2020 25th International Conference on Pattern Recognition (ICPR)最新文献_第8页

GAN-Based Image Deblurring Using DCT Discriminator 基于DCT鉴别器的gan图像去模糊

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412584

Hiroki Tomosada, Takahiro Kudo, Takanori Fujisawa, M. Ikehara

引用次数: 7

Estimating Static and Dynamic Brain Networks by Kulback-Leibler Divergence from fMRI Data 基于fMRI数据的Kulback-Leibler散度估计静态和动态脑网络

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9413047

Gonul Gunal Degirmendereli, F. Yarman-Vural

引用次数: 0

Energy Minimum Regularization in Continual Learning 持续学习中的能量最小正则化

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412744

Xiaobin Li, Lianlei Shan, Minglong Li, Weiqiang Wang

引用次数: 0

Quasibinary Classifier for Images with Zero and Multiple Labels 零标签和多标签图像的准二分类器

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412933

Shuai Liao, E. Gavves, Changyong Oh, Cees G. M. Snoek

{"title":"Quasibinary Classifier for Images with Zero and Multiple Labels","authors":"Shuai Liao, E. Gavves, Changyong Oh, Cees G. M. Snoek","doi":"10.1109/ICPR48806.2021.9412933","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9412933","url":null,"abstract":"The softmax and binary classifier are commonly preferred for image classification applications. However, as softmax is specifically designed for categorical classification, it assumes each image has just one class label. This limits its applicability for problems where the number of labels does not equal one, most notably zero- and multi-label problems. In these challenging settings, binary classifiers are, in theory, better suited. However, as they ignore the correlation between classes, they are not as accurate and scalable in practice. In this paper, we start from the observation that the only difference between binary and softmax classifiers is their normalization function. Specifically, while the binary classifier self-normalizes its score, the softmax classifier combines the scores from all classes before normalisation. On the basis of this observation we introduce a normalization function that is learnable, constant, and shared between classes and data points. By doing so, we arrive at a new type of binary classifier that we coin quasibinary classifier. We show in a variety of image classification settings, and on several datasets, that quasibinary classifiers are considerably better in classification settings where regular binary and softmax classifiers suffer, including zero-label and multi-label classification. What is more, we show that quasibinary classifiers yield well-calibrated probabilities allowing for direct and reliable comparisons, not only between classes but also between data points.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"100 1","pages":"8743-8750"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83350686","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

An Efficient Empirical Solver for Localized Multiple Kernel Learning via DNNs 基于dnn的局部多核学习的高效经验求解器

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9411974

Ziming Zhang

引用次数: 1

Information Graphic Summarization using a Collection of Multimodal Deep Neural Networks 使用多模态深度神经网络集合的信息图形总结

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412146

Edward J. Kim, Connor Onweller, Kathleen F. McCoy

引用次数: 6

2D Discrete Mirror Transform for Image Non-Linear Approximation 二维离散镜像变换用于图像非线性逼近

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412019

Alessandro Gnutti, Fabrizio Guerrini, R. Leonardi

{"title":"2D Discrete Mirror Transform for Image Non-Linear Approximation","authors":"Alessandro Gnutti, Fabrizio Guerrini, R. Leonardi","doi":"10.1109/ICPR48806.2021.9412019","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9412019","url":null,"abstract":"In this paper, a new 2D transform named Discrete Mirror Transform (DMT) is presented. The DMT is computed by decomposing a signal into its even and odd parts around an optimal location in a given direction so that the signal energy is maximally split between the two components. After minimizing the information required to regenerate the original signal by removing redundant structures, the process is iterated leading the signal energy to distribute into a continuously smaller set of coefficients. The DMT can be displayed as a binary tree, where each node represents the single (even or odd) signal derived from the decomposition in the previous level. An optimized version of the DMT (ODMT) is also introduced, by exploiting the possibility to choose different directions at which performing the decomposition. Experimental simulations have been carried out in order to test the sparsity properties of the DMT and ODMT when applied on images: referring to both transforms, the results show a superior performance with respect to the popular Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) in terms of non-linear approximation.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"23 1","pages":"9311-9317"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87298266","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

Multi-modal Contextual Graph Neural Network for Text Visual Question Answering 文本视觉问答的多模态上下文图神经网络

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412891

Yaoyuan Liang, Xin Wang, Xuguang Duan, Wenwu Zhu

{"title":"Multi-modal Contextual Graph Neural Network for Text Visual Question Answering","authors":"Yaoyuan Liang, Xin Wang, Xuguang Duan, Wenwu Zhu","doi":"10.1109/ICPR48806.2021.9412891","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9412891","url":null,"abstract":"Text visual question answering (TextVQA) targets at answering the question related to texts appearing in the given images, posing more challenges than VQA by requiring a deeper recognition and understanding of various shapes of human-readable scene texts as well as their meanings in different contexts. Existing works on TextVQA suffer from two weaknesses: i) scene texts and non-textual objects are processed separately and independently without considering their mutual interactions during the question understanding and answering process, ii) scene texts are encoded only through word embeddings without taking the corresponding visual appearance features as well as their potential relationships with other non-textual objects in the images into account. To overcome the weakness of existing works, we propose a novel multi-modal contextual graph neural network (MCG) model for TextVQA. The proposed MCG model can capture the relationships between visual features of scene texts and non-textual objects in the given images as well as utilize richer sources of multi-modal features to improve the model performance. In particular, we encode the scene texts into richer features containing textual, visual and positional features, then model the visual relations between scene texts and non-textual objects through a contextual graph neural network. Our extensive experiments on real-world dataset demonstrate the advantages of the proposed MCG model over baseline approaches.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"79 1","pages":"3491-3498"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84718296","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: 4

DenseRecognition of Spoken Languages 口语的密集识别

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412413

Jaybrata Chakraborty, Bappaditya Chakraborty, U. Bhattacharya

{"title":"DenseRecognition of Spoken Languages","authors":"Jaybrata Chakraborty, Bappaditya Chakraborty, U. Bhattacharya","doi":"10.1109/ICPR48806.2021.9412413","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9412413","url":null,"abstract":"In the present study, we have considered a large number (27) of Indian languages for recognition from their speech signals of different sources. A dense convolutional network architecture (DenseNet) has been used for this classification task. Dynamic elimination of low energy frames from the input speech signal has been considered as a preprocessing operation. Mel-spectrogram of pre-processed speech signal is fed as input to the DenseNet architecture. Language recognition performance of this architecture has been compared with that of several state-of-the-art deep architectures which include a convolutional neural network (CNN), ResNet, CNN-BLSTM and DenseNet-BLSTM hybrid architectures. Additionally, we obtained recognition performances of a stacked BLSTM architecture fed with different sets of handcrafted features for comparison purpose. Simulations for both speaker independent and speaker dependent scenarios have been performed on two different standard datasets which include (i) IITKGP-MLILSC dataset of news clips in 27 different Indian languages and (ii) Linguistic Data Consortium (LDC) dataset of telephonic conversations in 5 different Indian languages. In each case, recognition performance of the DenseNet architecture along with Mel-spectrogram features has been found to be significantly better than all other frameworks implemented in this study.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"78 1","pages":"9674-9681"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85264668","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: 2

3D Point Cloud Registration Based on Cascaded Mutual Information Attention Network 基于级联互信息关注网络的三维点云配准

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9413083

Xiang Pan, Xiaoyi Ji, Sisi Cheng

引用次数: 1