Person Re-ID through unsupervised hypergraph rank selection and fusion

Autor(es)

Valem, Lucas Pascotti ; Pedronette, Daniel Carlos Guimaraes

• Tipo de documento: Artigo Científico
• Fonte: Image and Vision Computing; v. 123, p. 14-pg., 2022-05-31.

Resumo

Person Re-ID has been gaining a lot of attention and nowadays is of fundamental importance in many camera sur-veillance applications. The task consists of identifying individuals across multiple cameras that have no overlap-ping views. Most of the approaches require labeled data, which is not always available, given the huge amount of demanded data and the difficulty of manually assigning a class for each individual. Recently, studies have shown that re-ranking methods are capable of achieving significant gains, especially in the absence of labeled data. Be-sides that, the fusion of feature extractors and multiple-source training is another promising research direction not extensively exploited. We aim to fill this gap through a manifold rank aggregation approach capable of exploiting the complementarity of different person Re-ID rankers. In this work, we perform a completely unsu-pervised selection and fusion of diverse ranked lists obtained from multiple and diverse feature extractors. Among the contributions, this work proposes a query performance prediction measure that models the relation-ship among images considering a hypergraph structure and does not require the use of any labeled data. Expres-sive gains were obtained in four datasets commonly used for person Re-ID. We achieved results competitive to the state-of-the-art in most of the scenarios.(c) 2022 Elsevier B.V. All rights reserved. (AU)

• Processo FAPESP: 18/15597-6 - Aplicação e investigação de métodos de aprendizado não-supervisionado em tarefas de recuperação e classificação
• Beneficiário: Daniel Carlos Guimarães Pedronette
• Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores - Fase 2
• Processo FAPESP: 17/25908-6 - Aprendizado fracamente supervisionado para análise de vídeos no domínio comprimido em tarefas de recuperação e classificação para alertas visuais
• Beneficiário: João Paulo Papa
• Modalidade de apoio: Auxílio à Pesquisa - Parceria para Inovação Tecnológica - PITE