检索结果-内蒙古大学图书馆

4th International Conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2022

作者： Liu, Jinde Zhang, Zhang University of Chinese Academy of Sciences Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665463997

In this paper, we propose a new framework for detecting objects in RGB images captured by conventional cameras by leveraging a set of labeled RGB-D data. We formulate this problem into a new multi-view learning problem, where we have the depth information in the training set that is not available in the testing set. To solve this problem, we use a three-view CCA learning method which combines visual features, depth features, and label information together to get the projection matrices. Sufficient experiments are done to demonstrate the effectiveness of our method, and improvement measures in the future are also proposed. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Hierarchical recurrent neural network for skeleton based action recognition

Hierarchical recurrent neural network for skeleton based act...

引用

IEEE Conference on Computer Vision and pattern recognition, CVPR 2015

作者： Du, Yong Wang, Wei Wang, Liang Center for Research on Intelligent Perception and Computing CRIPAC Nat'l Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences China

ISBN: (纸本)9781467369640

Human actions can be represented by the trajectories of skeleton joints. Traditional methods generally model the spatial structure and temporal dynamics of human skeleton with hand-crafted features and recognize human actions by well-designed classifiers. In this paper, considering that recurrent neural network (RNN) can model the long-term contextual information of temporal sequences well, we propose an end-to-end hierarchical RNN for skeleton based action recognition. Instead of taking the whole skeleton as the input, we divide the human skeleton into five parts according to human physical structure, and then separately feed them to five subnets. As the number of layers increases, the representations extracted by the subnets are hierarchically fused to be the inputs of higher layers. The final representations of the skeleton sequences are fed into a single-layer perceptron, and the temporally accumulated output of the perceptron is the final decision. We compare with five other deep RNN architectures derived from our model to verify the effectiveness of the proposed network, and also compare with several other methods on three publicly available datasets. Experimental results demonstrate that our model achieves the state-of-the-art performance with high computational efficiency. © 2015 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Toward few-shot domain adaptation with perturbation-invariant representation and transferable prototypes

引用

Frontiers of Computer Science 2022年第3期16卷 83-93页

作者： Junsong FAN Yuxi WANG He GUAN Chunfeng SONG Zhaoxiang ZHANG Center for Research on Intelligent Perception and Computing National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Centre for Artificial Intelligence and Robotics HKISI CASHongKong 999077China

Domain adaptation(DA)for semantic segmentation aims to reduce the annotation burden for the dense pixellevel prediction *** focuses on tackling the domain gap problem and manages to transfer knowledge learned from abundant source data to new target *** recent works have achieved rapid progress in this field,they still underperform fully supervised models with a large margin due to the absence of any available hints in the target *** that few-shot labels are cheap to obtain in practical applications,wc attempt to leverage them to mitigate the performance gap between DA and fully supervised *** key to this problem is to leverage the few-shot labels to learn robust domain-invariant predictions *** this end,we first design a data perturbation strategy to enhance the robustness of the ***,a transferable prototype module is proposed to bridge the domain gap based on the source data and few-shot *** means of these proposed methods,our approach can perform on par with the fully supervised models to some *** conduct extensive experiments to demonstrate the effectiveness of the proposed methods and report the state-of-the-art performance on two popular DA tasks,i.e.,from GTA5 to Cityscapes and SYNTHIA to Cityscapes.

关键词： domain adaptation semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Surface remeshing with robust user-guided segmentation

引用

Computational Visual Media 2018年第2期4卷 113-122页

作者： Dawar Khan Dong-Ming Yan Fan Ding Yixin Zhuang Xiaopeng Zhang National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing100049China National Digital Switching System Engineering&Technological Research Center China

Surface remeshing is widely required in modeling, animation, simulation, and many other computer graphics applications. Improving the elements' quality is a challenging task in surface remeshing. Existing methods often fail to efficiently remove poor-quality elements especially in regions with sharp features. In this paper, we propose and use a robust segmentation method followed by remeshing the segmented mesh. Mesh segmentation is initiated using an existing Live-wire interaction approach and is further refined using local mesh operations. The refined segmented mesh is finally sent to the remeshing pipeline, in which each mesh segment is remeshed independently. An experimental study compares our mesh segmentation method as well as remeshing results with representative existing methods. We demonstrate that the proposed segmentation method is robust and suitable for remeshing.

关键词： mesh generation surface remeshing mesh segmentation triangulation

来源：评论

学校读者我要写书评

暂无评论

Accurate mouth state estimation via convolutional neural networks

Accurate mouth state estimation via convolutional neural net...

引用

2016 IEEE International Conference on Digital Signal Processing, DSP 2016

作者： Cao, Jie Li, Haiqing Sun, Zhenan He, Ran National Laboratory of Pattern Recognition CASIA Center for Research on Intelligent Perception and Computing University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781509041657

Human mouth is very flexible such that its status (closed or open) is often used as a judgment in the liveness detection of face recognition. However, due to large head pose and illumination variations, accurate mouth status estimation is still challenging in real-world scenarios. In this paper, we propose a deep convolutional neural networks (CNNs) method for mouth status estimation under unconstrained conditions and different types of attacks. Different from previous methods that extract hand-crafted features and then treat the estimation problem as a binary classification task, our method automatically extracts discriminative features via learned convolutional and the pooling layers. To demonstrate the effectiveness of our method and the challenge of mouth status estimation in real-world, we also propose a mouth status estimation dataset that contains 10,714 images in the wild. Experimental results with two types of liveness attacks show that our proposed method outperforms the other traditional methods, especially in the wild condition. © 2016 IEEE.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Joint space learning for video-based face recognition 3

Joint space learning for video-based face recognition

引用

3rd IAPR Asian Conference on pattern recognition, ACPR 2015

作者： Cao, Dong He, Ran Sun, Zhenan Tan, Tieniu Center for Research on Intelligent Perception and Computing CASIA China National Laboratory of Pattern Recognition CASIA China Center for Excellence in Brain Science and Intelligence Technology CAS China

ISBN: (纸本)9781479961009

Popularity of surveillance and mobile cameras provides great opportunities to video-based face recognition (VFR) in less-controlled conditions. This paper proposes a joint space learning method to simultaneously identify the most representative samples and discriminative features from facial videos for reliable face recognition. Specifically, we use a mixture modal by learning multiple feature spaces to capture the data variations where the representative samples in each subspace are learned. Actually, this procedure is a chick to egg problem and an alternate algorithm is developed to monotonically optimize the joint task. In addition, randomized techniques are applied to kernel approximations for capturing the nonlinear structure in data, so that both accuracy and efficiency of our method can be improved. The proposed method performs better than the state-of-the-art video based face recognition methods on Honda, Mobo and YouTube Celebrities databases. © 2015 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Float greedy-search-based subspace clustering 3

Float greedy-search-based subspace clustering

引用

3rd IAPR Asian Conference on pattern recognition, ACPR 2015

作者： Song, Lingxiao Zhang, Man Li, Qi Sun, Zhenan He, Ran Center for Research on Intelligent Perception and Computing CASIA China National Laboratory of Pattern Recognition CASIA China Center for Excellence in Brain Science and Intelligence Technology CAS China

ISBN: (纸本)9781479961009

Many kinds of efficient greedy subspace clustering methods have been proposed to cut down the computation time in clustering large-scale multimedia datasets. However, these methods are easy to fall into local optimum due to the inherent characteristic of greedy algorithms, which are stepoptimal only. To alleviate this problem, this paper proposes a novel greedy subspace clustering strategy based on floating search, called Float Greedy Subspace Clustering (FloatGSC). In order to control the complexity, the nearest subspace neighbor is added in a greedy way, and the subspace is updated by adding an orthogonal basis involved with the newly added data points in each iteration. Besides, a backtracking mechanism is introduced after each iteration to reject wrong neighbors selected in previous iterations. Extensive experiments on motion segmentation and face clustering show that our algorithm can significantly improve the clustering accuracy without sacrificing much computational time, compared with previous greedy subspace clustering methods. © 2015 IEEE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Supervised topology preserving hashing 3

Supervised topology preserving hashing

引用

3rd IAPR Asian Conference on pattern recognition, ACPR 2015

作者： Zhang, Shu Zhang, Man Li, Qi Tan, Tieniu He, Ran Center for Research on Intelligent Perception and Computing CASIA China National Laboratory of Pattern Recognition CASIA China Center for Excellence in Brain Science and Intelligence Technology CAS China

ISBN: (纸本)9781479961009

Learning based hashing is gaining traction in large-scale retrieval systems. It aims to learn compact binary codes that can preserve semantic similarity in the hamming space. This paper presents a supervised topology hashing (SPTH) algorithm to learn compact binary codes that can exploit both the supervisory information as well as the local topology structure of datasets. To build a connection between the original space and the resultant hamming space, we minimize the quantization errors together with a classification error term and a topology preserving term. A nonlinear kernel feature space is further used to improve the generalization power. An alternating iterative algorithm is developed to minimize the complex objective function that contains both continuous and discrete variables. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed method on image retrieval tasks. © 2015 IEEE.

关键词： Binary codes

来源：评论

学校读者我要写书评

暂无评论

Every Corporation Owns Its Image: Corporate Credit Ratings via Convolutional Neural Networks 6

Every Corporation Owns Its Image: Corporate Credit Ratings v...

引用

6th IEEE International Conference on Computer and Communications, ICCC 2020

作者： Feng, Bojing Xue, Wenfang Xue, Bindang Liu, Zeyu Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Science Beijing China School of Astronautics Beihang University Beijing China Tianjin Academy for Intelligent Recognition Technologies Tianjin China

ISBN: (纸本)9781728186351

Credit rating is an analysis of the credit risks associated with a corporation, which reflect the level of the riskiness and reliability in investing. There have emerged many studies that implement machine learning techniques to deal with corporate credit rating. However, the ability of these models is limited by enormous amounts of data from financial statement reports. In this work, we analyze the performance of traditional machine learning models in predicting corporate credit rating. For utilizing the powerful convolutional neural networks and enormous financial data, we propose a novel end-to-end method, Corporate Credit Ratings via Convolutional Neural Networks, CCR-CNN for brevity. In the proposed model, each corporation is transformed into an image. Based on this image, CNN can capture complex feature interactions of data, which are difficult to be revealed by previous machine learning models. Extensive experiments conducted on the Chinese public-listed corporate rating dataset which we build, prove that CCR-CNN outperforms the state-of-the-art methods consistently. © 2020 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Robust Object Tracking via Information Theoretic Measures

引用

International Journal of Automation and computing 2020年第5期17卷 652-666页

作者： Wei-Ning Wang Qi Li Liang Wang Center for Research on Intelligent Perception and Computing National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190China Artificial Intelligence Research Chinese Academy of SciencesQingdao 266300China

Object tracking is a very important topic in the field of computer *** sophisticated appearance models have been *** them,the trackers based on holistic appearance information provide a compact notion of the tracked object and thus are robust to appearance variations under a small amount of ***,in practice,the tracked objects are often corrupted by complex noises(e.g.,partial occlusions,illumination variations)so that the original appearance-based trackers become less *** paper presents a correntropy-based robust holistic tracking algorithm to deal with various ***,a half-quadratic algorithm is carefully employed to minimize the correntropy-based objective *** on the proposed information theoretic algorithm,we design a simple and effective template update scheme for object *** results on publicly available videos demonstrate that the proposed tracker outperforms other popular tracking algorithms.

关键词： Object tracking information theoretic measures correntropy template update robust to complex noises

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：