2017 30th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T)最新文献

A Review of Texture Classification Methods and Databases 纹理分类方法及数据库研究进展

2017 30th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T) Pub Date : 2017-10-01 DOI: 10.1109/SIBGRAPI-T.2017.10

P. Cavalin, Luiz Oliveira

引用次数: 30

Everything You Wanted to Know about Deep Learning for Computer Vision but Were Afraid to Ask 你想知道的关于计算机视觉深度学习但又不敢问的一切

2017 30th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T) Pub Date : 2017-10-01 DOI: 10.1109/SIBGRAPI-T.2017.12

M. Ponti, Leo Sampaio Ferraz Ribeiro, T. S. Nazaré, Tu Bui, J. Collomosse

{"title":"Everything You Wanted to Know about Deep Learning for Computer Vision but Were Afraid to Ask","authors":"M. Ponti, Leo Sampaio Ferraz Ribeiro, T. S. Nazaré, Tu Bui, J. Collomosse","doi":"10.1109/SIBGRAPI-T.2017.12","DOIUrl":"https://doi.org/10.1109/SIBGRAPI-T.2017.12","url":null,"abstract":"Deep Learning methods are currently the state-of-the-art in many Computer Vision and Image Processing problems, in particular image classification. After years of intensive investigation, a few models matured and became important tools, including Convolutional Neural Networks (CNNs), Siamese and Triplet Networks, Auto-Encoders (AEs) and Generative Adversarial Networks (GANs). The field is fast-paced and there is a lot of terminologies to catch up for those who want to adventure in Deep Learning waters. This paper has the objective to introduce the most fundamental concepts of Deep Learning for Computer Vision in particular CNNs, AEs and GANs, including architectures, inner workings and optimization. We offer an updated description of the theoretical and practical knowledge of working with those models. After that, we describe Siamese and Triplet Networks, not often covered in tutorial papers, as well as review the literature on recent and exciting topics such as visual stylization, pixel-wise prediction and video processing. Finally, we discuss the limitations of Deep Learning for Computer Vision.","PeriodicalId":373912,"journal":{"name":"2017 30th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125984910","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: 101

Geometric Data Analysis Based on Manifold Learning with Applications for Image Understanding 基于流形学习的几何数据分析及其在图像理解中的应用

2017 30th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T) Pub Date : 2017-10-01 DOI: 10.1109/SIBGRAPI-T.2017.9

G. F. Miranda, C. Thomaz, G. Giraldi

{"title":"Geometric Data Analysis Based on Manifold Learning with Applications for Image Understanding","authors":"G. F. Miranda, C. Thomaz, G. Giraldi","doi":"10.1109/SIBGRAPI-T.2017.9","DOIUrl":"https://doi.org/10.1109/SIBGRAPI-T.2017.9","url":null,"abstract":"Nowadays, pattern recognition, computer vision, signal processing and medical image analysis, require the managing of large amount of multidimensional image databases, possibly sampled from nonlinear manifolds. The complex tasks involved in the analysis of such massive data lead to a strong demand for nonlinear methods for dimensionality reduction to achieve efficient representation for information extraction. In this avenue, manifold learning has been applied to embed nonlinear image data in lower dimensional spaces for subsequent analysis. The result allows a geometric interpretation of image spaces with relevant consequences for data topology, computation of image similarity, discriminant analysis/classification tasks and, more recently, for deep learning issues. In this paper, we firstly review Riemannian manifolds that compose the mathematical background in this field. Such background offers the support to set up a data model that embeds usual linear subspace learning and discriminant analysis results in local structures built from samples drawn from some unknown distribution. Afterwards, we discuss topological issues in data preparation for manifold learning algorithms as well as the determination of manifold dimension. Then, we survey dimensionality reduction techniques with particular attention to Riemannian manifold learning. Besides, we discuss the application of concepts in discrete and polyhedral geometry for synthesis and data clustering over the recovered Riemannian manifold with emphasis in face images in the computational experiments. Next, we discuss promising perspectives of manifold learning and related topics for image analysis, classification and relationships with deep learning methods. Specifically, we discuss the application of foliation theory, discriminant analysis and kernel methods in curved spaces. Besides, we take differential geometry in manifolds as a paradigm to discuss deep generative models and metric learning algorithms.","PeriodicalId":373912,"journal":{"name":"2017 30th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126404772","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: 7

Face Analysis in the Wild 野外人脸分析

2017 30th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T) Pub Date : 2017-10-01 DOI: 10.1109/SIBGRAPI-T.2017.11

F. H. B. Zavan, Nathaly Gasparin, Julio Cesar Batista, Luan P. e Silva, Vítor Albiero, O. Bellon, Luciano Silva

{"title":"Face Analysis in the Wild","authors":"F. H. B. Zavan, Nathaly Gasparin, Julio Cesar Batista, Luan P. e Silva, Vítor Albiero, O. Bellon, Luciano Silva","doi":"10.1109/SIBGRAPI-T.2017.11","DOIUrl":"https://doi.org/10.1109/SIBGRAPI-T.2017.11","url":null,"abstract":"With the global demand for extra security systems, and the growing of human-machine interaction, facial analysis in unconstrained environments (in the wild) became a hot-topic in recent computer vision research.Unconstrained environments include surveillance footage, social media photos and live broadcasts.This type of images and videos include no control over illumination, position, size, occlusion, and facial expressions. Successful facial processing methods for controlled scenarios are unable to pledge with challenging circumstances. Consequently, methods tailored for handling those situations are indispensable for the face analysis research progress. This work presents a comprehensive review of state-of-the-art methods, drawing attention to the complications derived from in the wild scenarios and the behavior differences when applied to the controlled images.The main topics to be covered are: (1) face detection; (2) facial image quality; (3) head pose estimation; (4) face alignment; (5) 3D face reconstruction; (6) gender and age estimation; (7) facial expressions and emotions; and (8) face recognition. Finally, available code and applications for in the wild face analysis are presented,followed by a discussion on future directions.","PeriodicalId":373912,"journal":{"name":"2017 30th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T)","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122053697","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