Int. J. Wavelets Multiresolution Inf. Process.最新文献_第7页

Free metaplectic wavelet transform in L2(ℝn) L2(l_ (n))中的自由偏小波变换

Int. J. Wavelets Multiresolution Inf. Process. Pub Date : 2022-03-07 DOI: 10.1142/s0219691322500059

F. Shah, Huzaifa L. Qadri, Waseem Z. Lone

引用次数: 2

Duality for matrix-valued wave packet frames in L2(ℝd, ℂs×r) L2(d, s×r)中矩阵值波包帧的对偶性

Int. J. Wavelets Multiresolution Inf. Process. Pub Date : 2022-03-07 DOI: 10.1142/s0219691322500072

L. K. Vashisht

引用次数: 0

Adaptive compensation visual odometry in dynamic scenarios 动态场景下的自适应补偿视觉里程计

Int. J. Wavelets Multiresolution Inf. Process. Pub Date : 2022-03-07 DOI: 10.1142/s0219691322500035

Yaming Wang, Wenqing Huang, Zhengheng Xu, Meiliang Wang

引用次数: 1

Near Riesz and Besselian Hilbert-Schmidt operator sequences 近Riesz和Besselian Hilbert-Schmidt算子序列

Int. J. Wavelets Multiresolution Inf. Process. Pub Date : 2022-03-07 DOI: 10.1142/s0219691322500060

Xiao-Li Zhang, Yun‐Zhang Li

引用次数: 0

Erratum: Multi-view feature selection via sparse tensor regression 勘误:通过稀疏张量回归的多视图特征选择

Int. J. Wavelets Multiresolution Inf. Process. Pub Date : 2022-02-24 DOI: 10.1142/s0219691322920011

Haoliang Yuan, Sio-Long Lo, Ming Yin, Yong Liang

引用次数: 0

Tight Wavelet Filter Banks with Prescribed Directions 规定方向的紧小波滤波器组

Int. J. Wavelets Multiresolution Inf. Process. Pub Date : 2022-02-20 DOI: 10.1142/s0219691322500084

Youngmi Hur

引用次数: 0

WAD-CMSN: Wasserstein Distance based Cross-Modal Semantic Network for Zero-Shot Sketch-Based Image Retrieval WAD-CMSN:基于Wasserstein距离的跨模态语义网络，用于基于零拍摄草图的图像检索

Int. J. Wavelets Multiresolution Inf. Process. Pub Date : 2022-02-11 DOI: 10.1142/s0219691322500540

Guanglong Xu, Zhensheng Hu, Jia Cai

{"title":"WAD-CMSN: Wasserstein Distance based Cross-Modal Semantic Network for Zero-Shot Sketch-Based Image Retrieval","authors":"Guanglong Xu, Zhensheng Hu, Jia Cai","doi":"10.1142/s0219691322500540","DOIUrl":"https://doi.org/10.1142/s0219691322500540","url":null,"abstract":"Zero-shot sketch-based image retrieval (ZSSBIR), as a popular studied branch of computer vision, attracts wide attention recently. Unlike sketch-based image retrieval (SBIR), the main aim of ZSSBIR is to retrieve natural images given free hand-drawn sketches that may not appear during training. Previous approaches used semantic aligned sketch-image pairs or utilized memory expensive fusion layer for projecting the visual information to a low dimensional subspace, which ignores the significant heterogeneous cross-domain discrepancy between highly abstract sketch and relevant image. This may yield poor performance in the training phase. To tackle this issue and overcome this drawback, we propose a Wasserstein distance based cross-modal semantic network (WAD-CMSN) for ZSSBIR. Specifically, it first projects the visual information of each branch (sketch, image) to a common low dimensional semantic subspace via Wasserstein distance in an adversarial training manner. Furthermore, identity matching loss is employed to select useful features, which can not only capture complete semantic knowledge, but also alleviate the over-fitting phenomenon caused by the WAD-CMSN model. Experimental results on the challenging Sketchy (Extended) and TU-Berlin (Extended) datasets indicate the effectiveness of the proposed WAD-CMSN model over several competitors.","PeriodicalId":158567,"journal":{"name":"Int. J. Wavelets Multiresolution Inf. Process.","volume":"1103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116052433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Frequency domain of weakly translation invariant frame MRAs 弱平移不变帧mra的频域

Int. J. Wavelets Multiresolution Inf. Process. Pub Date : 2021-12-15 DOI: 10.1142/s0219691321500594

Zhihua Zhang

引用次数: 0

A note on the applications of one primary function in deep neural networks 关于一个主要函数在深度神经网络中的应用的说明

Int. J. Wavelets Multiresolution Inf. Process. Pub Date : 2021-12-04 DOI: 10.1142/s0219691321500582

Hengjie Chen, Zhong Li

{"title":"A note on the applications of one primary function in deep neural networks","authors":"Hengjie Chen, Zhong Li","doi":"10.1142/s0219691321500582","DOIUrl":"https://doi.org/10.1142/s0219691321500582","url":null,"abstract":"By applying fundamental mathematical knowledge, this paper proves that the function [Formula: see text] is an integer no less than [Formula: see text] has the property that the difference between the function value of middle point of arbitrarily two adjacent equidistant distribution nodes on [Formula: see text] and the mean of function values of these two nodes is a constant depending only on the number of nodes if and only if [Formula: see text] By them, we establish an important result about deep neural networks that the function [Formula: see text] can be interpolated by a deep Rectified Linear Unit (ReLU) network with depth [Formula: see text] on the equidistant distribution nodes in interval [Formula: see text] and the error of approximation is [Formula: see text] Then based on the main result that has just been proven and the Chebyshev orthogonal polynomials, we construct a deep network and give the error estimate of approximation to polynomials and continuous functions, respectively. In addition, this paper constructs one deep network with local sparse connections, shared weights and activation function [Formula: see text] and discusses its density and complexity.","PeriodicalId":158567,"journal":{"name":"Int. J. Wavelets Multiresolution Inf. Process.","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134316912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Wavelet neural networks functional approximation and application 小波神经网络函数逼近及其应用

Int. J. Wavelets Multiresolution Inf. Process. Pub Date : 2021-11-29 DOI: 10.1142/s0219691321500600

Anis Zeglaoui, A. Mabrouk, O. Kravchenko

引用次数: 1