{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T12:16:41Z","timestamp":1770034601142,"version":"3.49.0"},"reference-count":23,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2021,9,15]]},"abstract":"<jats:p>Finding the common objects in a set of images is considered one of the recent challenges in different computer vision tasks. Most of the conventional methods have proposed unsupervised and weakly supervised co-localization methods to find the common objects; however, these methods require producing a huge amount of region proposals. This paper tackles this problem by exploiting supervised learning benefits to localize the common object in a set of unlabeled images containing multiple objects or with no common objects. Two stages are proposed to localize the common objects: the candidate box generation stage and the matching and clustering stage. In the candidate box generation stage, the objects are localized and surrounded by the bounding boxes. The matching and clustering stage is applied on the generated bounding boxes and creates a distance matrix based on a trained Siamese network to reflect the matching percentage. Hierarchical clustering uses the generated distance matrix to find the common objects and create clusters for each one. The proposed method is trained on PASCAL VOC 2007 dataset; on the other hand, it is assessed by applying different experiments on PASCAL VOC 2007 6\u00d72 and Object Discovery datasets, respectively. The results reveal that the proposed method outperforms the conventional methods by 8% to 40% in terms of corloc metric.<\/jats:p>","DOI":"10.3233\/jifs-210854","type":"journal-article","created":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T14:39:27Z","timestamp":1628606367000},"page":"3499-3508","source":"Crossref","is-referenced-by-count":3,"title":["Efficient common objects localization based on deep hybrid Siamese network"],"prefix":"10.1177","volume":"41","author":[{"given":"Mona M.","family":"Moussa","sequence":"first","affiliation":[{"name":"Computer and Systems Department, Electronics Research Institute (ERI), Egypt"}]},{"given":"Rasha","family":"Shoitan","sequence":"additional","affiliation":[{"name":"Computer and Systems Department, Electronics Research Institute (ERI), Egypt"}]},{"given":"Mohamed S.","family":"Abdallah","sequence":"additional","affiliation":[{"name":"Informatics Research Department, Electronics Research Institute (ERI), Egypt"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-210854_ref1","doi-asserted-by":"crossref","unstructured":"Cho M. , Kwak S. , Schmid C. , Ponce J. , Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals, Proc. IEEE Comput. Soc. Conf.Comput. Vis. Pattern Recognit., vol. 07-12-June, pp. 1201\u20131210, 2015.","DOI":"10.1109\/CVPR.2015.7298724"},{"key":"10.3233\/JIFS-210854_ref2","doi-asserted-by":"crossref","unstructured":"Tang K. , Joulin A. , Li L. , Co-localization in Real-World Images, Proceedings of the IEEE conference on computer vision andpattern recognition, 2014.","DOI":"10.1109\/CVPR.2014.190"},{"issue":"PART 6","key":"10.3233\/JIFS-210854_ref3","first-page":"253","article-title":"Efficient image and videoco-localization with Frank-Wolfe algorithm","volume":"8694 LNCS","author":"Joulin","year":"2014","journal-title":"Lect Notes ComputSci, Lect Notes Artif Intell, Lect Notes Bioinformatics"},{"key":"10.3233\/JIFS-210854_ref4","doi-asserted-by":"crossref","unstructured":"Wu L. , Liu Q. , Weakly supervised object co-localization via sharing parts based on a joint Bayesian model, Symmetry (Basel) 10(5) (2018).","DOI":"10.3390\/sym10050142"},{"issue":"2016","key":"10.3233\/JIFS-210854_ref5","first-page":"19","article-title":"Image co-localizationby mimicking a good detector\u00e2\u20ac\u2122s confidence scoredistribution","volume":"9906 LNCS","author":"Li","journal-title":"Lect Notes Comput Sci (including Subser. Lect.Notes Artif. Intell. Lect. Notes Bioinformatics)"},{"key":"10.3233\/JIFS-210854_ref6","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.patcog.2018.10.022","article-title":"Unsupervisedobject discovery and co-localization by deep descriptortransformation","volume":"88","author":"Wei","year":"2019","journal-title":"Pattern Recognit"},{"issue":"9","key":"10.3233\/JIFS-210854_ref7","doi-asserted-by":"crossref","first-page":"4503","DOI":"10.1109\/TIP.2018.2839901","article-title":"Simultaneously Discovering and LocalizingCommon Objects in Wild Images","volume":"27","author":"Wang","year":"2018","journal-title":"IEEE Trans Image Process"},{"key":"10.3233\/JIFS-210854_ref8","doi-asserted-by":"crossref","first-page":"8606","DOI":"10.1109\/TIP.2020.3015543","article-title":"Object Discovery from a Single Unlabeled Image by Mining Frequent Item sets with Multi-Scale Features","volume":"29","author":"Zhang","year":"2020","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"10.3233\/JIFS-210854_ref9","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEETrans Pattern Anal Mach Intell"},{"key":"10.3233\/JIFS-210854_ref10","doi-asserted-by":"crossref","unstructured":"Cho, Minsu, et al., Unsupervised object discovery and localizationin the wild: Part-based matching with bottom-up region proposals, Proceedings of the IEEE conference on computer vision andpattern recognition, 2015.","DOI":"10.1109\/CVPR.2015.7298724"},{"key":"10.3233\/JIFS-210854_ref11","doi-asserted-by":"crossref","unstructured":"Hashemi M. , Enlarging smaller images before inputting intoconvolutional neural network: zero-padding vs. interpolation, Journal of Big Data, 2019.","DOI":"10.1186\/s40537-019-0263-7"},{"issue":"12","key":"10.3233\/JIFS-210854_ref12","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.3390\/electronics8121394","article-title":"Zero-shot deep learning for media mining: Person spotting and face clustering in video big data","volume":"8","author":"Abdallah","year":"2019","journal-title":"Electronics"},{"key":"10.3233\/JIFS-210854_ref13","doi-asserted-by":"crossref","unstructured":"Malhotra R. , et al., Software defect prediction using Binary Particle Swarm Optimization with Binary Cross Entropy as the fitness function, Journal of Physics: Conference Series 1767(1), IOP Publishing, 2021.","DOI":"10.1088\/1742-6596\/1767\/1\/012003"},{"key":"10.3233\/JIFS-210854_ref14","unstructured":"Kingma D.P. , Ba J.L. , Adam: A method for stochastic optimization, 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. TrackProc., pp. 1\u201315, 2015."},{"key":"10.3233\/JIFS-210854_ref15","first-page":"83","article-title":"Agglomerative hierarchical clustering algorithm-a","volume":"83","author":"Sasirekha","year":"2013","journal-title":"International Journal of Scientific and Research Publications"},{"key":"10.3233\/JIFS-210854_ref16","unstructured":"Praveen P. , (PDF) An Efficient Linkage Criterion for Creating Clusters in Hierarchical Method, 12(5) (2019), 294\u2013300."},{"issue":"1","key":"10.3233\/JIFS-210854_ref17","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","article-title":"The Pascal Visual Object Classes Challenge: A Retrospective","volume":"111","author":"Everingham","year":"2015","journal-title":"Int J Comput Vis"},{"key":"10.3233\/JIFS-210854_ref18","doi-asserted-by":"crossref","unstructured":"Rubinstein M. , Joulin A. , Kopf J. , Liu C. , Unsupervised joint object discovery and segmentation in internet images, Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, pp. 1939\u20131946, 2013.","DOI":"10.1109\/CVPR.2013.253"},{"key":"10.3233\/JIFS-210854_ref19","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.patcog.2018.10.022","article-title":"Unsupervised object discovery and co-localization by deep descriptor transformation","volume":"88","author":"Wei","year":"2019","journal-title":"Pattern Recognit"},{"key":"10.3233\/JIFS-210854_ref20","doi-asserted-by":"crossref","unstructured":"Joulin A. , Bach F. , Ponce J. , Discriminative clustering for image co-segmentation, Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, pp. 1943\u20131950, 2010.","DOI":"10.1109\/CVPR.2010.5539868"},{"key":"10.3233\/JIFS-210854_ref21","doi-asserted-by":"crossref","unstructured":"Joulin A. , Bach F. , Sup E.N. , Multi-Class Cosegmentation, pp. 542\u2013549, 2012.","DOI":"10.1109\/CVPR.2012.6247719"},{"issue":"3","key":"10.3233\/JIFS-210854_ref22","first-page":"275","article-title":"Weakly supervised localization and learning with generic knowledge","volume":"100","author":"Deselaers","year":"2012","journal-title":"Int J ComputVis"},{"issue":"1","key":"10.3233\/JIFS-210854_ref23","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/TIP.2017.2718667","article-title":"Knowledge-Based Topic Model for Unsupervised Object Discovery and Localization","volume":"27","author":"Niu","year":"2018","journal-title":"IEEE TransImage Process"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-210854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T01:54:01Z","timestamp":1769997241000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-210854"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,15]]},"references-count":23,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/jifs-210854","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,15]]}}}