Advanced search
Start date
Betweenand

Re-Ranking and rank aggregation approaches for image retrieval tasks

Grant number: 13/08645-0
Support type:Research Grants - Young Investigators Grants
Duration: February 01, 2014 - January 31, 2018
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computer Systems
Principal Investigator:Daniel Carlos Guimarães Pedronette
Grantee:Daniel Carlos Guimarães Pedronette
Home Institution: Instituto de Geociências e Ciências Exatas (IGCE). Universidade Estadual Paulista (UNESP). Campus de Rio Claro. Rio Claro , SP, Brazil
Assoc. researchers:Denis Henrique Pinheiro Salvadeo ; Edson Borin ; Marco Antonio Garcia de Carvalho ; Ricardo da Silva Torres
Associated grant(s):18/15597-6 - Aplication and investigation of unsupervised learning methods in retrieval and classification tasks, AP.JP2
Associated scholarship(s):17/02091-4 - Selection and combination of unsupervised learning Methdos for content-based image retrieval, BP.MS
16/10908-8 - Use and evaluation of methods for reclassifying and aggregating lists in different applications, BP.IC
15/07934-4 - Automatic Speaker Identification using Unsupervised Learning, BP.MS
14/04220-8 - Lists efficient re-ranking and rank aggregation methods, BP.IC

Abstract

Content-Based Image Retrieval (CBIR) systems aims at retrieving the most similar images in a collection by taking into account image visual properties. Users are interested in the images placed at the first positions of the returned ranked lists, which usually are the most relevant ones. Therefore, accurately ranking collection images is of great relevance. However, in general, CBIR approaches perform only pairwise image analysis, that is, they compute similarity (or distance) measures considering only pairs of images, ignoring the rich information encoded in the relationships among images. Aiming at improving the effectiveness of CBIR systems, re-ranking and rank aggregation algorithms have been proposed. Re-ranking algorithms have been used to exploit contextual information, encoded in the relationships among collection images, while rank aggregation approaches have been used to combine results produced by different image descriptors. In the work developed by the principal investigator during his PhD research, several methods have been proposed for image re-ranking and rank aggregation, aiming at improving the effectiveness of CBIR systems. Experimental results demonstrated the effectiveness of the proposed approaches in comparison with other state-of-the-art methods recently proposed in the literature. However, the relevant results obtained led to new important research challenges. The objective of this research project is to investigate the re-ranking and rank aggregation approaches under various aspects, addressing the challenges still open. Important aspects to be investigated are related to the scalability and efficient computation of image re-ranking algorithms using parallel algorithms on heterogeneous computing environments. Another relevant aspect is the specification and implementation of new re-ranking approaches to be used in different scenarios and applications, such as multimodal and textual retrieval, relevance feedback, and collaborative image retrieval. (AU)

Scientific publications (18)
(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)
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. Web of Science Citations: 0.
PISANI, FLAVIA; PASCOTTI VALEM, LUCAS; GUIMARAES PEDRONETTE, DANIEL CARLOS; DA S. TORRES, RICARDO; BORIN, EDSON; BRETERNITZ, MAURICIO. A unified model for accelerating unsupervised iterative re-ranking algorithms. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, v. 32, n. 14 MAR 2020. Web of Science Citations: 0.
BALDASSIN, ALEXANDRO; WENG, YING; GUIMARAES PEDRONETTE, DANIEL CARLOS; ALMEIDA, JURANDY. An optimized unsupervised manifold learning algorithm for manycore architectures. INFORMATION SCIENCES, v. 496, p. 410-430, SEP 2019. Web of Science Citations: 1.
GUIMARAES PEDRONETTE, DANIEL CARLOS; WENG, YING; BALDASSIN, ALEXANDRO; HOU, CHAOHUAN. Semi-supervised and active learning through Manifold Reciprocal kNN Graph for image retrieval. Neurocomputing, v. 340, p. 19-31, MAY 7 2019. Web of Science Citations: 0.
PAPA, JOAO P.; ROSA, GUSTAVO H.; DE SOUZA, ANDRE N.; AFONSO, LUIS C. S. Feature selection through binary brain storm optimization. COMPUTERS & ELECTRICAL ENGINEERING, v. 72, p. 468-481, NOV 2018. Web of Science Citations: 3.
VALEM, LUCAS PASCOTTI; DE OLIVEIRA, CARLOS RENAN; GUIMARAES PEDRONETTE, DANIEL CARLOS; ALMEIDA, JURANDY. Unsupervised Similarity Learning through Rank Correlation and kNN Sets. ACM Transactions on Multimedia Computing Communications and Applications, v. 14, n. 4 NOV 2018. Web of Science Citations: 1.
VALEM, LUCAS PASCOTTI; GUIMARAES PEDRONETTE, DANIEL CARLOS; ALMEIDA, JURANDY. Unsupervised similarity learning through Cartesian product of ranking references. PATTERN RECOGNITION LETTERS, v. 114, n. SI, p. 41-52, OCT 15 2018. Web of Science Citations: 2.
GUIMARAES PEDRONETTE, DANIEL CARLOS; FERNANDES GONCALVES, FILIPE MARCEL; GUILHERME, IVAN RIZZO. Unsupervised manifold learning through reciprocal kNN graph and Connected Components for image retrieval tasks. PATTERN RECOGNITION, v. 75, n. SI, p. 161-174, MAR 2018. Web of Science Citations: 12.
FERNANDES GONCALVES, FILIPE MARCEL; GUILHERME, IVAN RIZZO; GUIMARAES PEDRONETTE, DANIEL CARLOS. Semantic Guided Interactive Image Retrieval for plant identification. EXPERT SYSTEMS WITH APPLICATIONS, v. 91, p. 12-26, JAN 2018. Web of Science Citations: 6.
PISANI, FLAVIA; PEDRONETTE, DANIEL C. G.; TORRES, RICARDO DA S.; BORIN, EDSON. Contextual Spaces Re-Ranking: accelerating the Re-sort Ranked Lists step on heterogeneous systems. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, v. 29, n. 22, SI NOV 25 2017. Web of Science Citations: 1.
GUIMARAES PEDRONETTE, DANIEL CARLOS; TORRES, RICARDO DA S. Unsupervised rank diffusion for content-based image retrieval. Neurocomputing, v. 260, p. 478-489, OCT 18 2017. Web of Science Citations: 0.
ALMEIDA, JURANDY; PEDRONETTE, DANIEL C. G.; ALBERTON, BRUNA C.; MORELLATO, LEONOR PATRICIA C.; TORRES, RICARDO DA S. Unsupervised Distance Learning for Plant Species Identification. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, v. 9, n. 12, 1, SI, p. 5325-5338, DEC 2016. Web of Science Citations: 4.
GUIMARAES PEDRONETTE, DANIEL CARLOS; ALMEIDA, JURANDY; TORRES, RICARDO DA S. A graph-based ranked-list model for unsupervised distance learning on shape retrieval. PATTERN RECOGNITION LETTERS, v. 83, n. 3, p. 357-367, NOV 1 2016. Web of Science Citations: 5.
GUIMARAES PEDRONETTE, DANIEL CARLOS; TORRES, RICARDO DA S. A correlation graph approach for unsupervised manifold learning in image retrieval tasks. Neurocomputing, v. 208, n. SI, p. 66-79, OCT 5 2016. Web of Science Citations: 9.
GUIMARAES PEDRONETTE, DANIEL CARLOS; TORRES, RICARDO DA S. Combining re-ranking and rank aggregation methods for image retrieval. MULTIMEDIA TOOLS AND APPLICATIONS, v. 75, n. 15, p. 9121-9144, AUG 2016. Web of Science Citations: 2.
GUIMARAES PEDRONETTE, DANIEL CARLOS; CALUMBY, RODRIGO T.; TORRES, RICARDO DA S. A semi-supervised learning algorithm for relevance feedback and collaborative image retrieval. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, AUG 10 2015. Web of Science Citations: 4.
GUIMARAES PEDRONETTE, DANIEL CARLOS; ALMEIDA, JURANDY; TORRES, RICARDO DA S. A scalable re-ranking method for content-based image retrieval. INFORMATION SCIENCES, v. 265, p. 91-104, MAY 1 2014. Web of Science Citations: 34.
FARIA, FABIO A.; PEDRONETTE, DANIEL C. G.; DOS SANTOS, JEFERSSON A.; ROCHA, ANDERSON; TORRES, RICARDO DA S. Rank Aggregation for Pattern Classifier Selection in Remote Sensing Images. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, v. 7, n. 4, p. 1103-1115, APR 2014. Web of Science Citations: 9.

Please report errors in scientific publications list by writing to: cdi@fapesp.br.