Aplication and investigation of unsupervised learning methods in retrieval and classification tasks

• Grant number: 18/15597-6
• Support Opportunities: Research Grants - Young Investigators Grants - Phase 2
• Start date: May 01, 2019
• End date: July 31, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Daniel Carlos Guimarães Pedronette
• Grantee: Daniel Carlos Guimarães Pedronette
• Host Institution: Instituto de Geociências e Ciências Exatas (IGCE). Universidade Estadual Paulista (UNESP). Campus de Rio Claro. Rio Claro , SP, Brazil
• Associated researchers: Denis Henrique Pinheiro Salvadeo ; Fabricio Aparecido Breve ; João Paulo Papa ; Jurandy Gomes de Almeida Junior ; Ricardo da Silva Torres
• Associated research grant: 13/08645-0 - Re-Ranking and rank aggregation approaches for image retrieval tasks, AP.JP
• Associated research grant(s): 23/00694-4 - Consistent and explainable natural language inference, AP.R SPRINT
• Associated scholarship(s): 23/12736-3 - Investigation of Visual Question Answering Approaches for Natural Disaster Management, BP.MS; 23/08150-3 - Investigação de Abordagens Auto-Supervisionadas utilizando Medidas baseda em Ranqueamento, BP.IC; 23/01828-4 - Unsupervised Effectiveness Estimation through Rank Based Measures, BP.IC; + associated scholarships 22/14448-2 - Investigation of Image Noise Reduction based on Unsupervised Learning, BP.IC; 22/07349-8 - Feature selection and aggregation based on rank measures, BP.MS; 22/01359-1 - Times series retrieval through unsupervised learning, BP.MS; 21/07993-1 - Investigation and evaluation of rank correlation measures, BP.IC; 20/02183-9 - Rank-based unsupervised learning through deep learning in diverse domains, BP.PD; 20/03311-0 - Unsupervised learning for general and multimodal multimedia retrieval, BP.MS - associated scholarships

Abstract

Unsupervised Learning methods have been established as a solution to increase the effectiveness of content-based searches without requiring user intervention. These methods exploit contextual relationship among images, usually encoded in the distance/similarity information of the collections.This research project intends to investigate the application of such methods in new and diversified domains. Unsupervised learning methods reevaluate the similarity between the elements of the collection and can be used as a pre-processing step in classification tasks. In addition, initial results indicate that the methods can be applied in general multimedia and multimodal retrieval scenarios, considering audio and video.Therefore, the central objective of the proposed project is to deepen such investigation, expanding the domains of application of unsupervised learning. methods. (AU)

Scientific publications

(29)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

CAMPOS, VICTOR DE ABREU; GUIMARAES PEDRONETTE, DANIEL CARLOS. A framework for speaker retrieval and identification through unsupervised learning. COMPUTER SPEECH AND LANGUAGE, v. 58, p. 153-174, NOV 2019. (17/25908-6, 15/07934-4, 18/15597-6)

GUIMARAES PEDRONETTE, DANIEL CARLOS; VALEM, LUCAS PASCOTTI; ALMEIDA, JURANDY; TONES, RICARDO DA S.. Multimedia Retrieval Through Unsupervised Hypergraph-Based Manifold Ranking. IEEE Transactions on Image Processing, v. 28, n. 12, p. 5824-5838, DEC 2019. (14/50715-9, 16/50250-1, 17/25908-6, 17/20945-0, 14/12236-1, 16/06441-7, 18/15597-6, 13/50155-0, 17/02091-4, 15/24494-8)

PEREIRA-FERRERO, VANESSA HELENA; VALEM, LUCAS PASCOTTI; PEDRONETTE, DANIEL CARLOS GUIMARAES. Feature augmentation based on manifold ranking and LSTM for image classification (R). EXPERT SYSTEMS WITH APPLICATIONS, v. 213, p. 16-pg., 2023-03-01. (17/25908-6, 20/02183-9, 18/15597-6, 20/11366-0)

DE ALMEIDA, LUCAS BARBOSA; PEREIRA-FERRERO, VANESSA HELENA; VALEM, LUCAS PASCOTTI; ALMEIDA, JURANDY; GUIMARAES PEDRONETTE, DANIEL CARLOS; IEEE COMP SOC. Representation Learning for Image Retrieval through 3D CNN and Manifold Ranking. 2021 34TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2021), v. N/A, p. 8-pg., 2021-01-01. (18/15597-6, 20/02183-9, 17/25908-6)

VALEM, LUCAS PASCOTTI; PEDRONETTE, DANIEL CARLOS GUIMARAES; LATECKI, LONGIN JAN. Graph Convolutional Networks based on manifold learning for semi-supervised image classification. COMPUTER VISION AND IMAGE UNDERSTANDING, v. 227, p. 14-pg., 2023-01-06. (17/25908-6, 18/15597-6, 20/11366-0)

CAMACHO PRESOTTO, JOAO GABRIEL; VALEM, LUCAS PASCOTTI; DE SA, NIKOLAS GOMES; GUIMARAES PEDRONETTE, DANIEL CARLOS; PAPA, JOAO PAULO; IEEE COMP SOC. Weakly Supervised Learning through Rank-based Contextual Measures. 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), v. N/A, p. 8-pg., 2021-01-01. (14/12236-1, 19/11104-8, 18/15597-6, 19/04754-6, 20/11366-0)

VALEM, LUCAS PASCOTTI; GUIMARAES PEDRONETTE, DANIEL CARLOS; ACM. A Denoising Convolutional Neural Network for Self-Supervised Rank Effectiveness Estimation on Image Retrieval. PROCEEDINGS OF THE 2021 INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL (ICMR '21), v. N/A, p. 9-pg., 2021-01-01. (18/15597-6, 17/25908-6, 20/11366-0)

VALEM, LUCAS PASCOTTI; PEDRONETTE, DANIEL CARLOS GUIMARAES. Person Re-ID through unsupervised hypergraph rank selection and fusion. Image and Vision Computing, v. 123, p. 14-pg., 2022-05-31. (18/15597-6, 17/25908-6)

VALEM, LUCAS PASCOTTI; GUIMARDES PEDRONETTE, DANIEL CARLOS; ASSOC COMP MACHINERY. An Unsupervised Genetic Algorithm Framework for Rank Selection and Fusion on Image Retrieval. ICMR'19: PROCEEDINGS OF THE 2019 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, v. N/A, p. 5-pg., 2019-01-01. (18/15597-6, 17/25908-6, 17/02091-4)

CAMACHO PRESOTTO, JOAO GABRIEL; VALEM, LUCAS PASCOTTI; PEDRONETTE, DANIEL CARLOS GUIMARAES; VENTO, M; PERCANNELLA, G. Unsupervised Effectiveness Estimation Through Intersection of Ranking References. COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2019, PT II, v. 11679, p. 14-pg., 2019-01-01. (18/15597-6, 17/25908-6, 17/02091-4)

GUIMARAES PEDRONETTE, DANIEL CARLOS; VALEM, LUCAS PASCOTTI; TORRES, RICARDO DA S.. A BFS-Tree of ranking references for unsupervised manifold learning. PATTERN RECOGNITION, v. 111, MAR 2021. (16/50250-1, 15/24494-8, 13/50155-0, 18/15597-6, 13/50169-1, 17/20945-0, 14/12236-1, 17/25908-6, 14/50715-9)

VALEM, LUCAS PASCOTTI; PEDRONETTE, DANIEL CARLOS GUIMARAES; LATECKI, LONGIN JAN. Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learning. IEEE Transactions on Image Processing, v. 32, p. 16-pg., 2023-01-01. (18/15597-6, 17/25908-6)

SILVA, LUCAS F. A.; PEDRONETTE, DANIEL C. G.; FARIA, FABIO A.; PAPA, JOAO P.; ALMEIDA, JURANDY; IEEE COMP SOC. Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers. 2021 34TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2021), v. N/A, p. 8-pg., 2021-01-01. (14/12236-1, 18/15597-6, 17/25908-6, 19/07665-4, 13/07375-0)

DE ALMEIDA, LUCAS BARBOSA; VALEM, LUCAS PASCOTTI; GUIMARAES PEDRONETTE, DANIEL CARLOS; IEEE. GRAPH CONVOLUTIONAL NETWORKS AND MANIFOLD RANKING FOR MULTIMODAL VIDEO RETRIEVAL. 2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, v. N/A, p. 5-pg., 2022-01-01. (20/11366-0, 18/15597-6, 20/03311-0)

VALEM, LUCAS PASCOTTI; SATO KAWAI, VINICIUS ATSUSHI; PEREIRA-FERRERO, VANESSA HELENA; GUIMARAES PEDRONETTE, DANIEL CARLOS; IEEE. A NOVEL RANK CORRELATION MEASURE FOR MANIFOLD LEARNING ON IMAGE RETRIEVAL AND PERSON RE-ID. 2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, v. N/A, p. 5-pg., 2022-01-01. (18/15597-6, 20/02183-9, 21/07993-1, 20/11366-0)

PRESOTTO, JOAO GABRIEL CAMACHO; DOS SANTOS, SAMUEL FELIPE; VALEM, LUCAS PASCOTTI; FARIA, FABIO AUGUSTO; PAPA, JOAO PAULO; ALMEIDA, JURANDY; PEDRONETTE, DANIEL CARLOS GUIMARAES. Weakly supervised learning based on hypergraph manifold ranking?. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, v. 89, p. 12-pg., 2022-10-25. (18/15597-6, 18/23908-1, 17/25908-6, 19/04754-6, 20/11366-0)

LOPES, LEONARDO TADEU; VALEM, LUCAS PASCOTTI; GUIMARAES PEDRONETTE, DANIEL CARLOS; GUILHERME, IVAN RIZZO; PAPA, JOAO PAULO; SILVA SANTANA, MARCOS CLEISON; COLOMBO, DANILO; FARINELLA, GM; RADEVA, P; BRAZ, J. Manifold Learning-based Clustering Approach Applied to Anomaly Detection in Surveillance Videos. VISAPP: PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 4: VISAPP, v. N/A, p. 9-pg., 2020-01-01. (18/15597-6, 14/12236-1, 13/07375-0, 17/25908-6, 19/07825-1, 18/21934-5)

GUIMARAES PEDRONETTE, DANIEL CARLOS; LATECKI, LONGIN JAN. Rank-based self-training for graph convolutional networks. INFORMATION PROCESSING & MANAGEMENT, v. 58, n. 2, MAR 2021. (17/25908-6, 18/15597-6)

VALEM, LUCAS PASCOTTI; GUIMARAES PEDRONETTE, DANIEL CARLOS. Unsupervised selective rank fusion for image retrieval tasks. Neurocomputing, v. 377, p. 182-199, FEB 15 2020. (17/25908-6, 17/02091-4, 18/15597-6)

RODRIGUES, RAFAEL B. M.; PRIVATTO, PEDRO I. M.; DE SOUSA, GUSTAVO JOSE; MURARI, RAFAEL P.; AFONSO, LUIS C. S.; PAPA, JOAO P.; PEDRONETTE, DANIEL C. G.; GUILHERME, IVAN R.; PERROUT, STEPHAN R.; RIENTE, ALIEL F.; et al. PetroBERT: A Domain Adaptation Language Model for Oil and Gas Applications in Portuguese. COMPUTATIONAL PROCESSING OF THE PORTUGUESE LANGUAGE, PROPOR 2022, v. 13208, p. 9-pg., 2022-01-01. (14/12236-1, 18/15597-6, 19/07665-4, 13/07375-0)

DE SA, NIKOLAS GOMES; VALEM, LUCAS PASCOTTI; GUIMARAES PEDRONETTE, DANIEL CARLOS; FARINELLA, GM; RADEVA, P; BRAZ, J; BOUATOUCH, K. A Multi-level Rank Correlation Measure for Image Retrieval. VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 5: VISAPP, v. N/A, p. 9-pg., 2021-01-01. (17/25908-6, 18/15597-6, 19/11104-8)

DE FERNANDO, FILIPE ALVES; GUIMARAES PEDRONETTE, DANIEL CARLOS; DE SOUSA, GUSTAVO JOSE; VALEM, LUCAS PASCOTTI; GUILHERME, IVAN RIZZO; FARINELLA, GM; RADEVA, P; BRAZ, J. RaDE: A Rank-based Graph Embedding Approach. VISAPP: PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 4: VISAPP, v. N/A, p. 11-pg., 2020-01-01. (17/25908-6, 18/15597-6)

LOPES, LEONARDO TADEU; GUIMARAES PEDRONETTE, DANIEL CARLOS; IEEE. Self-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks. 2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), v. N/A, p. 10-pg., 2023-01-01. (18/15597-6, 17/25908-6)

OLIVEIRA, GUILHERME C.; NGO, QUOC C.; PASSOS, LEANDRO A.; PAPA, JOAO P.; JODAS, DANILO S.; KUMAR, DINESH. Tabular data augmentation for video-based detection of hypomimia in Parkinson's disease. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, v. 240, p. 8-pg., 2023-10-01. (19/00585-5, 18/15597-6, 14/12236-1, 19/07665-4, 13/07375-0, 19/02205-5)

GONCALVES, FILIPE MARCEL FERNANDES; PEDRONETTE, DANIEL CARLOS GUIMARAES; TORRES, RICARDO DA SILVA. Regression by Re-Ranking. PATTERN RECOGNITION, v. 140, p. 17-pg., 2023-04-09. (13/50155-0, 18/15597-6, 14/12236-1, 16/50250-1, 15/24494-8, 17/25908-6, 17/20945-0)

VALEM, LUCAS PASCOTTI; GUIMARAES PEDRONETTE, DANIEL CARLOS. Graph -based selective rank fusion for unsupervised image retrieval. PATTERN RECOGNITION LETTERS, v. 135, p. 82-89, JUL 2020. (17/25908-6, 13/08645-0, 17/02091-4, 18/15597-6)

ASCENCAO, NATHALIA Q.; AFONSO, LUIS C. S.; COLOMBO, DANILO; OLIVEIRA, LUCIANO; PAPA, JOAO P.; IEEE. Information Ranking Using Optimum-Path Forest. 2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), v. N/A, p. 8-pg., 2020-01-01. (18/15597-6, 14/12236-1, 19/07665-4, 13/07375-0, 17/25908-6)

GUIMARAES PEDRONETTE, DANIEL CARLOS; PASCOTTI VALEM, LUCAS; LATECKI, LONGIN JAN. Efficient Rank-Based Diffusion Process with Assured Convergence. JOURNAL OF IMAGING, v. 7, n. 3, MAR 2021. (20/11366-0, 18/15597-6, 17/25908-6)

ROZIN, BIONDA; PEREIRA-FERRERO, VANESSA HELENA; LOPES, LEONARDO TADEU; PEDRONETTE, DANIEL CARLOS GUIMARAES. A rank-based framework through manifold learning for improved clustering tasks. INFORMATION SCIENCES, v. 580, p. 202-220, NOV 2021. (17/25908-6, 20/02183-9, 20/08854-2, 18/15597-6)