检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Roy, Swalpa Kumar Paoletti, Mercedes E. Haut, Juan M. Dubey, Shiv Ram Kar, Purbayan Plaza, Antonio Chaudhuri, Bidyut B. The Computer Science and Engineering Alipurduar Government Engineering and Management College 736206 India The Hyperspectral Computing Laboratory Department of Technology of Computers and Communications University of Extremadura Cáceres10003 Spain The Computer Vision and Biometrics Lab Indian Institute of Information Technology Prayagraj Uttar Pradesh Allahabad211015 India The Media Analysis Group Sony Research India Private Limited Karnataka Bangalore560103 India The Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India

Convolutional neural networks (CNNs) are trained using stochastic gradient descent (SGD)-based optimizers. Recently, the adaptive moment estimation (Adam) optimizer has become very popular due to its adaptive momentum, which tackles the dying gradient problem of SGD. Nevertheless, existing optimizers are still unable to exploit the optimization curvature information efficiently. This paper proposes a new AngularGrad optimizer that considers the behavior of the direction/angle of consecutive gradients. This is the first attempt in the literature to exploit the gradient angular information apart from its magnitude. The proposed AngularGrad generates a score to control the step size based on the gradient angular information of previous iterations. Thus, the optimization steps become smoother as a more accurate step size of immediate past gradients is captured through the angular information. Two variants of AngularGrad are developed based on the use of Tangent or Cosine functions for computing the gradient angular information. Theoretically, AngularGrad exhibits the same regret bound as Adam for convergence purposes. Nevertheless, extensive experiments conducted on benchmark data sets against state-of-the-art methods reveal a superior performance of AngularGrad. Source code: https://***/mhaut/AngularGrad. Copyright © 2021, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Exploring emotion features and fusion strategies for audio-video emotion recognition

arXiv

引用

arXiv 2020年

作者： Zhou, Hengshun Meng, Debin Zhang, Yuanyuan Peng, Xiaojiang Du, Jun Wang, Kai Qiao, Yu University of Science and Technology of China China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

The audio-video based emotion recognition aims to classify a given video into basic emotions. In this paper, we describe our approaches in EmotiW 2019, which mainly explores emotion features and feature fusion strategies for audio and visual modality. For emotion features, we explore audio feature with both speech-spectrogram and Log Mel-spectrogram and evaluate several facial features with different CNN models and different emotion pretrained strategies. For fusion strategies, we explore intra-modal and cross-modal fusion methods, such as designing attention mechanisms to highlights important emotion feature, exploring feature concatenation and factorized bilinear pooling (FBP) for cross-modal feature fusion. With careful evaluation, we obtain 65.5% on the AFEW validation set and 62.48% on the test set and rank second in the challenge. © 2020, CC BY.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Detach and Enhance: Learning Disentangled Cross-modal Latent Representation for Efficient Face-Voice Association and Matching

Detach and Enhance: Learning Disentangled Cross-modal Latent...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Zhenning Yu Xin Liu Yiu-Ming Cheung Minghang Zhu Xing Xu Nannan Wang Taihao Li Dept. of Comput. Sci. & Fujian Key Lab. of Big Data Intelligence and Security Huaqiao University Xiamen China Zhejiang Lab Hangzhou China Dept. of Comput. Sci. and Institute of Research and Continuing Education HK Baptist University Hong Kong SAR China Xiamen Key Lab. of Computer Vision and Pattern Recognition Huaqiao University Xiamen China Dept. of Computer Sci. and Eng. University of Electronic Science and Technology of China Chengdu China State Key Lab. of Integrated Services Networks & School of Telecommun. Eng. Xidian University Xi’an China

Many researches in cognitive science have shown that humans often perform face-voice association for various perception tasks, and some recent data mining works have been designed in emulating such ability intelligently. Nevertheless, most methods often suffer from the degraded performance when there exist semantically irrelevant interference factors across different modalities. To alleviate this concern, this paper presents an efficient Disentangled Cross-modal Latent Representation (DCLR) method to adaptively detach the discriminative feature attributes and enhance the face-voice association. To be specific, the proposed DCLR framework consists of two-stage cross-modal disentangling process. First, the former stage employs the supervised contrastive learning to push the representations of face-voice data from the same person closer while pulling those representations of different person away. Then, the latter stage freezes all the parameters of the former stage, and further innovates a multi-layer orthogonal decoupling scheme to learn the disentangled latent representations, while filtering out the modality-dependent irrelevant factors. Besides, the cross-modal reconstruction loss is further utilized to narrow down the semantic gap between heterogeneous feature expressions. Through the joint exploitation of the above, the proposed framework can well associate the face-voice data to benefit various kinds of cross-modal perception tasks. Extensive experiments verify the superiorities of the proposed face-voice association framework and show its competitive performances.

关键词： Representation learning Filtering Semantics Interference Data models Cognitive science Data mining

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Natural Image Matting by Refining Low-resolution Alpha Mattes

引用

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 2025年 PP卷 PP页

作者： Xianmin Ye Yihui Liang Mian Tan Fujian Feng Lin Wang Han Huang College of Data Science and Information Engineering Guizhou Minzu University Guiyang China Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China School of Computer Science Zhongshan Institute University of Electronic Science and Technology of China Zhongshan China Guizhou Key Laboratory of Pattern Recognition and Intelligent System and the College of Data Science and Information Engineering Guizhou Minzu University Guiyang China School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot (SCUT) MOE of China Guangzhou China Guangdong Engineering Center for Large Model and GenAI Technology Guangzhou China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

High-resolution natural image matting plays an important role in image editing, film-making and remote sensing due to its ability of accurately extract the foreground from a natural background. However, due to the complexity brought about by the proliferation of resolution, the existing image matting methods cannot obtain high-quality alpha mattes on high-resolution images in reasonable time. To overcome this challenge, we introduce a high-resolution image matting framework based on alpha matte refinement from low-resolution to high-resolution (HRIMF-AMR). The proposed framework transforms the complex high-resolution image matting problem into low-resolution image matting problem and high-resolution alpha matte refinement problem. While the first problem is solved by adopting an existing image matting method, the latter is addressed by applying the Detail Difference Feature Extractor (DDFE) designed as a part of our work. The DDFE extracts detail difference features from high-resolution images by measuring the image feature difference between high-resolution images and low-resolution images. The low-resolution alpha matte is refined according to the extracted detail difference feature, providing the high-resolution alpha matte. In addition, the Matte Detail Resolution Difference (MDRD) loss is introduced to train the DDFE, which imposes an additional constraint on the extraction of detail difference features with mattes. Experimental results show that integrating HRIMF-AMR significantly enhances the performance of existing matting methods on high-resolution images of Transparent-460 and Alphamatting. Project page: https://***/yexianmin/HRAMR-Matting.

关键词： Feature extraction Image resolution Image color analysis Optimization Remote sensing Clustering algorithms Accuracy Visualization Transforms Training

来源：评论

学校读者我要写书评

暂无评论

Exploring Multi-Scale Feature Propagation and Communication for Image Super Resolution

arXiv

引用

arXiv 2020年

作者： Feng, Ruicheng Guan, Weipeng Qiao, Yu Dong, Chao Shenzhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Acedamy of Sciences China Chinese University of Hong Kong Hong Kong

Multi-scale techniques have achieved great success in a wide range of computer vision tasks. However, while this technique is incorporated in existing works, there still lacks a comprehensive investigation on variants of multi-scale convolution in image super resolution. In this work, we present a unified formulation over widely-used multi-scale structures. With this framework, we systematically explore the two factors of multi-scale convolution – feature propagation and cross-scale communication. Based on the investigation, we propose a generic and efficient multi-scale convolution unit – Multi-Scale cross-Scale Share-weights convolution (MS3-Conv). Extensive experiments demonstrate that the proposed MS3-Conv can achieve better SR performance than the standard convolution with less parameters and computational cost. Beyond quantitative analysis, we comprehensively study the visual quality, which show that MS3-Conv behave better to recover high-frequency details. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Synchronization of Multi-Weighted Complex Networks with Mixed Variable Delays and Uncertainties Via Impulsive Pinning Control

SSRN

引用

SSRN 2023年

作者： Fan, Hongguang Shi, Kaibo Wen, Hui Zhao, Yi College of Computer Chengdu University Chengdu610106 China Key Laboratory of Pattern Recognition and Intelligent Information Processing Institutions of Higher Education of Sichuan Province Chengdu University Chengdu610106 China School of Electronic Information and Electrical Engineering Chengdu University Chengdu610106 China New Engineering Industry College Putian University Fujian Putian351100 China Engineering Research Center of Big Data Application in Private Health Medicine Fujian Province University Fujian Putian351100 China College of Mathematical and Statistical Shenzhen University Shenzhen518060 China

In this paper, we examine the synchronization problem in nonlinearly-coupled multi-weighted complex networks that contain uncertainties and varying delays. The complexities of these networks arise from the presence of both internal time-varying delays and multiple coupling time-varying delays. To address this challenge, we employ impulsive pinning control schemes and incorporate the impulsive pinning control ratio in the construction of the Lyapunov function, which allows us to determine the optimal number of pinned nodes at each pulse instant. Our analysis, based on stability theory, provides synchronization criteria that are strongly dependent on the multi-weights and time delays present in the network. Finally, we present numerical simulations of a delayed complex network to demonstrate the validity and efficacy of our derived theoretical results. © 2023, The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Attention in Attention: Modeling Context Correlation for Efficient Video Classification

arXiv

引用

arXiv 2022年

作者： Hao, Yanbin Wang, Shuo Cao, Pei Gao, Xinjian Xu, Tong Wu, Jinmeng He, Xiangnan The CCCD Key Lab of Ministry of Culture and Tourism School of Data Science School of Information Science and Technology University of Science and Technology of China Anhui 230026 China The Wuhan Research Institute of Posts and Telecommunications Hubei Wuhan430205 China The School of Computer Science and Information Engineering School of Artificial Intelligence Hefei University of Technology Anhui 230009 China The School of Data Science School of Computer Science and Technology University of Science and Technology of China Anhui 230026 China The Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Hubei Wuhan430070 China

Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts. However, the current research on video attention generally focuses on adopting a specific aspect of contexts (e.g., channel, spatial/temporal, or global context) to refine the features and neglects their underlying correlation when computing attentions. This leads to incomplete context utilization and hence bears the weakness of limited performance improvement. To tackle the problem, this paper proposes an efficient attention-in-attention (AIA) method for element-wise feature refinement, which investigates the feasibility of inserting the channel context into the spatio-temporal attention learning module, referred to as CinST, and also its reverse variant, referred to as STinC. Specifically, we instantiate the video feature contexts as dynamics aggregated along a specific axis with global average and max pooling operations. The workflow of an AIA module is that the first attention block uses one kind of context information to guide the gating weights calculation of the second attention that targets at the other context. Moreover, all the computational operations in attention units act on the pooled dimension, which results in quite few computational cost increase ( Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Fast and Error-Bounded Space-Variant Bilateral Filtering

引用

Journal of computer Science & Technology 2019年第3期34卷 550-568页

作者： Meng-Ke Yuan Long-Quan Dai Dong-Ming Yan Li-Qiang Zhang Jun Xiao Xiao-Peng Zhang National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China School of Computer Science and Technology Nanjing University of Science and TechnologyNanjing 210094China State Key Laboratory of Remote Sensing Science School of GeographyBeijing Normal UniversityBeijing 100875China

The traditional space-invariant isotropic kernel utilized by a bilateral filter(BF)frequently leads to blurry edges and gradient reversal artifacts due to tlie existence of a large amount of outliers in the local averaging ***,the efficient and accurate cstiinatioii of space-variant k(4rnels which adapt to image structures,and the fast realization of the corresponding space-variant bilateral filtering are challenging *** address these problems,we present a space-variant BF(SVBF).and its linear time and error-bounded acceleration ***,we accurately estimate spacevariant,anisotropic kernels that vary with image structures in linear time through structure tensor and mininnini spanning ***,we perform SVBF in linear time using two error-bounded approximation methods,namely,low-rank tensor approximation via higher-order singular value decomposition and exponential sum *** proposed SVBF can efficiently achieve good edge-preserving *** validate the advantages of the proposed filter in applications including:image denoising,image enhancement,and image focus *** results(leinonstrate that our fast and error-bounded SVBF is superior to state-of-the-art methods.

关键词： error-bounded acceleration edge-aware smoothing space-variant bilateral filtering

来源：评论

学校读者我要写书评

暂无评论

Fast Texture Synthesis via Pseudo Optimizer

Fast Texture Synthesis via Pseudo Optimizer

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Wu Shi Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Texture synthesis using deep neural networks can generate high quality and diversified textures. However, it usually requires a heavy optimization process. The following works accelerate the process by using feed-forward networks, but at the cost of scalability. diversity or quality. We propose a new efficient method that aims to simulate the optimization process while retains most of the properties. Our method takes a noise image and the gradients from a descriptor network as inputs, and synthesize a refined image with respect to the target image. The proposed method can synthesize images with better quality and diversity than the other fast synthesis methods do. Moreover, our method trained on a large scale dataset can generalize to synthesize unseen textures.

关键词： Neural networks Training Transforms Scalability Optimization methods Convolution

来源：评论

学校读者我要写书评

暂无评论

Smallbignet: Integrating core and contextual views for video classification

arXiv

引用

arXiv 2020年

作者： Li, Xianhang Wang, Yali Zhou, Zhipeng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Temporal convolution has been widely used for video classification. However, it is performed on spatio-temporal contexts in a limited view, which often weakens its capacity of learning video representation. To alleviate this problem, we propose a concise and novel SmallBig network, with the cooperation of small and big views. For the current time step, the small view branch is used to learn the core semantics, while the big view branch is used to capture the contextual semantics. Unlike traditional temporal convolution, the big view branch can provide the small view branch with the most activated video features from a broader 3D receptive field. Via aggregating such big-view contexts, the small view branch can learn more robust and discriminative spatio-temporal representations for video classification. Furthermore, we propose to share convolution in the small and big view branch, which improves model compactness as well as alleviates overfitting. As a result, our SmallBigNet achieves a comparable model size like 2D CNNs, while boosting accuracy like 3D CNNs. We conduct extensive experiments on the large-scale video benchmarks, e.g., Kinetics400, Something-Something V1 and V2. Our SmallBig network outperforms a number of recent state-of-the-art approaches, in terms of accuracy and/or efficiency. The codes and models will be available on https://***/xhl-video/SmallBigNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

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：