Cargando…
Multi-Information Flow CNN and Attribute-Aided Reranking for Person Reidentification
This paper presents a multi-information flow convolutional neural network (MiF-CNN) model for person reidentification (re-id). It contains several specific multilayer convolutional structures, where the input and output of a convolutional layer are concatenated together on channel dimension. With th...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6381562/ https://www.ncbi.nlm.nih.gov/pubmed/30881442 http://dx.doi.org/10.1155/2019/7028107 |
_version_ | 1783396523086708736 |
---|---|
author | Sang, Haifeng Wang, Chuanzheng He, Dakuo Liu, Qing |
author_facet | Sang, Haifeng Wang, Chuanzheng He, Dakuo Liu, Qing |
author_sort | Sang, Haifeng |
collection | PubMed |
description | This paper presents a multi-information flow convolutional neural network (MiF-CNN) model for person reidentification (re-id). It contains several specific multilayer convolutional structures, where the input and output of a convolutional layer are concatenated together on channel dimension. With this idea, layers of model can go deeper and feature maps can be reused by each subsequent layer. Inspired by an image caption, a person attribute recognition network is proposed based on long-short-term memory network and attention mechanism. By fusing identification results of MiF-CNN and attribute recognition, this paper introduces the attribute-aided reranking algorithm to improve the accuracy of person re-id further. Experiments on VIPeR, CUHK01, and Market1501 datasets verify the proposed MiF-CNN can be trained sufficiently with small-scale datasets and obtain outstanding accuracy of person re-id. Contrast experiments also confirm the availability of the attribute-assisted reranking algorithm. |
format | Online Article Text |
id | pubmed-6381562 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Hindawi |
record_format | MEDLINE/PubMed |
spelling | pubmed-63815622019-03-17 Multi-Information Flow CNN and Attribute-Aided Reranking for Person Reidentification Sang, Haifeng Wang, Chuanzheng He, Dakuo Liu, Qing Comput Intell Neurosci Research Article This paper presents a multi-information flow convolutional neural network (MiF-CNN) model for person reidentification (re-id). It contains several specific multilayer convolutional structures, where the input and output of a convolutional layer are concatenated together on channel dimension. With this idea, layers of model can go deeper and feature maps can be reused by each subsequent layer. Inspired by an image caption, a person attribute recognition network is proposed based on long-short-term memory network and attention mechanism. By fusing identification results of MiF-CNN and attribute recognition, this paper introduces the attribute-aided reranking algorithm to improve the accuracy of person re-id further. Experiments on VIPeR, CUHK01, and Market1501 datasets verify the proposed MiF-CNN can be trained sufficiently with small-scale datasets and obtain outstanding accuracy of person re-id. Contrast experiments also confirm the availability of the attribute-assisted reranking algorithm. Hindawi 2019-02-06 /pmc/articles/PMC6381562/ /pubmed/30881442 http://dx.doi.org/10.1155/2019/7028107 Text en Copyright © 2019 Haifeng Sang et al. http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Article Sang, Haifeng Wang, Chuanzheng He, Dakuo Liu, Qing Multi-Information Flow CNN and Attribute-Aided Reranking for Person Reidentification |
title | Multi-Information Flow CNN and Attribute-Aided Reranking for Person Reidentification |
title_full | Multi-Information Flow CNN and Attribute-Aided Reranking for Person Reidentification |
title_fullStr | Multi-Information Flow CNN and Attribute-Aided Reranking for Person Reidentification |
title_full_unstemmed | Multi-Information Flow CNN and Attribute-Aided Reranking for Person Reidentification |
title_short | Multi-Information Flow CNN and Attribute-Aided Reranking for Person Reidentification |
title_sort | multi-information flow cnn and attribute-aided reranking for person reidentification |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6381562/ https://www.ncbi.nlm.nih.gov/pubmed/30881442 http://dx.doi.org/10.1155/2019/7028107 |
work_keys_str_mv | AT sanghaifeng multiinformationflowcnnandattributeaidedrerankingforpersonreidentification AT wangchuanzheng multiinformationflowcnnandattributeaidedrerankingforpersonreidentification AT hedakuo multiinformationflowcnnandattributeaidedrerankingforpersonreidentification AT liuqing multiinformationflowcnnandattributeaidedrerankingforpersonreidentification |