{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T13:40:47Z","timestamp":1753882847369,"version":"3.41.2"},"reference-count":30,"publisher":"World Scientific Pub Co Pte Ltd","issue":"03","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1813222"],"award-info":[{"award-number":["U1813222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"publisher","award":["F2021202038"],"award-info":[{"award-number":["F2021202038"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2022,3,15]]},"abstract":"<jats:p> Aiming to obtain more discriminative features in scene images and overcome the impacts of intra-class differences and inter-class similarities, the paper proposes a scene recognition method that combines attention and context information. First, we introduce the attention mechanism and build a multi-scale attention model. Discriminative information considers salient objects and regions by means of channel attention and spatial attention. Besides, the central loss function joint supervision strategy is introduced to further reduce the misjudgment of intra-class differences. Second, a model based on multi-level context information is proposed to describe the positional relationship between objects, which can effectively alleviate the influence of the similarity of objects between classes. Finally, the two models are merged to give full play to the compatibility of features, so that the final feature representation not only focuses on the effective discriminant information, but also manifests the relative position relationship between significant objects. Extensive experiments have proved that the method in this paper effectively solves the problem of insufficient feature representation in scene recognition tasks, and improves the accuracy of scene recognition. <\/jats:p>","DOI":"10.1142\/s0218001422500148","type":"journal-article","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T11:42:16Z","timestamp":1647258136000},"source":"Crossref","is-referenced-by-count":1,"title":["Fusing Attention Features and Contextual Information for Scene Recognition"],"prefix":"10.1142","volume":"36","author":[{"given":"Yuqing","family":"Peng","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, P. R. China"}]},{"given":"Xianzi","family":"Liu","sequence":"additional","affiliation":[{"name":"China Shenhua International Engineering Co., Ltd., Beijing 100007, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8910-9501","authenticated-orcid":false,"given":"Chenxi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, P. R. China"}]},{"given":"Tengfei","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, P. R. China"}]},{"given":"Tiejun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Hebei University of Technology, Tianjin 300401, P. R. China"}]}],"member":"219","published-online":{"date-parts":[[2022,3,12]]},"reference":[{"doi-asserted-by":"publisher","key":"S0218001422500148BIB001","DOI":"10.1016\/j.eswa.2018.08.056"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB002","DOI":"10.1109\/TCSVT.2002.808079"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB003","DOI":"10.1109\/TIP.2020.2986599"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB004","DOI":"10.1109\/CVPR.2015.7298721"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB005","DOI":"10.1016\/j.patcog.2017.09.025"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB006","DOI":"10.1109\/TIP.2016.2629443"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB007","DOI":"10.1016\/j.cviu.2012.10.005"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB008","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB009","DOI":"10.1109\/TIP.2016.2567076"},{"key":"S0218001422500148BIB010","first-page":"1106","volume-title":"Advances in Neural Information Processing Systems","volume":"25","author":"Krizhevsky A.","year":"2012"},{"issue":"3","key":"S0218001422500148BIB011","first-page":"600","volume":"46","author":"Li Y.-D.","year":"2017","journal-title":"J. Univ. Electron. Sci. Technol. China"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB012","DOI":"10.1016\/j.patcog.2020.107256"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB013","DOI":"10.1016\/B978-012375731-9\/50045-8"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB014","DOI":"10.1109\/CVPR.2009.5206537"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB016","DOI":"10.1109\/TCSVT.2018.2848543"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB017","DOI":"10.1109\/FSKD.2017.8393385"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB018","DOI":"10.1109\/CVPR.2015.7298594"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB019","DOI":"10.1016\/j.neucom.2016.11.023"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB020","DOI":"10.1109\/83.892448"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB021","DOI":"10.1109\/TNN.2005.852235"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB022","DOI":"10.1109\/TIP.2017.2675339"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB023","DOI":"10.1109\/TIP.2017.2666739"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB024","DOI":"10.1007\/978-3-319-46478-7_31"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB025","DOI":"10.1109\/ICCV.2015.152"},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB026","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"S0218001422500148BIB027","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1109\/CVPR.2012.6247739","volume-title":"Proc. 2012 IEEE Conf. Computer Vision and Pattern Recognition","author":"Yao J.","year":"2012"},{"issue":"7","key":"S0218001422500148BIB028","first-page":"2008","volume":"37","author":"Ye L.","year":"2017","journal-title":"J. Comput. Appl."},{"issue":"13","key":"S0218001422500148BIB029","first-page":"26","volume":"36","author":"Yu L.","year":"2017","journal-title":"Microcomput. Appl."},{"doi-asserted-by":"publisher","key":"S0218001422500148BIB030","DOI":"10.1109\/ICASSP.2018.8461692"},{"key":"S0218001422500148BIB031","first-page":"487","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Zhou B.","year":"2014"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001422500148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T03:49:01Z","timestamp":1648525741000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0218001422500148"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,12]]},"references-count":30,"journal-issue":{"issue":"03","published-print":{"date-parts":[[2022,3,15]]}},"alternative-id":["10.1142\/S0218001422500148"],"URL":"https:\/\/doi.org\/10.1142\/s0218001422500148","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"type":"print","value":"0218-0014"},{"type":"electronic","value":"1793-6381"}],"subject":[],"published":{"date-parts":[[2022,3,12]]},"article-number":"2250014"}}