine-grained geometry, which is attributed to insufficient ground-truth 3D shapes, unreliable training strategies and limited representation power of 3DMM. To alleviate this issue, this paper proposes a complete solution to capture the personalized shape so that the reconstructed shape looks identical to the corresponding person. Specifically, given a 2D image as the input, we virtually render the image in several calibrated views to normalize pose variations while preserving the original image geometry. A many-to-one hourglass network serves as the encode-decoder to fuse multiview features and generate vertex displacements as the fine-grained geometry. Besides, the neural network is trained by directly optimizing the visual effect, where two 3D shapes are compared by measuring the similarity between the multiview images rendered from the shapes. Finally, we propose to generate the ground-truth 3D shapes by registering RGB-D images followed by pose and shape augmentation, providing sufficient data for network training. Experiments on several challenging protocols demonstrate the superior reconstruction accuracy of our proposal on the face shape. Copyright © 2022, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

SADet: Learning an efficient and accurate pedestrian detector

arXiv

引用

arXiv 2020年

作者： Zhuang, Chubin Lei, Zhen Li, Stan Z. Center for Biometrics and Security Research and National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Although the anchor-based detectors have taken a big step forward in pedestrian detection, the overall performance of algorithm still needs further improvement for practical applications, e.g., a good trade-off between the accuracy and efficiency. To this end, this paper proposes a series of systematic optimization strategies for the detection pipeline of one-stage detector, forming a single shot anchor-based detector (SADet) for efficient and accurate pedestrian detection, which includes three main improvements. Firstly, we optimize the sample generation process by assigning soft tags to the outlier samples to generate semi-positive samples with continuous tag value between 0 and 1, which not only produces more valid samples, but also strengthens the robustness of the model. Secondly, a novel Center-IoU loss is applied as a new regression loss for bounding box regression, which not only retains the good characteristics of IoU loss, but also solves some defects of it. Thirdly, we also design Cosine-NMS for the postprocess of predicted bounding boxes, and further propose adaptive anchor matching to enable the model to adaptively match the anchor boxes to full or visible bounding boxes according to the degree of occlusion, making the NMS and anchor matching algorithms more suitable for occluded pedestrian detection. Though structurally simple, it presents state-of-the-art result and real-time speed of 20 FPS for VGA-resolution images (640×480) on challenging pedestrian detection benchmarks, i.e., CityPersons, Caltech, and human detection benchmark CrowdHuman, leading to a new attractive pedestrian detector. Copyright © 2020, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Weakly Aligned Feature Fusion for Multi-modal Object Detection

arXiv

引用

arXiv 2022年

作者： Zhang, Lu Liu, Zhiyong Zhu, Xiangyu Song, Zhan Yang, Xu Lei, Zhen Qiao, Hong The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100086 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China The Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong The Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China

To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, depth, etc. However, multi-modal data often suffer from the position shift problem, i.e. the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multi-modal features and puzzles the CNN training. In this paper, we propose a general multi-modal detector named Aligned Region CNN (AR-CNN) to tackle the position shift problem. Firstly, a region feature alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal region features. Secondly, we propose a novel RoI jitter strategy to improve the robustness to unexpected shift patterns. Thirdly, we present a new multi-modal feature fusion method, which selects the more reliable feature and suppresses the less useful one via feature re-weighting. Additionally, by locating bounding boxes in both modalities and building their relationships, we provide novel multi-modal labelling named KAIST-Paired. Extensive experiments on 2D and 3D object detection, RGB-T and RGB-D datasets demonstrate the effectiveness and robustness of our method. Copyright © 2022, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Auxiliary Demographic Information Assisted Age Estimation With Cascaded Structure

引用

IEEE TRANSACTIONS ON CYBERNETICS 2018年第9期48卷 2531-2541页

作者： Wan, Jun Tan, Zichang Lei, Zhen Guo, Guodong Li, Stan Z. Center for Biometrics and Security Research and the National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Lane Department of Computer Science and Electrical Engineering West Virginia University Morgantown WV USA

Owing to the variations including both intrinsic and extrinsic factors, age estimation remains a challenging problem. In this paper, five cascaded structure frameworks are proposed for age estimation based on convolutional neural networks. All frameworks are learned and guided by auxiliary demographic information, since other demographic information (i.e., gender and race) is beneficial for age prediction. Each cascaded structure framework is embodied in a parent network and several subnetworks. For example, one of the applied framework is a gender classifier trained by gender information, and then two subnetworks are trained by the male and female samples, respectively. Furthermore, we use the features extracted from the cascaded structure frameworks with Gaussian process regression that can boost the performance further for age estimation. Experimental results on the MORPH II and CACD datasets have gained superior performances compared to the state-of-the-art methods. The mean absolute error is significantly reduced from 3.63 to 2.93 years under the same test protocol on the MORPH II dataset.

关键词： Age estimation convolutional neural networks (CNNs) demographic Gaussian process regression (GPR)

来源：评论

学校读者我要写书评

暂无评论

AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks

arXiv

引用

arXiv 2021年

作者： Roy, Swalpa Kumar Paoletti, Mercedes E. Haut, Juan M. Dubey, Shiv Ram Kar, Purbayan Plaza, Antonio Chaudhuri, Bidyut B. The Computer Science and Engineering Alipurduar Government Engineering and Management College 736206 India The Hyperspectral Computing Laboratory Department of Technology of Computers and Communications University of Extremadura Cáceres10003 Spain The Computer Vision and Biometrics Lab Indian Institute of Information Technology Prayagraj Uttar Pradesh Allahabad211015 India The Media Analysis Group Sony Research India Private Limited Karnataka Bangalore560103 India The Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India

Convolutional neural networks (CNNs) are trained using stochastic gradient descent (SGD)-based optimizers. Recently, the adaptive moment estimation (Adam) optimizer has become very popular due to its adaptive momentum, which tackles the dying gradient problem of SGD. Nevertheless, existing optimizers are still unable to exploit the optimization curvature information efficiently. This paper proposes a new AngularGrad optimizer that considers the behavior of the direction/angle of consecutive gradients. This is the first attempt in the literature to exploit the gradient angular information apart from its magnitude. The proposed AngularGrad generates a score to control the step size based on the gradient angular information of previous iterations. Thus, the optimization steps become smoother as a more accurate step size of immediate past gradients is captured through the angular information. Two variants of AngularGrad are developed based on the use of Tangent or Cosine functions for computing the gradient angular information. Theoretically, AngularGrad exhibits the same regret bound as Adam for convergence purposes. Nevertheless, extensive experiments conducted on benchmark data sets against state-of-the-art methods reveal a superior performance of AngularGrad. Source code: https://***/mhaut/AngularGrad. Copyright © 2021, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Domain adaptive person re-identification via camera style generation and label propagation

arXiv

引用

arXiv 2019年

作者： Ren, Chuan-Xian Liang, Bo-Hua Lei, Zhen School of Mathematics Sun Yat-Sen University Guangzhou510275 China Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190

Unsupervised domain adaptation in person reidentification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping labels challenge that source domain and target domain have entirely different persons further increases the re-identification difficulty. In this paper, we propose a novel algorithm to narrow such domain gaps. We derive a camera style adaptation framework to learn the style-based mappings between different camera views, from the target domain to the source domain, and then we can transfer the identity-based distribution from the source domain to the target domain on the camera level. To overcome the non-overlapping labels challenge and guide the person re-identification model to narrow the gap further, an efficient and effective soft-labeling method is proposed to mine the intrinsic local structure of the target domain through building the connection between GAN-translated source domain and the target domain. Experiment results conducted on real benchmark datasets indicate that our method gets state-of-the-art results. Copyright © 2019, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

DEEP BACKGROUND SUBTRACTION WITH GUIDED LEARNING

DEEP BACKGROUND SUBTRACTION WITH GUIDED LEARNING

引用

IEEE International Conference on Multimedia and Expo

作者： Xuezhi Liang Shengcai Liao Xiaobo Wang Wei Liu Yuxuan Chen Stan Z. Li University of Chinese Academy of Sciences Beijing China Center for Biometrics and Security Research & National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

Recently, convolutional neural networks (CNNs) have been applied in background subtraction (change detection) and gained notable improvements. Two typical methods have been proposed. The first one learns a specific CNN model for each video, but requires manual labeling of training frames on the fly. The other one learns a universal model offline, however, limits its performance in handling various surveillance scenarios. To address these problems, in this paper, a new deep background subtraction method is proposed by introducing a guided learning strategy. The main idea is to learn a specific CNN model for each video to ensure accuracy, but manage to avoid manual labeling. To achieve this, firstly we apply the SubSENSE algorithm [1] to get an initial segmentation, and then an adaptive strategy is designed to select reliable pixels to guide the CNN training. Besides, we also design a simple strategy to automatically select informative frames for guided learning. Experiments on the largest background subtraction benchmark CDnet2014 show that the proposed guided deep learning method outperforms existing state of the arts.

关键词： Background subtraction Change detection Deep learning

来源：评论

学校读者我要写书评

暂无评论

Large-scale bisample learning on ID versus spot face recognition

arXiv

引用

arXiv 2018年

作者： Zhu, Xiangyu Liu, Hao Lei, Zhen Shi, Hailin Yang, Fan Yi, Dong Qi, Guojun Li, Stan Z. Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences College of Software Beihang University DAMO Academy Alibaba Group HUAWEI Cloud United States

In real-world face recognition applications, there is a tremendous amount of data with two images for each person. One is an ID photo for face enrollment, and the other is a probe photo captured on spot. Most existing methods are designed for training data with limited breadth (a relatively small number of classes) and sufficient depth (many samples for each class). They would meet great challenges on ID versus Spot (IvS) data, including the under-represented intra-class variations and an excessive demand on computing devices. In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition. To tackle the bisample problem with only two samples for each class, a classification-verification-classification (CVC) training strategy is proposed to progressively enhance the IvS performance. Besides, a dominant prototype softmax (DP-softmax) is incorporated to make the deep learning scalable on large-scale classes. We conduct LBL on a IvS face dataset with more than two million identities. Experimental results show the proposed method achieves superior performance to previous ones, validating the effectiveness of LBL on IvS face recognition. Copyright © 2018, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

diffGrad: An optimization method for convolutional neural networks

arXiv

引用

arXiv 2019年

作者： Dubey, Shiv Ram Chakraborty, Soumendu Roy, Swalpa Kumar Mukherjee, Snehasis Singh, Satish Kumar Chaudhuri, Bidyut Baran The Computer Vision Group Indian Institute of Information Technology Sri City Andhra Pradesh Chittoor517646 India The Indian Institute of Information Technology Uttar Pradesh Lucknow India The Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India Techno India University Sector V Salt Lake City Kolkata700091 India The Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Allahabad211015 India

Stochastic Gradient Decent (SGD) is one of the core techniques behind the success of deep neural networks. The gradient provides information on the direction in which a function has the steepest rate of change. The main problem with basic SGD is to change by equal sized steps for all parameters, irrespective of gradient behavior. Hence, an efficient way of deep network optimization is to make adaptive step sizes for each parameter. Recently, several attempts have been made to improve gradient descent methods such as AdaGrad, AdaDelta, RMSProp and Adam. These methods rely on the square roots of exponential moving averages of squared past gradients. Thus, these methods do not take advantage of local change in gradients. In this paper, a novel optimizer is proposed based on the difference between the present and the immediate past gradient (i.e., diffGrad). In the proposed diffGrad optimization technique, the step size is adjusted for each parameter in such a way that it should have a larger step size for faster gradient changing parameters and a lower step size for lower gradient changing parameters. The convergence analysis is done using the regret bound approach of online learning framework. Rigorous analysis is made in this paper over three synthetic complex non-convex functions. The image categorization experiments are also conducted over the CIFAR10 and CIFAR100 datasets to observe the performance of diffGrad with respect to the state-of-the-art optimizers such as SGDM, AdaGrad, AdaDelta, RMSProp, AMSGrad, and Adam. The residual unit (ResNet) based Convolutional Neural Networks (CNN) architecture is used in the experiments. The experiments show that diffGrad outperforms other optimizers. Also, we show that diffGrad performs uniformly well for training CNN using different activation functions. The source code is made publicly available at https://***/shivram1987/diffGrad. Copyright © 2019, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Improving Tiny Vehicle Detection in Complex Scenes

Improving Tiny Vehicle Detection in Complex Scenes

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wei Liu Shengcai Liao Weidong Hu Xuezhi Liang Yan Zhang Center for Biometrics and Security Research & National Laboratory of Pattern Recognition Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China College of Electronic Science National University of Defense Technology Changsha China

Vehicle detection is still a challenge in complex traffic scenes, especially for vehicles of tiny scales. Though RCNN based two-stage detectors have demonstrated considerably good performance, less attention has been paid to the quality of the first stage, where, however, tiny vehicles are very likely to be missed. In this paper, we propose a deep network for accurate vehicle detection, with the main idea of using a relatively large feature map for proposal generation, and keeping ROI feature's spatial layout to represent and detect tiny vehicles. However, large feature maps in lower levels of a deep network generally contain limited discriminant information. To address this, we introduce a backward feature enhancement operation, which absorbs higher level information step by step to enhance the base feature map. By doing so, even with only 100 proposals, the resulting proposal network achieves an encouraging recall over 99%. Furthermore, unlike a common practice which flatten features after ROI pooling, we argue that for a better detection of tiny vehicles, the spatial layout of the ROI features should be preserved and fully integrated. Accordingly, we use a multi-path light-weight processing chain to effectively integrate ROI features, while preserving the spatial layouts. Experiments done on the challenging DETRAC vehicle detection benchmark show that the proposed method largely improves a competitive baseline (ResNet50 based Faster RCNN) by 16.5% mAP, and it outperforms all previously published and unpublished results.

关键词： Proposals Feature extraction Vehicle detection Layout Object detection Detectors Benchmark testing

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：