<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>2227-1899</journal-id>
<journal-title><![CDATA[Revista Cubana de Ciencias Informáticas]]></journal-title>
<abbrev-journal-title><![CDATA[Rev cuba cienc informat]]></abbrev-journal-title>
<issn>2227-1899</issn>
<publisher>
<publisher-name><![CDATA[Editorial Ediciones Futuro]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S2227-18992020000200070</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Single-Shot Person Re-Identi&#64257;cation based on Unsupervised Saliency Information]]></article-title>
<article-title xml:lang="es"><![CDATA[Single-Shot Re-identificación de persona basada en información saliente no supervisada]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[León Guerra]]></surname>
<given-names><![CDATA[Reynolds]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[García Reyes]]></surname>
<given-names><![CDATA[Edel B.]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Advanced Technologies Application Center (CENATAV)  ]]></institution>
<addr-line><![CDATA[ Havana]]></addr-line>
<country>Cuba</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>06</month>
<year>2020</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>06</month>
<year>2020</year>
</pub-date>
<volume>14</volume>
<numero>2</numero>
<fpage>70</fpage>
<lpage>82</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://scielo.sld.cu/scielo.php?script=sci_arttext&amp;pid=S2227-18992020000200070&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://scielo.sld.cu/scielo.php?script=sci_abstract&amp;pid=S2227-18992020000200070&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://scielo.sld.cu/scielo.php?script=sci_pdf&amp;pid=S2227-18992020000200070&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[ABSTRACT Person re-identi&#64257;cation task is important in video surveillance to improve security in public place. In recent years there is a lot of investigation about this thematic. However, the performance in these algorithms is a&#64256;ected by di&#64256;erent problems in the scenes, for example, complex background, atmospheric conditions, etc. Some methods as deep learning and saliency descriptor have been used to solve these problems in the real world. In this paper, we developed a method based on the combination of convolutional neural network without &#64257;ne-tuning and a saliency descriptor to weight all the information present into a person image. Feature maps are extracted from the last convolutional layer of a neural network and merged with other salient map obtained in spatial domain. Finally, di&#64256;erent features are generated based on color histograms and local binary patterns. To verify the e&#64256;ectiveness of our proposal, the method is validated using VIPeR dataset and compared with others state of the art algorithms. The results shown that our proposal is easy to implement and is comparable with other approach using the Cumulative Matching Characteristic curve.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[RESUMEN La re-identi&#64257;cación de personas es una tarea importante en video protección para mejorar la seguridad en áreas públicas. En los últimos años existe un gran incremento en las investigaciones sobre este tema. Sin embargo, el desempeño de estos algoritmos es afectado por diferentes problemas presentes en las escenas, por ejemplo, fondos complejos, condiciones atmosféricas y otros. Algunos métodos como el aprendizaje profundo y descriptores de saliencia han sido usados para contrarrestar estos problemas en el mundo real. En el presente artículo, es desarrollado un método basado en la combinación de redes neuronales por comvolución sin aplicar &#64257;ne-tuning y un descriptor de saliencia para ponderar toda la información presente en la imagen de la persona. Los mapas de rasgos son extraídos desde la última capa de convolución de una red neuronal y combinado con otro mapa de saliencia obtenido en el dominio espacial. Finalmente, diferentes rasgos son generados basados en un histograma de color y patrones binarios locales. Para verificar el desempeño del método propuesto, es validado en la base de datos VIPeR y comparado con otros algoritmos del estado del arte. Los resultados muestran que el método propuesto es fácil de implementar y es comparable con otros métodos usando la curva de correspondencia cumulativa.]]></p></abstract>
<kwd-group>
<kwd lng="es"><![CDATA[Aprendizaje profundo]]></kwd>
<kwd lng="es"><![CDATA[Re-identi&#64257;cación de personas]]></kwd>
<kwd lng="es"><![CDATA[Saliencia]]></kwd>
<kwd lng="es"><![CDATA[Mapas]]></kwd>
<kwd lng="es"><![CDATA[Rasgos]]></kwd>
<kwd lng="en"><![CDATA[Deep learning]]></kwd>
<kwd lng="en"><![CDATA[Person re-identi&#64257;cation]]></kwd>
<kwd lng="en"><![CDATA[Saliency]]></kwd>
<kwd lng="en"><![CDATA[Maps]]></kwd>
<kwd lng="en"><![CDATA[Features]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kansal]]></surname>
<given-names><![CDATA[Kajal]]></given-names>
</name>
<name>
<surname><![CDATA[Subramanyam]]></surname>
<given-names><![CDATA[A. V]]></given-names>
</name>
</person-group>
<source><![CDATA[Hdrnet: Person Re-Identi&#64257;cation Using Hybrid Sampling in Deep Reconstruction Network.]]></source>
<year>2019</year>
<volume>7</volume>
<page-range>40856-65</page-range><publisher-name><![CDATA[IEEE Access]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Liao]]></surname>
<given-names><![CDATA[Shengcai]]></given-names>
</name>
</person-group>
<source><![CDATA[Person re-identi&#64257;cation by local maximal occurrence representation and metric learning.]]></source>
<year>2015</year>
<page-range>2197-206</page-range></nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Jia]]></surname>
<given-names><![CDATA[Jieru]]></given-names>
</name>
</person-group>
<source><![CDATA[Multiple metric learning with query adaptive weights and multi-task re-weighting for person re-identi&#64257;cation.]]></source>
<year>2017</year>
<volume>160</volume>
<page-range>87-99</page-range><publisher-name><![CDATA[Computer Vision and Image Understanding]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[Jiabao]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Yang]]></given-names>
</name>
<name>
<surname><![CDATA[Miao]]></surname>
<given-names><![CDATA[Zhuang]]></given-names>
</name>
</person-group>
<source><![CDATA[Siamese cosine network embedding for person re-identi&#64257;cation.]]></source>
<year>2017</year>
<page-range>352-62</page-range><publisher-loc><![CDATA[Singapore ]]></publisher-loc>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Álvarez-Miranda]]></surname>
<given-names><![CDATA[Eduardo]]></given-names>
</name>
<name>
<surname><![CDATA[Díaz-Guerrero]]></surname>
<given-names><![CDATA[John]]></given-names>
</name>
</person-group>
<source><![CDATA[Multicriteria saliency detection: a (exact) robust network design approach.]]></source>
<year>2018</year>
<page-range>1-20</page-range><publisher-name><![CDATA[Annals of Operations Research]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhao]]></surname>
<given-names><![CDATA[Rui]]></given-names>
</name>
<name>
<surname><![CDATA[Ouyang]]></surname>
<given-names><![CDATA[Wanli]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[Xiaogang]]></given-names>
</name>
</person-group>
<source><![CDATA[Unsupervised salience learning for person re-identi&#64257;cation.]]></source>
<year>2013</year>
<page-range>3586-93</page-range></nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Martinel]]></surname>
<given-names><![CDATA[Niki]]></given-names>
</name>
<name>
<surname><![CDATA[Micheloni]]></surname>
<given-names><![CDATA[Christian]]></given-names>
</name>
<name>
<surname><![CDATA[Foresti]]></surname>
<given-names><![CDATA[Gian Luca]]></given-names>
</name>
</person-group>
<source><![CDATA[Saliency weighted features for person re-identi&#64257;cation.]]></source>
<year>2014</year>
<page-range>191-208</page-range><publisher-loc><![CDATA[Cham ]]></publisher-loc>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Huo]]></surname>
<given-names><![CDATA[Zhonghua]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[Ying]]></given-names>
</name>
<name>
<surname><![CDATA[Hua]]></surname>
<given-names><![CDATA[Chunjian]]></given-names>
</name>
</person-group>
<source><![CDATA[Person re-identi&#64257;cation based on multi-directional saliency metric learning.]]></source>
<year>2015</year>
<page-range>45-55</page-range><publisher-name><![CDATA[Springer, Cham]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Tiezhu]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Person re-identi&#64257;cation using salient region matching game.]]></article-title>
<source><![CDATA[Multimedia Tools and Applications]]></source>
<year>2018</year>
<month>a</month>
<volume>77</volume>
<numero>16</numero>
<issue>16</issue>
<page-range>21393-415</page-range></nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Wei]]></given-names>
</name>
<name>
<surname><![CDATA[Zhu]]></surname>
<given-names><![CDATA[Xiatian]]></given-names>
</name>
<name>
<surname><![CDATA[Gong]]></surname>
<given-names><![CDATA[Shaogang]]></given-names>
</name>
</person-group>
<source><![CDATA[Harmonious attention network for person re-identi&#64257;cation.]]></source>
<year>2018</year>
<month>b</month>
<page-range>2285-94</page-range></nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Rahimpour]]></surname>
<given-names><![CDATA[Alireza]]></given-names>
</name>
</person-group>
<source><![CDATA[Person re-identi&#64257;cation using visual attention.]]></source>
<year>2017</year>
<page-range>4242-6</page-range><publisher-name><![CDATA[IEEE]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Douglas]]></surname>
<given-names><![CDATA[Gray]]></given-names>
</name>
<name>
<surname><![CDATA[Brennan]]></surname>
<given-names><![CDATA[Shane]]></given-names>
</name>
<name>
<surname><![CDATA[Tao]]></surname>
<given-names><![CDATA[Hai]]></given-names>
</name>
</person-group>
<source><![CDATA[Evaluating appearance models for recognition, reacquisition, and tracking.]]></source>
<year>2007</year>
<page-range>1-7</page-range><publisher-name><![CDATA[Citeseer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hirzer]]></surname>
<given-names><![CDATA[Martin]]></given-names>
</name>
</person-group>
<source><![CDATA[Person re-identi&#64257;cation by descriptive and discriminative classi&#64257;cation.]]></source>
<year>2011</year>
<page-range>91-102</page-range><publisher-loc><![CDATA[Berlin, Heidelberg ]]></publisher-loc>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zeiler]]></surname>
<given-names><![CDATA[Matthew D]]></given-names>
</name>
</person-group>
<source><![CDATA[Adaptive deconvolutional networks for mid and high level feature learning.]]></source>
<year>2011</year>
<page-range>6</page-range><publisher-name><![CDATA[ICCV]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Chatfield]]></surname>
<given-names><![CDATA[Ken]]></given-names>
</name>
</person-group>
<source><![CDATA[Return of the devil in the details: Delving deep into convolutional nets.]]></source>
<year>2014</year>
</nlm-citation>
</ref>
<ref id="B16">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Guerra]]></surname>
<given-names><![CDATA[Reynolds León]]></given-names>
</name>
</person-group>
<source><![CDATA[FqSD: Full-Quaternion Saliency Detection in Images.]]></source>
<year>2018</year>
<page-range>462-9</page-range><publisher-loc><![CDATA[Cham ]]></publisher-loc>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B17">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Koestinger]]></surname>
<given-names><![CDATA[Martin]]></given-names>
</name>
</person-group>
<source><![CDATA[Large scale metric learning from equivalence constraints.]]></source>
<year>2012</year>
<page-range>2288-95</page-range><publisher-name><![CDATA[IEEE]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B18">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Feng]]></surname>
<given-names><![CDATA[Guanhua]]></given-names>
</name>
</person-group>
<source><![CDATA[Hessian Regularized Distance Metric Learning for People Re-Identi&#64257;cation]]></source>
<year>2019</year>
<page-range>1-14</page-range><publisher-name><![CDATA[Neural Processing Letters]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B19">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Fang]]></surname>
<given-names><![CDATA[Wen]]></given-names>
</name>
</person-group>
<source><![CDATA[Perceptual hash-based feature description for person re-identi&#64257;cation]]></source>
<year>2018</year>
<volume>272</volume>
<page-range>520-31</page-range><publisher-name><![CDATA[Neurocomputing]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B20">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[Chen]]></given-names>
</name>
<name>
<surname><![CDATA[LIU]]></surname>
<given-names><![CDATA[Qiaoling]]></given-names>
</name>
</person-group>
<source><![CDATA[Region constraint person re-identi&#64257;cation via partial least square on Riemannian manifold]]></source>
<year>2018</year>
<volume>6</volume>
<page-range>17060-6</page-range><publisher-name><![CDATA[IEEE Access]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B21">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[Chengyuan]]></given-names>
</name>
</person-group>
<source><![CDATA[Crossing generative adversarial networks for cross-view person re-identi&#64257;cation]]></source>
<year>2019</year>
<publisher-name><![CDATA[Neurocomputing]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B22">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mao]]></surname>
<given-names><![CDATA[Chaojie]]></given-names>
</name>
</person-group>
<source><![CDATA[Multi-channel pyramid person matching network for person re-identi&#64257;cation.]]></source>
<year>2018</year>
</nlm-citation>
</ref>
</ref-list>
</back>
</article>
