{"title":"Feature Selection Based on the Self-calibration of Binocular Camera Extrinsic Parameters","authors":"Siyu Chen, Chao Ma, Chao Liu, Qian Long, Haitao Zhu","doi":"10.1142/s0219691323500303","DOIUrl":"https://doi.org/10.1142/s0219691323500303","url":null,"abstract":"","PeriodicalId":50282,"journal":{"name":"International Journal of Wavelets Multiresolution and Information Processing","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46715530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-20DOI: 10.1142/s0219691323500236
Peng Wang, Jingzhou Chen, Yuntao Qian
Hierarchical classification (HC) assigns each object with multiple labels organized into a hierarchical structure. The existing deep learning-based HC methods usually predict an instance starting from the root node until a leaf node is reached. However, in the real world, images impaired by noise, occlusion, blur, or low resolution may not provide sufficient information for the classification at subordinate levels. To address this issue, we propose a novel Semantic Guided level-category Hybrid Prediction Network (SGHPN) that can jointly perform the level and category prediction in an end-to-end manner. SGHPN comprises two modules: a visual transformer that extracts feature vectors from the input images, and a semantic guided cross-attention module that uses categories word embeddings as queries to guide learning category-specific representations. In order to evaluate the proposed method, we construct two new datasets in which images are at a broad range of quality and thus are labeled to different levels (depths) in the hierarchy according to their individual quality. Experimental results demonstrate the effectiveness of our proposed HC method.
{"title":"Semantic guided level-category hybrid prediction network for hierarchical image classification","authors":"Peng Wang, Jingzhou Chen, Yuntao Qian","doi":"10.1142/s0219691323500236","DOIUrl":"https://doi.org/10.1142/s0219691323500236","url":null,"abstract":"Hierarchical classification (HC) assigns each object with multiple labels organized into a hierarchical structure. The existing deep learning-based HC methods usually predict an instance starting from the root node until a leaf node is reached. However, in the real world, images impaired by noise, occlusion, blur, or low resolution may not provide sufficient information for the classification at subordinate levels. To address this issue, we propose a novel Semantic Guided level-category Hybrid Prediction Network (SGHPN) that can jointly perform the level and category prediction in an end-to-end manner. SGHPN comprises two modules: a visual transformer that extracts feature vectors from the input images, and a semantic guided cross-attention module that uses categories word embeddings as queries to guide learning category-specific representations. In order to evaluate the proposed method, we construct two new datasets in which images are at a broad range of quality and thus are labeled to different levels (depths) in the hierarchy according to their individual quality. Experimental results demonstrate the effectiveness of our proposed HC method.","PeriodicalId":50282,"journal":{"name":"International Journal of Wavelets Multiresolution and Information Processing","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135473922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-05DOI: 10.1142/s0219691323500285
Xinhong Meng, Jinyao Yan, Hailiang Ye, F. Cao
{"title":"Construction and Approximation for a Class of Feedforward Neural Networks with Sigmoidal Function","authors":"Xinhong Meng, Jinyao Yan, Hailiang Ye, F. Cao","doi":"10.1142/s0219691323500285","DOIUrl":"https://doi.org/10.1142/s0219691323500285","url":null,"abstract":"","PeriodicalId":50282,"journal":{"name":"International Journal of Wavelets Multiresolution and Information Processing","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47741424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-28DOI: 10.1142/s0219691323500273
Kuldip Acharya, D. Ghoshal
{"title":"Modified von Neumann Neighborhood and Taxicab Geometry-Based Edge Detection Technique for Infrared Images","authors":"Kuldip Acharya, D. Ghoshal","doi":"10.1142/s0219691323500273","DOIUrl":"https://doi.org/10.1142/s0219691323500273","url":null,"abstract":"","PeriodicalId":50282,"journal":{"name":"International Journal of Wavelets Multiresolution and Information Processing","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44337816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-20DOI: 10.1142/s021969132350025x
Junwei Jin, Zhenhao Qin, Dengxiu Yu, Tiejun Yang, C. L. P. Chen, Yanting Li
{"title":"Relaxed least square regression with ℓ2,1-norm for pattern classification","authors":"Junwei Jin, Zhenhao Qin, Dengxiu Yu, Tiejun Yang, C. L. P. Chen, Yanting Li","doi":"10.1142/s021969132350025x","DOIUrl":"https://doi.org/10.1142/s021969132350025x","url":null,"abstract":"","PeriodicalId":50282,"journal":{"name":"International Journal of Wavelets Multiresolution and Information Processing","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47891265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-20DOI: 10.1142/s0219691323500182
Jia Cai, Tianhua Luo, Zhilong Xiong, Yi Tang
Aquila optimizer (AO) is an efficient meta-heuristic optimization method, which mimics the hunting style of Aquila in nature. However, the AO algorithm may suffer from immature convergence during the exploitation stage. In this paper, two strategies are elegantly employed into conventional AO, such as random opposition-based learning and nonlinear flexible jumping factor, which can efficiently enhance the performance of conventional AO. Experiments on [Formula: see text] benchmark functions and image segmentation demonstrate the effectiveness of the proposed algorithm. Comparison with several state-of-the-art meta-heuristic optimization techniques indicates the efficacy of the developed method.
{"title":"A novel multi-level image segmentation algorithm via random opposition learning-based Aquila optimizer","authors":"Jia Cai, Tianhua Luo, Zhilong Xiong, Yi Tang","doi":"10.1142/s0219691323500182","DOIUrl":"https://doi.org/10.1142/s0219691323500182","url":null,"abstract":"Aquila optimizer (AO) is an efficient meta-heuristic optimization method, which mimics the hunting style of Aquila in nature. However, the AO algorithm may suffer from immature convergence during the exploitation stage. In this paper, two strategies are elegantly employed into conventional AO, such as random opposition-based learning and nonlinear flexible jumping factor, which can efficiently enhance the performance of conventional AO. Experiments on [Formula: see text] benchmark functions and image segmentation demonstrate the effectiveness of the proposed algorithm. Comparison with several state-of-the-art meta-heuristic optimization techniques indicates the efficacy of the developed method.","PeriodicalId":50282,"journal":{"name":"International Journal of Wavelets Multiresolution and Information Processing","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42244603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-20DOI: 10.1142/s0219691323500261
Bhargav
{"title":"Character recognition and digital conversion of degraded document images with removal of typical strikeouts in the kannada language","authors":"Bhargav","doi":"10.1142/s0219691323500261","DOIUrl":"https://doi.org/10.1142/s0219691323500261","url":null,"abstract":"","PeriodicalId":50282,"journal":{"name":"International Journal of Wavelets Multiresolution and Information Processing","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47202591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-20DOI: 10.1142/s0219691323500248
A. Ghali, S. Chouraqui, Amine Khaldi, Med Redouane Kafi
{"title":"Few-Shot Learning CNN Optimized Using Combined 2D-DWT Injection and Evolutionary Optimization Algorithms for Human Face Recognition","authors":"A. Ghali, S. Chouraqui, Amine Khaldi, Med Redouane Kafi","doi":"10.1142/s0219691323500248","DOIUrl":"https://doi.org/10.1142/s0219691323500248","url":null,"abstract":"","PeriodicalId":50282,"journal":{"name":"International Journal of Wavelets Multiresolution and Information Processing","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48449484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-13DOI: 10.1142/s0219691323500224
Divya Jindal, Jyoti, L. K. Vashisht
{"title":"Matrix-valued nonstationary frames associated with the Weyl-Heisenberg group and the extended affine group","authors":"Divya Jindal, Jyoti, L. K. Vashisht","doi":"10.1142/s0219691323500224","DOIUrl":"https://doi.org/10.1142/s0219691323500224","url":null,"abstract":"","PeriodicalId":50282,"journal":{"name":"International Journal of Wavelets Multiresolution and Information Processing","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42176011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-07DOI: 10.1142/s0219691323500212
Jianwen Huang, Xinling Liu, Jinping Jia
. The null space property (NSP), which relies merely on the null space of the sensing matrix column space, has drawn numerous interests in sparse signal recovery. This article studies NSP of the weighted ℓ r − ℓ 1 minimization. Several versions of NSP of the weighted ℓ r − ℓ 1 minimization including the weighted ℓ r − ℓ 1 NSP, the weighted ℓ r − ℓ 1 stable NSP, the weighted ℓ r − ℓ 1 robust NSP, and the ℓ q weighted ℓ r − ℓ 1 NSP for 1 ≤ q ≤ 2, are proposed, as well as the associating considerable results are derived. Under these NSP, sufficient conditions for the recovery of (sparse) signals with the weighted ℓ r − ℓ 1 minimization are established. Furthermore, we show that to some extent, the weighted ℓ r − ℓ 1 stable NSP is weaker than the restricted isometric property (RIP). And the RIP condition we obtained is better than that of Zhou Z. (2022).
{"title":"The Null Space Property of the Weighted ℓr − ℓ1 Minimization","authors":"Jianwen Huang, Xinling Liu, Jinping Jia","doi":"10.1142/s0219691323500212","DOIUrl":"https://doi.org/10.1142/s0219691323500212","url":null,"abstract":". The null space property (NSP), which relies merely on the null space of the sensing matrix column space, has drawn numerous interests in sparse signal recovery. This article studies NSP of the weighted ℓ r − ℓ 1 minimization. Several versions of NSP of the weighted ℓ r − ℓ 1 minimization including the weighted ℓ r − ℓ 1 NSP, the weighted ℓ r − ℓ 1 stable NSP, the weighted ℓ r − ℓ 1 robust NSP, and the ℓ q weighted ℓ r − ℓ 1 NSP for 1 ≤ q ≤ 2, are proposed, as well as the associating considerable results are derived. Under these NSP, sufficient conditions for the recovery of (sparse) signals with the weighted ℓ r − ℓ 1 minimization are established. Furthermore, we show that to some extent, the weighted ℓ r − ℓ 1 stable NSP is weaker than the restricted isometric property (RIP). And the RIP condition we obtained is better than that of Zhou Z. (2022).","PeriodicalId":50282,"journal":{"name":"International Journal of Wavelets Multiresolution and Information Processing","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47011439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：