检索结果-内蒙古大学图书馆

RBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax 1

16th European Conference on computer vision, ECCV 2020

作者： Zhang, Xiao Zhao, Rui Qiao, Yu Li, Hongsheng CUHK-SenseTime Joint Lab The Chinese University of Hong Kong Hong Kong SenseTime Research Hong Kong ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9783030585747

ISBN: (纸本)9783030585730

Deep neural networks have achieved remarkable successes in learning feature representations for visual classification. However, deep features learned by the softmax cross-entropy loss generally show excessive intra-class variations. We argue that, because the traditional softmax losses aim to optimize only the relative differences between intra-class and inter-class distances (logits), it cannot obtain representative class prototypes (class weights/centers) to regularize intra-class distances, even when the training is converged. Previous efforts mitigate this problem by introducing auxiliary regularization losses. But these modified losses mainly focus on optimizing intra-class compactness, while ignoring keeping reasonable relations between different class prototypes. These lead to weak models and eventually limit their performance. To address this problem, this paper introduces a novel Radial Basis Function (RBF) distances to replace the commonly used inner products in the softmax loss function, such that it can adaptively assign losses to regularize the intra-class and inter-class distances by reshaping the relative differences, and thus creating more representative prototypes of classes to improve optimization. The proposed RBF-Softmax loss function not only effectively reduces intra-class distances, stabilizes the training behavior, and reserves ideal relations between prototypes, but also significantly improves the testing performance. Experiments on visual recognition benchmarks including MNIST, CIFAR-10/100, and ImageNet demonstrate that the proposed RBF-Softmax achieves better results than cross-entropy and other state-of-the-art classification losses. The code is at https://***/2han9x1a0release/RBF-Softmax. © 2020, Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic recognition of Parkinson's Disease Using Surface Electromyography During Standardized Gait Tests

Automatic Recognition of Parkinson's Disease Using Surface E...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society

作者： Patrick Kugler Christian Jaremenko Johannes Schlachetzki Juergen Winkler Jochen Klucken Bjoern Eskofier Digital Sports Group Pattern Recognition Lab Computer Science Department Friedrich-Alexander

ISBN: (纸本)9781457702150

Diagnosis and severity staging of Parkinsons disease (PD) relies mainly on subjective clinical examination. To better monitor disease progression and therapy success in PD patients, new objective and rater independent parameters are required. Surface electromyography (EMG) during dynamic movements is one possible modality. However, EMG signals are often difficult to understand and interpret clinically. In this study pattern recognition was applied to find suitable parameters to differentiate PD patients from healthy controls. EMG signals were recorded from 5 patients with PD and 5 younger healthy controls, while performing a series of standardized gait tests. Wireless surface electrodes were placed bilaterally on tibialis anterior and gastrocnemius medialis and lateralis. Accelerometers were positioned on both heels and used for step segmentation. Statistical and frequency features were extracted and used to train a Support Vector Machine classifier. Sensitivity and specificity were high at 0.90 using leave-one-subject-out cross-validation. Feature selection revealed kurtosis and mean frequency as best features, with a significant difference in kurtosis (p=0.013). Evaluated on a bigger population, this could lead to objective diagnostic and staging tools for PD.

关键词： Surface Electromyography Parkinson Disease kurtosis Electromyogram Intermediate frequencies Anterior Tibial Muscle Gait Locomotion

来源：评论

学校读者我要写书评

暂无评论

Facial landmark localization based on hierarchical pose regression with cascaded random ferns 13

Facial landmark localization based on hierarchical pose regr...

引用

21st ACM International Conference on Multimedia, MM 2013

作者： Zhang, Zhanpeng Zhang, Wei Liu, Jianzhuang Tang, Xiaoou Shenzhen Key Lab of Computer Vision and Pattern Recognition Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology China Department of Information Engineering Chinese University of Hong Kong Hong Kong Media Lab Huawei Technologies Co. Ltd. China

ISBN: (纸本)9781450324045

The main challenge of facial landmark localization in realworld application is that the large changes of head pose and facial expressions cause substantial image appearance variations. To avoid high dimensional regression in the 3D and 2D facial pose spaces simultaneously, we propose a hierarchical pose regression approach, estimating the head rotation, facial components and landmarks hierarchically. The regression process works in a unified cascaded fern framework. We present generalized gradient boosted ferns (GBFs) for the regression framework, which give better performance than traditional ferns. The framework also achieves real time performance. We verify our method on the latest benchmark datasets. The results show that it outperforms state-of-theart methods in both accuracy and speed. Copyright © 2013 ACM.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Learning to Predict Context-Adaptive Convolution for Semantic Segmentation 16th

Learning to Predict Context-Adaptive Convolution for Semanti...

引用

16th European Conference on computer vision, ECCV 2020

作者： Liu, Jianbo He, Junjun Qiao, Yu Ren, Jimmy S. Li, Hongsheng CUHK-SenseTime Joint Laboratory The Chinese University of Hong Kong Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SenseTime Research Hong Kong

ISBN: (纸本)9783030585945

Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods demonstrate that using global context for re-weighting feature channels can effectively improve the accuracy of semantic segmentation. However, the globally-sharing feature re-weighting vector might not be optimal for regions of different classes in the input image. In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. In CaC-Net, a set of context-adaptive convolution kernels are predicted from the global contextual information in a parameter-efficient manner. When used for convolution with the semantic feature maps, the predicted convolutional kernels can generate the spatially-varying feature weighting factors capturing both global and local contextual information. Comprehensive experimental results show that our CaC-Net achieves superior segmentation performance on three public datasets, PASCAL Context, PASCAL VOC 2012 and ADE20K. © 2020, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Multi-feature canonical correlation analysis for face photo-sketch image retrieval 13

Multi-feature canonical correlation analysis for face photo-...

引用

21st ACM International Conference on Multimedia, MM 2013

作者： Gong, Dihong Li, Zhifeng Liu, Jianzhuang Qiao, Yu Shenzhen Key Lab of Computer Vision and Pattern Recognition Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology China Media Lab Huawei Technologies Co. Ltd. China Department of Information Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781450324045

Automatic face photo-sketch image retrieval has attracted great attention in recent years due to its important applications in real life. The major difficulty in automatic face photo-sketch image retrieval lies in the fact that there exists great discrepancy between the different image modalities (photo and sketch). In order to reduce such discrepancy and improve the performance of automatic face photo-sketch image retrieval, we propose a new framework called multi-feature canonical correlation analysis (MCCA) to effectively address this problem. The MCCA is an extension and improvement of the canonical correlation analysis (CCA) algorithm using multiple features combined with two different random sampling methods in feature space and sample space. In this framework, we first represent each photo or sketch using a patch-based local feature representation scheme, in which histograms of oriented gradients (HOG) and multi-scale local binary pattern (MLBP) serve as the local descriptors. Canonical correlation analysis (CCA) is then performed on a collection of random subspaces to construct an ensemble of classifiers for photo-sketch image retrieval. Extensive experiments on two public-domain face photo-sketch datasets (CUFS and CUFSF) clearly show that the proposed approach obtains a substantial improvement over the state-of-the-art. Copyright © 2013 ACM.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Fast single image dehazing through Edge-Guided Interpolated Filter

Fast single image dehazing through Edge-Guided Interpolated ...

引用

IAPR International Conference on Machine vision Applications (MVA)

作者： Ximei Zhu Ying Li Yu Qiao Shenzhen Key lab of Computer Vision Pattern Recognition The Chinese University of Hong Kong Hong Kong SAR

ISBN: (纸本)9781479982479

Images and videos taken in foggy weather often suffer from low visibility. Recent studies demonstrate the effectiveness of dark channel prior [3] and guided filter [4] based approaches for image dehazing. However, these methods require high computational cost which makes them infeasible for realtime and embedding systems. In this paper, we propose Edge-Guided Interpolated Filter (EGIF) for fast image and video dehazing. The main contributions are twofold. Firstly, we develop Guided Interpolated Filter (GIF) to significantly speed up the estimation of transmission map, which is the most computational cost step in previous methods. Secondly, we utilize edge map as guidance image in GIF to enhance the fine details in dehazed images. Experimental results show that GIF can largely improve the computational efficiency and achieve comparable dehazing performance as previous guided filter based methods. EGIF can further enhance the sharpness of transmission map. Our method can achieve real-time processing for image of size 1024 × 768 with single CPU core (2GHz).

关键词： Image edge detection Interpolation Videos Real-time systems Image restoration computer vision Atmosphere

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution Using Vast-Receptive-Field Attention 17th

Efficient Image Super-Resolution Using Vast-Receptive-Field ...

引用

17th European Conference on computer vision, ECCV 2022

作者： Zhou, Lin Cai, Haoming Gu, Jinjin Li, Zheyuan Liu, Yingqi Chen, Xiangyu Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Shanghai AI Laboratory Shanghai China The University of Sydney Sydney Australia University of Macau Zhuhai China

ISBN: (纸本)9783031250620

The attention mechanism plays a pivotal role in designing advanced super-resolution (SR) networks. In this work, we design an efficient SR network by improving the attention mechanism. We start from a simple pixel attention module and gradually modify it to achieve better super-resolution performance with reduced parameters. The specific approaches include: (1) increasing the receptive field of the attention branch, (2) replacing large dense convolution kernels with depthwise separable convolutions, and (3) introducing pixel normalization. These approaches paint a clear evolutionary roadmap for the design of attention mechanisms. Based on these observations, we propose VapSR, the Vast-receptive-field Pixel attention network. Experiments demonstrate the superior performance of VapSR. VapSR outperforms the present lightweight networks with even fewer parameters. And the light version of VapSR can use only 21.68% and 28.18% parameters of IMDB and RFDN to achieve similar performances to those networks. The code and models are available at https://***/zhoumumu/VapSR. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

EfficientFCN: Holistically-Guided Decoding for Semantic Segmentation 1

引用

16th European Conference on computer vision, ECCV 2020

作者： Liu, Jianbo He, Junjun Zhang, Jiawei Ren, Jimmy S. Li, Hongsheng CUHK-SenseTime Joint Laboratory The Chinese University of Hong Kong Shatin Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SenseTime Research Beijing China

ISBN: (数字)9783030585747

ISBN: (纸本)9783030585730

Both performance and efficiency are important to semantic segmentation. State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN), which adopt dilated convolutions in the backbone networks to extract high-resolution feature maps for achieving high-performance segmentation performance. However, due to many convolution operations are conducted on the high-resolution feature maps, such dilatedFCN-based methods result in large computational complexity and memory consumption. To balance the performance and efficiency, there also exist encoder-decoder structures that gradually recover the spatial information by combining multi-level feature maps from the encoder. However, the performances of existing encoder-decoder methods are far from comparable with the dilatedFCN-based methods. In this paper, we propose the EfficientFCN, whose backbone is a common ImageNet pretrained network without any dilated convolution. A holistically-guided decoder is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. The decoding task is converted to novel codebook generation and codeword assembly task, which takes advantages of the high-level and low-level features from the encoder. Such a framework achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost. Extensive experiments on PASCAL Context, PASCAL VOC, ADE20K validate the effectiveness of the proposed EfficientFCN. © 2020, Springer Nature Switzerland AG.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Communication via eye blinks and eyebrow raises: Video-based human-computer interfaces

引用

Universal Access in the Information Society 2003年第4期2卷 359-373页

作者： Grauman, K. Betke, M. Lombardi, J. Gips, J. Bradski, G.R. Vision Interface Group AI Laboratory Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA02139 United States Computer Science Department Boston University 111 Cummington St BostonMA02215 United States EagleEyes Computer Science Department Boston College Fulton Hall Chestnut HillMA02467 United States Vision Graphics and Pattern Recognition Microcomputer Research Laboratory Intel Corporation SC12-303 2200 Mission College Blvd Santa ClaraCA95054-1537 United States

Two video-based human-computer interaction tools are introduced that can activate a binary switch and issue a selection command. "BlinkLink," as the first tool is called, automatically detects a user's eye blinks and accurately measures their durations. The system is intended to provide an alternate input modality to allow people with severe disabilities to access a computer. Voluntary long blinks trigger mouse clicks, while involuntary short blinks are ignored. The system enables communication using "blink patterns:" sequences of long and short blinks which are interpreted as semiotic messages. The second tool, "EyebrowClicker," automatically detects when a user raises his or her eyebrows and then triggers a mouse click. Both systems can initialize themselves, track the eyes at frame rate, and recover in the event of errors. No special lighting is required. The systems have been tested with interactive games and a spelling program. Results demonstrate overall detection accuracy of 95.6% for BlinkLink and 89.0% for EyebrowClicker. © Springer-Verlag 2003.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

An adaptable inertial sensor fusion-based approach for energy expenditure estimation 15

引用

15th International Conference on Biomedical Engineering, ICBME 2013

作者： Schuldhaus, D. Dorn, S. Leutheuser, H. Tallner, A. Klucken, J. Eskofier, B.M. Digital Sports Group Pattern Recognition Lab Department of Computer Science University Erlangen-Nuremberg Germany Institute of Sport Science and Sport University Erlangen-Nuremberg Germany Department of Molecular Neurology University Hospital Erlangen Germany

ISBN: (纸本)9783319029122

Using multiple inertial sensors for energy expenditure estimation provides a useful tool for the assessment of daily life activities. Due to the high variety of new upcoming sensor types and recommendations for sensor placement to assess physiological human body function, an adaptable inertial sensor fusion-based approach is mandatory. In this paper, two inertial body sensors, consisting of a triaxial accelerometer and a triaxial gyroscope, were placed on hip and ankle. Ten subjects performed two trials of running on a treadmill under three speed levels ([3.2, 4.8, 6.4] km/h). Each sensor source was separately subjected to preprocessing, feature extraction and regression. In the final step, decision level fusion was performed by averaging the predicted results. A mean absolute error of 0.50 MET was achieved against indirect calorimetry. The system allows an easy integration of new sensors without retraining the complete system. This is an advantage over commonly used feature level fusion approaches. © Springer International Publishing Switzerland 2014.

关键词： Sporting goods

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：