检索结果-内蒙古大学图书馆

Meta auxiliary learning for facial action unit detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Yong Shan, Shiguang Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Cas Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Cas Center for Excellence in Brain Science and Intelligence Technology

Despite the success of deep neural networks on facial action unit (AU) detection, better performance depends on a large number of training images with accurate AU annotations. However, labeling AU is time-consuming, expensive, and error-prone. Considering AU detection and facial expression recognition (FER) are two highly correlated tasks, and facial expression (FE) is relatively easy to annotate, we consider learning AU detection and FER in a multi-task manner. However, the performance of the AU detection task cannot be always enhanced due to the negative transfer in the multi-task scenario. To alleviate this issue, we propose a Meta Auxiliary Learning method (MAL) that automatically selects highly related FE samples by learning adaptative weights for the training FE samples in a meta learning manner. The learned sample weights alleviate the negative transfer from two aspects: 1) balance the loss of each task automatically, and 2) suppress the weights of FE samples that have large uncertainties. Experimental results on several popular AU datasets demonstrate MAL consistently improves the AU detection performance compared with the state-of-the-art multi-task and auxiliary learning methods. MAL automatically estimates adaptive weights for the auxiliary FE samples according to their semantic relevance with the primary AU detection task. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

Learning fair face representation with progressive cross transformer

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Yong Sun, Yufei Cui, Zhen Shan, Shiguang Yang, Jian Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology

Face recognition (FR) has made extraordinary progress owing to the advancement of deep convolutional neural networks. However, demographic bias among different racial cohorts still challenges the practical face recognition system. The race factor has been proven to be a dilemma for fair FR (FFR) as the subject-related specific attributes induce the classification bias whilst carrying some useful cues for FR. To mitigate racial bias and meantime preserve robust FR, we abstract face identityrelated representation as a signal denoising problem and propose a progressive cross transformer (PCT) method for fair face recognition. Originating from the signal decomposition theory, we attempt to decouple face representation into i) identity-related components and ii) noisy/identity-unrelated components induced by race. As an extension of signal subspace decomposition, we formulate face decoupling as a generalized functional expression model to cross-predict face identity and race information. The face expression model is further concretized by designing dual cross-transformers to distill identity-related components and suppress racial noises. In order to refine face representation, we take a progressive face decoupling way to learn identity/racespecific transformations, so that identity-unrelated components induced by race could be better disentangled. We evaluate the proposed PCT on the public fair face recognition benchmarks (BFW, RFW) and verify that PCT is capable of mitigating bias in face recognition while achieving state-of-the-art FR performance. Besides, visualization results also show that the attention maps in PCT can well reveal the race-related/biased facial regions. © 2021, CC BY-NC-SA.

关键词： Face recognition

Graph jigsaw learning for cartoon face recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Yong Lao, Lingjie Cui, Zhen Shan, Shiguang Yang, Jian Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology

Cartoon face recognition is challenging as they typically have smooth color regions and emphasized edges, the key to recognize cartoon faces is to precisely perceive their sparse and critical shape patterns. However, it is quite difficult to learn a shape-oriented representation for cartoon face recognition with convolutional neural networks (CNNs). To mitigate this issue, we propose the GraphJigsaw that constructs jigsaw puzzles at various stages in the classification network and solves the puzzles with the graph convolutional network (GCN) in a progressive manner. Solving the puzzles requires the model to spot the shape patterns of the cartoon faces as the texture information is quite limited. The key idea of GraphJigsaw is constructing a jigsaw puzzle by randomly shuffling the intermediate convolutional feature maps in the spatial dimension and exploiting the GCN to reason and recover the correct layout of the jigsaw fragments in a self-supervised manner. The proposed GraphJigsaw avoids training the classification model with the deconstructed images that would introduce noisy patterns and are harmful for the final classification. Specially, GraphJigsaw can be incorporated at various stages in a top-down manner within the classification model, which facilitates propagating the learned shape patterns gradually. GraphJigsaw does not rely on any extra manual annotation during the training process and incorporates no extra computation burden at inference time. Both quantitative and qualitative experimental results have verified the feasibility of our proposed GraphJigsaw, which consistently outperforms other face recognition or jigsaw-based methods on two popular cartoon face datasets with considerable improvements. © 2021, CC BY-NC-SA.

关键词： Face recognition

Contrastive Learning of Person-independent Representations for Facial Action Unit Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Yong Shan, Shiguang The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology CAS Beijing100190 China The University of Chinese Academy of Sciences Beijing100049 China Peng Cheng Laboratory Shenzhen518055 China

Facial action unit (AU) detection, aiming to classify AU present in the facial image, has long suffered from insufficient AU annotations. In this paper, we aim to mitigate this data scarcity issue by learning AU representations from a large number of unlabelled facial videos in a contrastive learning paradigm. We formulate the self-supervised AU representation learning signals in two-fold: (1) AU representation should be frame-wisely discriminative within a short video clip;(2) Facial frames sampled from different identities but show analogous facial AUs should have consistent AU representations. As to achieve these goals, we propose to contrastively learn the AU representation within a video clip and devise a cross-identity reconstruction mechanism to learn the person-independent representations. Specially, we adopt a margin-based temporal contrastive learning paradigm to perceive the temporal AU coherence and evolution characteristics within a clip that consists of consecutive input facial frames. Moreover, the cross-identity reconstruction mechanism facilitates pushing the faces from different identities but show analogous AUs close in the latent embedding space. Experimental results on three public AU datasets demonstrate that the learned AU representation is discriminative for AU detection. Our method outperforms other contrastive learning methods and significantly closes the performance gap between the self-supervised and supervised AU detection approaches. © 2024, CC BY.

关键词： Learning systems

Stereoscopic learning for disparity estimation

学校读者我要写书评

暂无评论

Stereoscopic learning for disparity estimation

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Zhebin Zhang Yizhou Wang Tingting Jiang Wen Gao National Engineering Laboratory for Video Technology Peking University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China Key Laboratory of Machine Perception (MoE) School of EECS Peking University Beijing China Peking University Beijing Beijing CN

In this paper, we propose a learning based approach to estimating pixel disparities from the motion information extracted out of input monoscopic video sequences. We represent each video frame with superpixels, and extract the motion features from the superpixels and the frame boundary. These motion features account for the motion pattern of the superpixel as well as camera motion. In the learning phase, given a pair of stereoscopic video sequences, we employ a state-of-the-art stereo matching method to compute the disparity map of each frame as ground truth. Then a multi-label SVM is trained from the estimated disparities and the corresponding motion features. In the testing phase, we use the learned SVM to predict the disparity for each superpixel in a monoscopic video sequence. Experiment results show that the proposed method achieves low error rate in disparity estimation.

关键词： Pixel Three dimensional displays Cameras Feature extraction Histograms Support vector machines Optical imaging

Learning data-adaptive nonparametric kernels

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Fanghui Huang, Xiaolin Gong, Chen Yang, Jie Li, Li Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Automation Tsinghua University

Kernel methods have been extensively used in a variety of machine learning tasks such as classification, clustering, and dimensionality reduction. For complicated practical tasks, the traditional kernels, e.g., Gaussian kernel and sigmoid kernel, or their combinations are often not sufficiently flexible to fit the data. In this paper, we present a Data-Adaptive Nonparametric Kernel (DANK) learning framework in a data-driven manner. To be specific, in model formulation, we impose an adaptive matrix on the kernel/Gram matrix in an entry-wise strategy. Since we do not specify the formulation of the adaptive matrix, each entry in the adaptive matrix can be directly and flexibly learned from the data. Therefore, the solution space of the learned kernel is largely expanded, which makes our DANK model flexible to capture the data with different local statistical properties. Specifically, the proposed kernel learning framework can be seamlessly embedded to support vector machines (SVM) and support vector regression (SVR), which has the capability of enlarging the margin between classes and reducing the model generalization error. Theoretically, we demonstrate that the objective function of our DANK model embedded in SVM/SVR is gradient-Lipschitz continuous. Thereby, the training process for kernel and parameter learning in SVM/SVR can be efficiently optimized in a unified framework. Further, to address the scalability issue in nonparametric kernel learning framework, we decompose the entire optimization problem in DANK into several smaller easy-to-solve problems, so that our DANK model can be efficiently approximated by this partition. The effectiveness of this approximation is demonstrated by both empirical studies and theoretical guarantees. Experimentally, the proposed DANK model embedded in SVM/SVR achieves encouraging performance on various classification and regression benchmark datasets when compared with other representative kernel learning based algorithms. Copyrig

关键词： Matrix algebra

An extragradient algorithm for fixed point problems and pseudomonotone equilibrium problems

学校读者我要写书评

暂无评论

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2020年第4期82卷 89-96页

作者： Yao, Zhangsong Liou, Yeong-Cheng Zhu, Li-Jun School of Information Engineering Nanjing Xiaozhuang University Nanjing211171 China Department of Healthcare Administration and Medical Informatics Research Center of Nonlinear Analysis and Optimization Kaohsiung Medical University Department of Medical Research Kaohsiung Medical University Hospital Kaohsiung807 Taiwan The Key Laboratory of Intelligent Information and Big Data Processing of NingXia Province and Health Big Data Research Institute Advanced Intelligent Perception and Control Technology Innovative Team of NingXia North Minzu University Yinchuan750021 China

Iterative methods for solving fixed point problems and pseudomonotone equilibrium problems have been considered. An extragradient algorithm has been presnted for finding a common element of the fixed points of pseudocontractive operators and the solutions of pseudomonotone equilibrium problems in Hilbert spaces. Weak convergence result of the suggested algorithm is proved. © 2020, Politechnica University of Bucharest. All rights reserved.

关键词： Iterative methods

Eu-Mof Based Fluorescence Probe for Ratiometric and Visualization Detection of Copper Ions

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Li, Zhihua Deng, Jiaxi Zhang, Jing Qiao, Cailin Yang, Mei Xu, Guoren Luo, Xiaogang Huo, Danqun Hou, Changjun Ministry of Education College of Bioengineering Chongqing University Chongqing400044 China State Key Laboratory of Urban Water Resources & Environment Harbin Institute of Technology Harbin150090 China Chongqing Key Laboratory of Bio-perception & Intelligent Information Processing School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China

In this work, a novel and effective ratio fluorescent probe Eu-BTB was prepared for the detection of Cu2+ using 1,3, 5-tri (4-carboxyphenyl) benzene (H3BTB) as ligand and Eu3+ as metal framework, which showed excellent fluorescence performance in the detection of Cu2+. The BTB of the probe can achieve "antenna effect" with Eu3+, which can sensitize Eu3+ emission effectively while maintaining its own emission. Copper ions can competitively bind to BTB, thus inhibiting the antenna effect. In the concentration range of 0.05-10 μM, the ratio of fluorescence intensity and copper ion concentration showed a good linear relationship, and the detection limit was as low as 10 nM, corresponding time was 3 minutes. The fluorescence probe has been successfully applied to the detection of copper ions in water in different environments, the standard method Inductively coupled plasma mass spectrometry(ICP-MS) proved that the results were reliable. which confirmed the potential of Eu-BTB probe in the rapid and accurate detection of Cu2+ in different environmental water samples. © 2022, The Authors. All rights reserved.

关键词： Fluorescence

Edge-Aware Graph Attention Network for Ratio of Edge-User Estimation in Mobile Networks

学校读者我要写书评

暂无评论

Edge-Aware Graph Attention Network for Ratio of Edge-User Es...

International Conference on Pattern Recognition

作者： Jiehui Deng Sheng Wan Xiang Wang Enmei Tu Xiaolin Huang Jie Yang Chen Gong PCA Lab the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Hong Kong Polytechnic University Hong Kong SAR China

Estimating the Ratio of Edge-Users (REU) is an important issue in mobile networks, as it helps the subsequent adjustment of loads in different cells. However, existing approaches usually determine the REU manually, which are experience-dependent and labor-intensive, and thus the estimated REU might be imprecise. Considering the inherited graph structure of mobile networks, in this paper, we utilize a graph-based deep learning method for automatic REU estimation, where the practical cells are deemed as nodes and the load switchings among them constitute edges. Concretely, Graph Attention Network (GAT) is employed as the backbone of our method due to its impressive generalizability in dealing with networked data. Nevertheless, conventional GAT cannot make full use of the information in mobile networks, since it only incorporates node features to infer the pairwise importance and conduct graph convolutions, while the edge features that are actually critical in our problem are disregarded. To accommodate this issue, we propose an Edge-Aware Graph Attention Network (EAGAT), which is able to fuse the node features and edge features for REU estimation. Extensive experimental results on two real-world mobile network datasets demonstrate the superiority of our EAGAT approach to several state-of-the-art methods.

关键词： Deep learning Fuses Estimation Switches Pattern recognition