检索结果-内蒙古大学图书馆

Occlusion-aware R-CNN: Detecting pedestrians in a Crowd

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhang, Shifeng Wen, Longyin Bian, Xiao Lei, Zhen Li, Stan Z. Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China GE Global Research NiskayunaNY United States Macau University of Science and Technology Macau China

Pedestrian detection in crowded scenes is a challenging prob-lem since the pedestrians often gather together and occlude each other. In this paper, we propose a new occlusion-aware R-CNN (OR-CNN) to im-prove the detection accuracy in the crowd. Specically, we design a new aggregation loss to enforce proposals to be close and locate compactly to the corresponding objects. Meanwhile, we use a new part occlusion- A ware region of interest (PORoI) pooling unit to replace the RoI pooling layer in order to integrate the prior structure information of human body with visibility prediction into the network to handle occlusion. Our de-tector is trained in an end-to-end fashion, which achieves state-of-the-art results on three pedestrian detection datasets, i.e., CityPersons, ETH, and INRIA, and performs on-pair with the state-of-the-arts on Caltech. Copyright © 2018, The Authors. All rights reserved.

关键词： Visibility

Age estimation based on a single network with soft softmax of aging modeling

学校读者我要写书评

暂无评论

Age estimation based on a single network with soft softmax o...

Lecture Notes in Computer Science

作者： Tan, Zichang Zhou, Shuai Wan, Jun Lei, Zhen Li, Stan Z. National Laboratory of Pattern Recognition Center for Biometrics and Security Research Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Faculty of Information Technology Macau University of Science and Technology Taipa Macau China

ISBN: (纸本)9783319541860

In this paper, we propose a novel approach based on a single convolutional neural network (CNN) for age estimation. In our proposed network architecture, we first model the randomness of aging with the Gaussian distribution which is used to calculate the Gaussian integral of an age interval. Then, we present a soft softmax regression function used in the network. The new function applies the aging modeling to compute the function loss. Compared with the traditional softmax function, the new function considers not only the chronological age but also the interval nearby true age. Moreover, owing to the complex of Gaussian integral in soft softmax function, a look up table is built to accelerate this process. All the integrals of age values are calculated offline in advance. We evaluate our method on two public datasets: MORPH II and Cross-Age Celebrity Dataset (CACD), and experimental results have shown that the proposed method has gained superior performances compared to the state of the art. © Springer International Publishing AG 2017

关键词： Gaussian distribution

Learning efficient image representation for person re-identification

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Yang, Yang Liao, Shengcai 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

Color names based image representation is successfully used in person re-identification, due to the advantages of being compact, intuitively understandable as well as being robust to photometric variance. However, there exists the diversity between underlying distribution of color names' RGB values and that of image pixels' RGB values, which may lead to inaccuracy when directly comparing them in Euclidean space. In this paper, we propose a new method named soft Gaussian mapping (SGM) to address this problem. We model the discrepancies between color names and pixels using a Gaussian and utilize the inverse of covariance matrix to bridge the gap between them. Based on SGM, an image could be converted to several soft Gaussian maps. In each soft Gaussian map, we further seek to establish stable and robust descriptors within a local region through a max pooling operation. Then, a robust image representation based on color names is obtained by concatenating the statistical descriptors in each stripe. When labeled data are available, one discriminative subspace projection matrix is learned to build efficient representations of an image via cross-view coupling learning. Experiments on the public datasets - VIPeR, PRID450S and CUHK03, demonstrate the effectiveness of our method. Copyright © 2017, The Authors. All rights reserved.

关键词： Gaussian distribution

Vehicle re-identification using quadruple directional deep learning features

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhu, Jianqing Zeng, Huanqiang Huang, Jingchang Liao, Shengcai Lei, Zhen Cai, Canhui Zheng, LiXin College of Engineering Huaqiao University Quanzhou362021 China Fujian Provincial Academic Engineering Research Centre in Industrial Intellectual Techniques and Systems College of Information Science and Engineering Huaqiao University Xiamen361021 China IBM-Research China Building 10/6F 399 Ke-Yuan Road Zhangjiang Hi-Tech Park Pudong New District Shanghai201203 China Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China

In order to resist the adverse effect of viewpoint variations for improving vehicle re-identification performance, we design quadruple directional deep learning networks to extract quadruple directional deep learning features (QD-DLF) of vehicle images. The quadruple directional deep learning networks are with similar overall architecture, including the same basic deep learning architecture but different directional feature pooling layers. Specifically, the same basic deep learning architecture is a shortly and densely connected convolutional neural network to extract basic feature maps of an input square vehicle image in the first stage. Then, the quadruple directional deep learning networks utilize different directional pooling layers, i.e., horizontal average pooling (HAP) layer, vertical average pooling (VAP) layer, diagonal average pooling (DAP) layer and anti-diagonal average pooling (AAP) layer, to compress the basic feature maps into horizontal, vertical, diagonal and anti-diagonal directional feature maps, respectively. Finally, these directional feature maps are spatially normalized and concatenated together as a quadruple directional deep learning feature for vehicle re-identification. Extensive experiments on both VeRi and VehicleID databases show that the proposed QD-DLF approach outperforms multiple state-of-the-art vehicle re-identification methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Vehicles

Cooperative training of deep aggregation networks for RGB-D action recognition

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Wang, Pichao Li, Wanqing Wan, Jun Ogunbona, Philip Liu, Xinwang Advanced Multimedia Research Lab University of Wollongong Australia Motovis Inc Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences School of Computer Science National University of Defense Technology Changsha410073 China

A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power of the deeply learned features and weakens the undesired modality discrepancy by jointly optimizing a ranking loss and a softmax loss for both homogeneous and heterogeneous modalities. The ranking loss consists of intra-modality and cross-modality triplet losses, and it reduces both the intra-modality and cross-modality feature variations. Furthermore, the correlations between RGB and depth data are embedded in the c-ConvNet, and can be retrieved by either of the modalities and contribute to the recognition in the case even only one of the modalities is available. The proposed method was extensively evaluated on two large RGB-D action recognition datasets, ChaLearn LAP IsoGD and NTU RGB+D datasets, and one small dataset, SYSU 3D HOI, and achieved state-of-the-art results. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

Face alignment across large poses: A 3D solution

学校读者我要写书评

暂无评论

Face alignment across large poses: A 3D solution

2016 IEEE Conference on Computer Vision and pattern recognition, CVPR 2016

作者： Zhu, Xiangyu Lei, Zhen Liu, Xiaoming Shi, Hailin Li, Stan Z. Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China Department of Computer Science and Engineering Michigan State University United States

ISBN: (纸本)9781467388511

Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in CV community. However, most algorithms are designed for faces in small to medium poses (below 45°), lacking the ability to align faces in large poses up to 90°. The challenges are three-fold: Firstly, the commonly used landmark-based face model assumes that all the landmarks are visible and is therefore not suitable for profile views. Secondly, the face appearance varies more dramatically across large poses, ranging from frontal view to profile view. Thirdly, labelling landmarks in large poses is extremely challenging since the invisible landmarks have to be guessed. In this paper, we propose a solution to the three problems in an new alignment framework, called 3D Dense Face Alignment (3DDFA), in which a dense 3D face model is fitted to the image via convolutional neutral network (CNN). We also propose a method to synthesize large-scale training samples in profile views to solve the third problem of data labelling. Experiments on the challenging AFLW database show that our approach achieves significant improvements over state-of-the-art methods.

关键词： Alignment

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhu, Jianqing Zeng, Huanqiang Liao, Shengcai Lei, Zhen Cai, Canhui Zheng, LiXin College of Engineering Huaqiao University QuanzhouFujian362021 China Fujian Provincial Academic Engineering Research Centre in Industrial Intellectual Techniques and Systems College of Information Science and Engineering Huaqiao University XiamenFujian361021 China Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China

—Person Re-IDentification (Re-ID) aims to match person images captured from two non-overlapping cameras. In this paper, a deep hybrid similarity learning (DHSL) method for person Re-ID based on a convolution neural network (CNN) is proposed. In our approach, a CNN learning feature pair for the input image pair is simultaneously extracted. Then, both the element-wise absolute difference and multiplication of the CNN learning feature pair are calculated. Finally, a hybrid similarity function is designed to measure the similarity between the feature pair, which is realized by learning a group of weight coefficients to project the element-wise absolute difference and multiplication into a similarity score. Consequently, the proposed DHSL method is able to reasonably assign parameters of feature learning and metric learning in a CNN so that the performance of person Re-ID is improved. Experiments on three challenging person Re-ID databases, QMUL GRID, VIPeR and CUHK03, illustrate that the proposed DHSL method is superior to multiple state-of-the-art person Re-ID methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Convolution

Face Alignment Across Large Poses: A 3D Solution

学校读者我要写书评

暂无评论

Face Alignment Across Large Poses: A 3D Solution

IEEE Conference on Computer Vision and pattern recognition

作者： Xiangyu Zhu Zhen Lei Xiaoming Liu Hailin Shi Stan Z. Li Center for Biometrics and Security Research & National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Department of Computer Science and Engineering Michigan State University

ISBN: (纸本)9781467388528

关键词： face modeling Face Posing Face landmarks Imagery (Psychotherapy) images Alignment

Subspace learning with frequency regularizer: Its application to face recognition

学校读者我要写书评

暂无评论

Subspace learning with frequency regularizer: Its applicatio...

IAPR International Conference on biometrics (ICB)

作者： Zhen Lei Dong Yi Xiangsheng Huang Stan Z. Li Center for Biometrics and Security Research & National Laboratory of Pattern Recognition Chinese Academy of Sciences Beijing China

Subspace learning is an important technique to enhance the discriminative ability of feature representation and reduce the dimension to improve its efficiency. Due to limited training samples and the usual high-dimensional feature, subspace learning always suffers from overfitting problem, which affects its generalization performance. One possible method is to introduce prior information as a regularizer to constrain its solution space. Traditional regularizers are usually designed in spatial domain, which usually make the projection smooth. In this work, we propose a frequency regularizer (FR), which suppresses the high frequency energy so that the smooth priori is incorporated. Two representative supervised subspace methods with frequency regularizer, FR-LDA and FR-SR are introduced and further applied to face recognition problem. Extensive experiments on popular face databases validate the effectiveness and superiority of FR based subspace learning compared to traditional subspace learning methods.

关键词： Face recognition Face Databases Accuracy Principal component analysis Learning systems Frequency-domain analysis