检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing (ICIP)

作者： Chen, Yu Luo, Wei Yang, Jian Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781479983391

Facial landmark detection is an important issue in a face recognition system. However, human faces in wild conditions often present large variations in shape due to different poses, occlusions or expressions, which makes it a difficult task. Instead of learning the same map for all images, we propose a Pose-Induced auto-encoder Networks (PIAN) approach which uses different pose-induced networks for landmark estimation under different pose conditions. Firstly, we build a network to simultaneously get the initial landmark and pose estimation. Then, different networks which are induced by the estimated pose are built for local search where a component-based searching method is explored. By using the pose inducing strategy, the initial estimation is reliable and it helps reduce the variations in local patches. This makes the component-based search feasible and more accurate than previous searching methods. Experiments show that our method outperforms the state-of-the-art algorithms especially in terms of fine estimation of landmarks.

关键词： Facial landmark Pose-induced deep auto-encoder

来源：评论

学校读者我要写书评

暂无评论

SEMI-SUPERVISED LEARNING WITH BIDIRECTIONAL ADAPTIVE PAIRWISE ENCODING 15

SEMI-SUPERVISED LEARNING WITH BIDIRECTIONAL ADAPTIVE PAIRWIS...

引用

15th IEEE International Conference on Machine Learning and Applications (ICMLA)

作者： Yuan, Jiangbo Yu, Jie VipShop US Inc San Jose CA 95131 USA Canon USA Inc San Jose CA USA

ISBN: (纸本)9781509061679

In contrast to classic supervised learning methods that demand pre-defined class labels, pairwise encoding or side-information encoding merely requires pairwise similarity information to drive feature learning, which makes it very appealing for many fundamental tasks such as dimensionality reduction and semi-supervised learning. In this paper, we present a novel bimarginal pairwise encoding model, along with deep autoencoder, to learn nonlinear embedding for the aforementioned tasks. The new method learns powerful features that preserve critical pairwise information in a semi-supervised manner. It has achieved better performance on the well-known yet hard to make improvement benchmark MINIST compared with other methods in the same category, i.e. autoencoder [4], Invariant Mapping for Dimensionality Reduction [1], Neighborhood Component Analysis [3], and Fixed Bi-Margin Pairwise Encoding [11].

关键词： Side-information deep auto-encoder metric learning dimensionality reduction semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

High Dimensionality Reduction Using CUR Matrix Decomposition and auto-encoder for Web Image Classification

High Dimensionality Reduction Using CUR Matrix Decomposition...

引用

11th Pacific Rim Conference on Multimedia

作者： Liu, Yang Shao, Jian Zhejiang Univ Collage Comp Sci & Technol Hangzhou 310027 Zhejiang Peoples R China

ISBN: (纸本)9783642156953

Reducing the dimensionality of image with high-dimensional feature plays a significant role in image retrieval and classification. Recently, two methods have been proposed to improve the efficiency and accuracy of dimensionality reduction, one uses CUR matrix decompositions to construct low rank matrix approximations and another approach for dimension reduction trains an auto-encoder with deep architecture to learn low-dimensional codes. In this paper, after above two mentioned methods are respectively utilized to reduce the high-dimensional features of images, we train individual classifiers on both original and reduced feature space for image classification. This paper compares these two approaches with other approaches in image classification. At the same, we also study the effects of the depth of layers on the performance of dimensionality reduction using auto-encoder.

关键词： Dimensionality Reduction deep auto-encoder CUR Matrix Decomposition Image Classification

来源：评论

学校读者我要写书评

暂无评论

AnEffective Design for Fast Query-by-Humming System with Melody Segmentation and Feature Extraction

AnEffective Design for Fast Query-by-Humming System with Mel...

引用

International Conference on Computer Systems, Electronics and Control (ICCSEC)

作者： Lv, Anchao Liu, Gang Beijing Univ Posts & Telecommun Dept Automat Pattern Recognit & Intelligent Syst Lab Beijing Peoples R China Beijing Univ Posts & Telecommun Dept Informat & Commun Engn Pattern Recognit & Intelligent Syst Lab Beijing Peoples R China

ISBN: (纸本)9781538635735

A melody segmentation scheme based on pivotal points combined deep auto-encoder (DAE) for Query-by-Humming (QBH) systems is investigated. In order to deal with personalization of human voice, especially the instability in rhythm, we adopt a joint melody segmentation and encoded features extraction method. Pitch sequence between pivotal points shows characteristic differences largely due to monolithic deviation on tones, dynamic diversification in vocal range and mutative scale of tempo. The pivotal points in melody involve extreme and some extreme midpoints which depict the global trends, simultaneously exhibit robust to humming melody. Based on feature extraction, a novel melody segmentation scheme is derived to solve the problem. Through the trained DAE from the deep learning, the deep level coding features in melody are acquired. The experiment results are carried out to demonstrate the validity of the proposed scheme.

关键词： Feature extraction Melody segmentation Pivotal points deep auto-encoder Query-by-Humming

来源：评论

学校读者我要写书评

暂无评论

Lip-reading via a DNN-HMM Hybrid System Using Combination of The Image-based and Model-based Features 3

Lip-reading via a DNN-HMM Hybrid System Using Combination of...

引用

3rd International Conference on Pattern Analysis and Image Analysis (IPRIA)

作者： Rahmani, Mohammad Hasan Almasganj, Farshad Amirkabir Univ Technol Tehran Polytech Biomed Engn Dept Tehran Iran

ISBN: (纸本)9781509064540

Introducing features that better represent the visual information of speakers during the speech production is still an open issue that highly affects the quality of the lip-reading and Audio Visual Speech Recognition (AVSR) tasks. In this paper, three different types of visual features from both the image-based and model-based ones are investigated inside a professional lip reading task. The simple raw gray level information of the lips Region of Interest (ROI), the geometric representation of lips shape and the deep Bottle-neck Features (DBNFs) extracted from a 6-layer deep auto-encoder Neural Network (DANN) are three valuable feature sets compared while employed for the lip reading purpose. Two different recognition systems, including the conventional GMM-HMM and the state-of-the-art DNN-HMM hybrid, are utilized to perform an isolated and connected digit recognition task. The results indicate that the high level information extracted from deep layers of the lips ROI can represent the visual modality with advantage of "high amount of information in a low dimension feature vector". Moreover, the DBNFs showed a relative improvement with an average of 15.4% in comparison to the shape features and the shape features showed a relative improvement with an average of 20.4% in comparison to the ROI features over the test data.

关键词： lip-reading feature extraction deep auto-encoder DBNF

来源：评论

学校读者我要写书评

暂无评论

HRTF Representation with Convolutional auto-encoder 26th

HRTF Representation with Convolutional Auto-encoder

引用

26th International Conference on MultiMedia Modeling (MMM)

作者： Chen, Wei Hu, Ruimin Wang, Xiaochen Li, Dengshi Wuhan Univ Natl Engn Res Ctr Multimedia Software Sch Comp Sci Wuhan 430072 Peoples R China Wuhan Univ Hubei Key Lab Multimedia & Network Commun Engn Wuhan 430072 Peoples R China Collaborat Innovat Ctr Geospatial Technol Wuhan 430079 Peoples R China Jianghan Univ Sch Math & Comp Sci Wuhan Peoples R China

ISBN: (纸本)9783030377311;9783030377304

The head-related transfer function (HRTF) can be considered as some kind of filter that describes how a sound from an arbitrary spatial direction transfers to the listener's eardrums. HRTF can be used to synthesize vivid virtual 3D sound that seems to come from any spatial location, which makes it play an important role in the 3D audio technology. However, the complexity and variation of auditory cues inherent in HRTF make it difficult to set up an accurate mathematical model with the conventional methods. In this paper, we put forward an HRTF representation modeling based on convolutional auto-encoder (CAE), which is some type of auto-encoder that contains convolutional layers in the encoder part and deconvolution layers in the decoder part. The experimental evaluation on the ARI HRTF database shows that the proposed model provides very good results on dimensionality reduction of HRTF.

关键词： HRTF Representation Convolutional auto-encoder deep auto-encoder Denoising auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Risk Measurement of the Financial Credit Industry Driven by Data: Based on DAE-LSTM deep Learning Algorithm

引用

JOURNAL OF GLOBAL INFORMATION MANAGEMENT 2022年第11期30卷

作者： Li, Guizhi Wang, Xuebiao Bi, Datian Hou, Jiayu Yingkou Inst Technol Yingkou Peoples R China Dongbei Univ Finance & Econ Dalian Peoples R China Jilin Univ Changchun Peoples R China

The risk measurement of the financial credit industry is an important research issue in the field of financial risk assessment. The design of a financial credit risk measurement algorithm can help investors avoid greater risks and obtain higher returns, so as to promote the benign development of financial credit industry. Based on the combined deep learning algorithm, this paper studies the risk measurement of financial and credit industry and proposes a fusion algorithm of deep auto-encoder (DAE) and long short-term memory (LSTM) network. The algorithm recombines the value of fixed features by using the unsupervised mechanism of DAE and extracts non-fixed features for measurement combined with the memory characteristics of LSTM network. The experimental results show that, compared with single generalized regression neural network and LSTM network, the average accuracy of DAE-LSTM algorithm is improved by about 6.49% and 3.25%, respectively, which has a better application effect in credit risk measurement.

关键词： Data Mining deep auto-encoder Financial Credit Industry LSTM

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Graph Edge Convolutional Network for Anomaly Detection 30th

Semi-supervised Graph Edge Convolutional Network for Anomaly...

引用

30th International Conference on Artificial Neural Networks (ICANN)

作者： Lun, Zhicheng Gu, Xiaoyan Fan, Haihui Li, Bo Wang, Weiping Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9783030863623;9783030863616

In recent years, with deep learning development, graph-based deep anomaly detection has attracted more and more researchers' attention due to graph data's strong expression ability. However, at present, graph-based methods mainly focus on node-level anomaly detection, while edge-level anomaly detection is relatively minor. Anomaly detection at the edge level can distinguish the specific edges connected to nodes as detection objects, so its resolution granularity is more detailed than that of the node-based method. Second, the rules of anomalies are challenging to learn. At present, most of the algorithms adopt the unsupervised method to train the model. As a result, the detected result is likely to be noise data. In this paper, we propose a Graph Edge Anomaly Detection model based on a Semi-supervised auto-encoder (GEADS). In this model, we first adjust the traditional mini-batch training strategy to train the model on a large-scale graph. It improves the scalability of the model. Second, we design an edge convolutional neural network layer to realize the fusion of edge neighborhood information. We take the reconstruction error as the evaluation criterion after stacking multiple edge convolutional neural network layers that encode and decode the edges. Third, the few abnormal samples with known labels are utilized to guide the model's parameter optimization process. While ensuring the generalization ability of the model, it also improves the pertinence to specific anomalies. Finally, we show the effectiveness of the proposed algorithm through experiments on two real-world datasets.

关键词： Anomaly detection Neural networks Semi-supervised learning deep auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Graph Convolutional Network Boosted Flow-Frame Prediction For Video Anomaly Detection 48

Spatial-Temporal Graph Convolutional Network Boosted Flow-Fr...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Cheng, Kai Zeng, Xinhua Liu, Yang Zhao, Mengyang Pang, Chengxin Hu, Xing Fudan University Academy for Engineering & Technology Shanghai China Shanghai University of Electric Power School of Eie Shanghai China University of Shanghai for Science and Technology School of Oece Shanghai China

ISBN: (纸本)9781728163277

Video Anomaly Detection (VAD) is a critical technology for intelligent surveillance systems and remains a challenging task in the signal processing community. An intuitive idea for VAD is to use a two-stream network to learn appearance and motion normality, respectively. However, existing approaches usually design a network architecture for the appearance stream with effort, then apply a similar architecture to the motion stream, ignoring the unique appearance and motion characteristics. In this paper, we propose STGCN-FFP, an unsupervised Spatial-Temporal Graph Convolutional Networks (STGCN) boosted Flow-Frame Prediction model. Specifically, we first design an STGCN-based memory module to extract and memorize normal patterns for optical flow, which is more suitable for learning motion normality. Then, we use a memory-augmented auto-encoder to model normal appearance patterns. Finally, the latent representation of two streams is fused to predict future frames, boosting the model to learn spatial-temporal normality. To our knowledge, STGCN-FFP is the first work applying STGCN to uniquely model the motion normality. Our method performs comparably to the state-of-the-art methods on three benchmarks. © 2023 IEEE.

关键词： deep auto-encoder memory network spatial-temporal graph convolutional network unsupervised learning Video anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A feature reconstruction and SAE model based diagnosis method for multiple mixed faults

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第8期35卷 086130-086130页

作者： Yang, Jing Chen, Jianwen Zhan, Xuan Liu, Chuanshui Yang, Cheng Tianshui Normal Univ Sch Mechatron & Automot Engn Tianshui 741000 Peoples R China Tianshui Normal Univ Engn Res Ctr Integrated Circuit Packaging & Testin Minist Educ Tianshui 741000 Peoples R China

Owing to the merits of automatic feature extraction and depth structure, intelligent fault diagnosis based on deep neural networks has become a great concern. However, the non-fault state monitoring data volume of actual industrial machinery is rich, whereas the fault state data volume is insufficient and weak. Furthermore, achieving multiple mixed-fault diagnoses using skewed data distributions is extremely difficult. A feature reconstruction and sparse auto-encoder (AE) model-based diagnosis method for multiple mixed faults is proposed in this study to bridge these gaps. Such a feature reconstruction algorithm is designed and employed to address the following issues: (1) expensive computing resulting from the long sequential features of vibration monitoring data and (2) the extraction problem caused by the submersion of scarce data features. Furthermore, an adaptive loss function was formulated, and a deep AE network was constructed to identify the health status and determine the fault level. Diagnoses of artificial and real faults verify the availability and superiority of the proposed scheme, demonstrating the adaptability and robustness of these hyperparameters.

关键词： data scarcity feature reconstruction deep auto-encoder multiple fault mixed faults intelligent diagnosis

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：