<\/a>Recent Advances in Pattern Classification Using Optimum-Path Forest<\/div>\n

\n\nJo\u00e3o Paulo Papa<\/span>
\nS\u00e3o Paulo State University, Brazil
\n WEB<\/a>

\n\nJo\u00e3o P. Papa received his Ph.D. in Computer Science from the University of Campinas, SP, Brazil. During 2014-2015, he worked as a visiting scholar at Harvard University, USA. He is an associate professor at the Computer Science Department, S\u00e3o Paulo, State University. He is an Alexander von Humboldt Research Fellow (Germany), an IEEE Senior Member, and a Brazilian representative at the International Association of Pattern Recognition.

\n\n<\/div>\n

ABSTRACT<\/span>
\nMachine learning has been in the spotlight in the past decade, with astonishing results in many research domains. It is a consensus that deeply learnable features are a must-have, but improvements must be made on the classification layer. This talk discusses recent advances in the Optimum-Path Forest, a framework to design graph-based classification methods that cover supervised, unsupervised, and semi-supervised paradigms. Applications to deal with unbalanced datasets, recommender systems, and quantum computing will also be addressed. <\/div>\n

<\/a>What is common between Self-supervised learning and Food Fine-grained recognition?!<\/div>\n

$\"\"$ <\/div>\n

\n\nPetia Radeva<\/span>
\nUniversitat de Barcelona, Spain
\n WEB<\/a>

\n\nProf. Petia Radeva is a Full professor at the Universitat de Barcelona (UB), Head of the Consolidated Research Group \u201cComputer Vision and Machine Learning\u201d at the University of Barcelona (CVMLUB) at UB (www.cvc.uab.es<\/a>) and Senior researcher in Computer Vision Center (www.cvc.uab.es<\/a>). She was PI of UB in 7 European, 3 international and more than 25 national projects devoted to applying Computer Vision and Machine learning for real problems like food intake monitoring (e.g. for patients with kidney transplants and for older people). Petia Radeva is a REA-FET-OPEN vice-chair since 2015 on, and international mentor in the Wild Cards EIT program since 2017.

\n\nShe is an Associate editor in Chief of Pattern Recognition journal (Q1, IP=7.196) and International Journal of Visual Communication and Image Representation (Q2, IP=3.13).

\n\nShe is a Research Manager of the State Agency of Research (Agencia Estatal de Investigaci\u00f3n, AEI) of the Ministry of Science and Innovation of Spain.

\n\nPetia Radeva belongs to the top 2% of the World ranking of scientists with the major impact in the field of TIC according to the citations indicators of the popular ranking of Stanford. Also, she was selected in the first 6% of the ranking of Spanish and foreign most cited female researchers from any field according to the Ranking of CSIC: https:\/\/lnkd.in\/djx2Yz5p<\/a>. Moreover, she was awarded IAPR Fellow since 2015, ICREA Academia assigned to the 30 best scientists in Catalonia for her scientific merits since 2014, received several international awards (\u201cAurora Pons Porrata\u201d of CIARP, Prize \u201cAntonio Caparr\u00f3s\u201d for the best technology transfer of UB, etc).\n\nShe supervised 23 PhD students and published more than 100 SCI journal publications and 250 international chapters and proceedings, her Google scholar h-index is 50 with more than 10000 cites.

\n\n<\/div>\n

ABSTRACT<\/span>
\nDeep Learning (DL) has made remarkable progress in tasks such as face and lip recognition or cancer detection in medical images, achieving super-human performance. However, when it comes to classifying a large number of classes, such as in fine-grained recognition, there is still much room for improvement, especially for groups of classes that are easily confused. Additionally, DL relies on greedy methods that require thousands of annotated images, which can be a time-consuming and tedious process.\nTo address these issues, self-supervised learning offers an efficient way to leverage a large amount of non-annotated images and make DL models more robust and accurate. In this talk, we will present our work on self-supervised learning and fine-grained recognition, highlighting how this approach can help solve complex computer vision problems like food image recognition. Food classes have high variability, significant similarity between classes, and a vast number of unannotated images. By using self-supervised learning and fine-grained recognition, we demonstrate how these challenges can be overcome.<\/div>\n

<\/a>Segmentation of Objects in Engineering and Biomedicine: Techniques and Applications<\/div>\n

$\"Jo\u00e3o$ <\/div>\n

\n\nJo\u00e3o Manuel R. S. Tavares<\/span>
\nUniversity of Porto, Portugal
\n WEB<\/a>

\n\nJo\u00e3o Manuel R. S. Tavares graduated in Mechanical Engineering at the Universidade do Porto, Portugal in 1992. He also earned his M.Sc. degree and Ph.D. degree in Electrical and Computer Engineering from the Universidade do Porto in 1995 and 2001, and attained his Habilitation in Mechanical Engineering in 2015 from the same University. He is a senior researcher at the Instituto de Ci\u00eancia e Inova\u00e7\u00e3o em Engenharia Mec\u00e2nica e Engenharia Industrial (INEGI) and Full Professor at the Department of Mechanical Engineering (DEMec) of the Faculdade de Engenharia da Universidade do Porto (FEUP).
\nJo\u00e3o Tavares is co-editor of more than 80 books, co-author of more than 50 book chapters, 650 articles in international and national journals and conferences, and 3 international and 3 national patents. He has been a committee member of several international and national journals and conferences, is co-founder and co-editor of the book series \u201cLecture Notes in Computational Vision and Biomechanics\u201d published by Springer, founder and Editor-in-Chief of the journal \u201cComputer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization\u201d published by Taylor & Francis, Editor-in-Chief of the journal \u201cComputer Methods in Biomechanics and Biomedical Engineering\u201d published by Taylor & Francis, and co-founder and co-chair of the international conference series: International Symposium on Computational Modeling of Objects Presented in Images, ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing, International Conference on Computational and Experimental Biomedical Sciences and International Conference on Biodental Engineering. Additionally, he has been (co-)supervisor of several MSc and PhD thesis and supervisor of several post-doc projects, and has participated in many scientific projects both as researcher and as scientific coordinator.
\nHis main research areas include computational vision, medical imaging, computational mechanics, scientific visualization, human-computer interaction and new product development.
\t\n(More information can be found at: https:\/\/www.fe.up.pt\/~tavares<\/a>)

\n<\/div>\n

ABSTRACT<\/span>
\nThe segmentation of objects in images by computational approaches is very challenging, and it can be tackled using, for example, thresholding, deformable models built on statistical, geometrical or physical principles, registration, and\/or machine learning-based approaches. Examples of current applications of object segmentation include the identification of regions and structures of Engineering and the delineation of lesions and tissues in Biomedicine.
\nIn this lecture, techniques we have developed to segment images acquired using different imaging modalities will be described, and their use in engineering and medicine applications will be discussed.<\/div>\n