{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:42:40Z","timestamp":1774366960947,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&amp;D Program of China","award":["2021ZD0112001"],"award-info":[{"award-number":["2021ZD0112001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61831005"],"award-info":[{"award-number":["61831005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871087"],"award-info":[{"award-number":["61871087"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971095"],"award-info":[{"award-number":["61971095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3192729","type":"journal-article","created":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T19:33:16Z","timestamp":1658345596000},"page":"5400-5412","source":"Crossref","is-referenced-by-count":10,"title":["What Happens in Crowd Scenes: A New Dataset About Crowd Scenes for Image Captioning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3745-0262","authenticated-orcid":false,"given":"Lanxiao","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7481-095X","authenticated-orcid":false,"given":"Hongliang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7941-231X","authenticated-orcid":false,"given":"Wenzhe","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9313-8428","authenticated-orcid":false,"given":"Xiaoliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0963-0311","authenticated-orcid":false,"given":"Heqian","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3016-2567","authenticated-orcid":false,"given":"Fanman","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2936-6340","authenticated-orcid":false,"given":"Qingbo","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10475"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2984093"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01076"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3020691"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2980945"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00320"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3044219"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17551"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16314"},{"key":"ref17","article-title":"Crowdhuman: A benchmark for detecting human in a crowd","author":"Shao","year":"2018","journal-title":"arXiv:1805.00123"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00772"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.356"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00859"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2915033"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3093725"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3072479"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976552"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990074"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951226"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref41","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst., 28th Annu. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref45","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref47","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":""},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478331"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09834140.pdf?arnumber=9834140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:10:01Z","timestamp":1705021801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9834140\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3192729","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}