检索结果-内蒙古大学图书馆

CASIA-Face-Africa: A large-scale African face image database

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Muhammad, Jawad Wang, Yunlong Wang, Caiyong Zhang, Kunbo Sun, Zhenan The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing100044 China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044 China

Face recognition is a popular and well-studied area with wide applications in our society. However, racial bias had been proven to be inherent in most State Of The Art (SOTA) face recognition systems. Many investigative studies on face recognition algorithms have reported higher false positive rates of African subjects cohorts than the other cohorts. Lack of large-scale African face image databases in public domain is one of the main restrictions in studying the racial bias problem of face recognition. To this end, we collect a face image database namely CASIA-Face-Africa which contains 38,546 images of 1,183 African subjects. Multi-spectral cameras are utilized to capture the face images under various illumination settings. Demographic attributes and facial expressions of the subjects are also carefully recorded. For landmark detection, each face image in the database is manually labeled with 68 facial keypoints. A group of evaluation protocols are constructed according to different applications, tasks, partitions and scenarios. The performances of SOTA face recognition algorithms without retraining are reported as baselines. The proposed database along with its face landmark annotations, evaluation protocols and preliminary results form a good benchmark to study the essential aspects of face biometrics for African subjects, especially face image preprocessing, face feature analysis and matching, facial expression recognition, sex/age estimation, ethnic classification, face image generation, etc. The database can be downloaded from our website* Copyright © 2021, The Authors. All rights reserved.

关键词： Face recognition

Answer-supervised question reformulation for enhancing conversational machine comprehension 2

学校读者我要写书评

暂无评论

Answer-supervised question reformulation for enhancing conve...

2nd Workshop on Machine Reading for Question Answering, MRQA@EMNLP 2019

作者： Li, Qian Su, Hui Niu, Cheng Wang, Daling Li, Zekang Feng, Shi Zhang, Yifei School of Computer Science and Engineering Northeastern University Shenyang China Pattern Recognition Center WeChat Ai Tencent Inc China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences

ISBN: (纸本)9781950737819

In conversational machine comprehension, it has become one of the research hotspots integrating conversational history information through question reformulation for obtaining better answers. However, the existing question reformulation models are trained only using supervised question labels annotated by annotators without considering any feedback information from answers. In this paper, we propose a novel Answer-Supervised Question Reformulation (ASQR) model for enhancing conversational machine comprehension with reinforcement learning technology. ASQR utilizes a pointer-copy-based question reformulation model as an agent, takes an action to predict the next word, and observes a reward for the whole sentence state after generating the end-of-sequence token. The experimental results on QuAC dataset prove that our ASQR model is more effective in conversational machine comprehension. Moreover, pretraining is essential in reinforcement learning models, so we provide a high-quality annotated dataset for question reformulation by sampling a part of QuAC dataset. © 2019 MRQA@EMNLP 2019 - Proceedings of the 2nd Workshop on Machine Reading for Question Answering. All rights reserved.

关键词： Reinforcement learning

Multi-level graph convolutional network with automatic graph learning for hyperspectral image classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wan, Sheng Gong, Chen Pan, Shirui Yang, Jie Yang, Jian PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Faculty of Information Technology Monash University ClaytonVIC3800 Australia

Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification. However, the current GCN-based methods treat graph construction and image classification as two separate tasks, which often results in suboptimal performance. Another defect of these methods is that they mainly focus on modeling the local pairwise importance between graph nodes while lack the capability to capture the global contextual information of HSI. In this paper, we propose a Multi-level GCN with Automatic Graph Learning method (MGCN-AGL) for HSI classification, which can automatically learn the graph information at both local and global levels. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions, which helps encode the spatial context to form the graph information at local level. Moreover, we utilize multiple pathways for local-level graph convolution, in order to leverage the merits from the diverse spatial context of HSI and to enhance the expressive power of the generated representations. To reconstruct the global contextual relations, our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level. Then inference can be performed along the reconstructed graph edges connecting faraway regions. Finally, the multi-level information is adaptively fused to generate the network output. In this means, the graph learning and image classification can be integrated into a unified framework and benefit each other. Extensive experiments have been conducted on three real-world hyperspectral datasets, which are shown to outperform the state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： image classification

DAmageNet: A universal adversarial dataset

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chen, Sizhe Huang, Xiaolin He, Zhengbao Sun, Chengjin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing 800 Dongchuan Road Shanghai200240 China

It is now well known that deep neural networks (DNNs) are vulnerable to adversarial attack. Adversarial samples are similar to the clean ones, but are able to cheat the attacked DNN to produce incorrect predictions in high confidence. But most of the existing adversarial attacks have high success rate only when the information of the attacked DNN is well-known or could be estimated by massive queries. A promising way is to generate adversarial samples with high transferability. By this way, we generate 96020 transferable adversarial samples from original ones in imageNet. The average difference, measured by root means squared deviation, is only around 3.8 on average. However, the adversarial samples are misclassified by various models with an error rate up to 90%. Since the images are generated independently with the attacked DNNs, this is essentially zero-query adversarial attack. We call the dataset DAmageNet, which is the first universal adversarial dataset that beats many models trained in imageNet. By finding the drawbacks, DAmageNet could serve as a benchmark to study and improve robustness of DNNs. DAmageNet could be downloaded in http://***/Show/56/122 Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

A comprehensive survey of oracle character recognition: Challenges, datasets, methodology, and beyond

学校读者我要写书评

暂无评论

pattern recognition 2026年 169卷

作者： Jing Li Xueke Chi Qiufeng Wang Kaizhu Huang Da-Han Wang Yongge Liu Cheng-Lin Liu College of Science & Technology Ningbo University Ningbo China School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou China Duke Kunshan University Suzhou China Fujian Key Laboratory of Pattern Recognition and Image Understanding School of Computer and Information Engineering Xiamen University of Technology Xiamen China Anyang Normal University Anyang China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

Oracle character recognition — an analysis of ancient Chinese inscriptions found on oracle bones — has become a pivotal field intersecting archaeology, paleography, and historical cultural studies. Traditional methods of oracle character recognition have relied heavily on manual interpretation by experts, which is not only labor-intensive but also limits broader accessibility to the general public. With recent breakthroughs in pattern recognition and deep learning, there is a growing movement toward the automation of oracle character recognition (OrCR), showing considerable promise in tackling the challenges inherent to these ancient scripts. However, a comprehensive understanding of OrCR still remains elusive. Therefore, this paper presents a systematic and structured survey of the current landscape of OrCR research. We commence by identifying and analyzing the key challenges of OrCR. Then, we provide an overview of the primary benchmark datasets and digital resources available for OrCR. A review of contemporary research methodologies follows, in which their respective efficacies, limitations, and applicability to the complex nature of oracle characters are critically highlighted and examined. Additionally, our review extends to ancillary tasks associated with OrCR across diverse disciplines, providing a broad-spectrum analysis of its applications. We conclude with a forward-looking perspective, proposing potential avenues for future investigations that could yield significant advancements in the field.

关键词：

Bridging text and video: A universal multimodal transformer for video-audio scene-aware dialog

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Zekang Li, Zongjia Zhang, Jinchao Feng, Yang Niu, Cheng Zhou, Jie Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Pattern Recognition Center WeChat AI Tencent Inc China School of EECS Peking University University of Chinese Academy of Sciences

Audio-Visual Scene-Aware Dialog (AVSD) is a task to generate responses when chatting about a given video, which is organized as a track of the 8th Dialog System Technology Challenge (DSTC8). To solve the task, we propose a universal multimodal transformer and introduce the multitask learning method to learn joint representations among different modalities as well as generate informative and fluent responses. Our method extends the natural language generation pre-trained model to multimodal dialogue generation task. Our system achieves the best performance in both objective and subjective evaluations in the challenge. Copyright © 2020, The Authors. All rights reserved.

关键词： Natural language processing systems

Research on Laser Measurement of 3D curved Glass Contour based on computer Vision

学校读者我要写书评

暂无评论

Research on Laser Measurement of 3D curved Glass Contour bas...

International Conference on Information Science and Control Engineering (ICISCE)

作者： Peng Wang Jinmeng Wu Guilin Yan Shuo Bian Hubei Key Laboratory of Optical Information and Pattern Recognition Hubei Research Centre of Video Image and High Definition Projection Wuhan Institute of Technology Wuhan China School of Mechanical and Electrical Engineering School of Electrical and Information Engineering

In the mobile phone glass industry, curved glass is widely used. Whether the curved glass is measured with high efficiency and precision and whether the curved edge profile error can be evaluated directly affects the quality and service cycle of glass products. In view of the difficulty of accurate measurement and evaluation of 3D mobile phones curved glass profile, a visual measurement method of 3D mobile phones curved glass profile error based on laser scanning and shape template matching is proposed in this paper. Accurate measurement of mobile phone curved glass greatly improves the fit between curved glass and mobile phone and the efficiency of production. Therefore, this paper proposes a method for evaluating the contour degree of curved glass on mobile phones based on Open Cascade and OpenCV. This method uses the lasers and camera equipment to extract the profile outline of the curved glass, then extract the profile outline of the mobile phone curved glass model that has been drawn in 3D software. The extracted contour lines are matched by methods such as translation and rotation, and finally the distance between the corresponding points is calculated as the contour error. Experimental results show that the method is able to accurately measure the profile error and greatly reduce the measurement instability and have good robustness.

关键词： Computer vision Three-dimensional displays Shape Shape measurement Measurement uncertainty Measurement by laser beam Glass

Identification and Extraction of Circular Markers in 3D Reconstruction

学校读者我要写书评

暂无评论

Identification and Extraction of Circular Markers in 3D Reco...

International Conference on Wireless Communications and Signal processing (WCSP)

作者： Yunfei Wang Hanyu Hong Jinmeng Wu Guangya Wang Shiyang Li Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan China Hubei Engineering Research Center of Video Image and HD Projection Wuhan China School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan China

ISBN: (数字)9781728172361

ISBN: (纸本)9781728172378

This paper presents a method for the identification and location of circular markers in 3D reconstruction. The input image is processed with gray scale and gaussian filter to remove noise interference and improve the accuracy of edge detection. The size and direction of the gradient of the image were calculated to obtain the edge features of the circular marker, and the circle degree of the closed edge was judged, and the center of the marker was obtained by fitting the edge features with the ellipse of the least square method. Hu moment similarity of each marker was obtained, and the non-marker was deleted and the real marker was retained by similarity judgment. Experiments show that the algorithm has good robustness, high precision, can effectively reduce the probability of false detection, and has high accuracy in complex environments.

关键词： image edge detection Transforms Three-dimensional displays Fitting Feature extraction Cameras Least mean squares methods

Analysis of Least Squares Regularized Regression in Reproducing Kernel Kreın Spaces

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Fanghui Shi, Lei Huang, Xiaolin Yang, Jie Suykens, Johan A.K. Department of Electrical Engineering [ESAT-STADIUS KU Leuven LeuvenB-3001 Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai China

In this paper, we study the asymptotical properties of least squares regularized regression with indefinite kernels in reproducing kernel Kreın spaces (RKKS). The classical approximation analysis cannot be directly applied to study its asymptotical behavior under the framework of learning theory as this problem is in essence non-convex and outputs stationary points. By introducing a bounded hyper-sphere constraint to such non-convex regularized risk minimization problem, we theoretically demonstrate that this problem has a globally optimal solution with a closed form on the sphere, which makes our approximation analysis feasible in RKKS. Accordingly, we modify traditional error decomposition techniques, prove convergence results for the introduced hypothesis error based on matrix perturbation theory, and derive learning rates of such regularized regression problem in RKKS. Under some conditions, the derived learning rates in RKKS are the same as that in reproducing kernel Hilbert spaces (RKHS), which is actually the first work on approximation analysis of regularized learning algorithms in RKKS. Copyright © 2020, The Authors. All rights reserved.

关键词： Learning algorithms