{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:12:34Z","timestamp":1783527154884,"version":"3.55.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406090"],"award-info":[{"award-number":["62406090"]}],"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":["U22A2095"],"award-info":[{"award-number":["U22A2095"]}],"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":["62276281"],"award-info":[{"award-number":["62276281"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tcsvt.2024.3460482","type":"journal-article","created":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T14:55:02Z","timestamp":1726239302000},"page":"713-727","source":"Crossref","is-referenced-by-count":8,"title":["Learning Crowd Scale and Distribution for Weakly Supervised Crowd Counting and Localization"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7381-0299","authenticated-orcid":false,"given":"Yaowu","family":"Fan","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8198-1629","authenticated-orcid":false,"given":"Jia","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0165-8416","authenticated-orcid":false,"given":"Andy J.","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2837153"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2875002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2021.100023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600799CM"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.03.002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00120"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00524"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00527"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208714"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3241175"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3203870"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02075"},{"key":"ref15","first-page":"3386","article-title":"Modeling noisy annotations for crowd counting","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3299753"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00839"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124272"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01365-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747070"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89131-2_5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108484"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref24","article-title":"Diffusion-based data augmentation for object counting problems","author":"Wang","year":"2024","journal-title":"arXiv:2401.13992"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3146459"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3137593"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3179824"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3445-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107616"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109830"},{"key":"ref31","article-title":"Joint CNN and transformer network via weakly supervised learning for efficient crowd counting","author":"Wang","year":"2022","journal-title":"arXiv:2203.06388"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475230"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25131"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611793"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095275"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-0027-7"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00663"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2974830"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055632"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459191"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.21"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.329"},{"key":"ref46","first-page":"1324","article-title":"Learning to count objects in images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Lempitsky"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.429"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00443"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611797"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00739"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00624"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"ref53","first-page":"1","article-title":"Distribution matching for crowd counting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-02831-z"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-27299-0"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref58","article-title":"Learning independent instance maps for crowd localization","author":"Gao","year":"2020","journal-title":"arXiv:2012.04164"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00194"},{"key":"ref60","article-title":"DiffusionEngine: Diffusion model is scalable data engine for object detection","author":"Zhang","year":"2023","journal-title":"arXiv:2309.03893"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_23"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00077"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref66","article-title":"DALL-E for detection: Language-driven compositional image synthesis for object detection","author":"Ge","year":"2022","journal-title":"arXiv:2206.09592"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01333"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"ref71","first-page":"3870","article-title":"Incorporating side information by adaptive convolution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Kang"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"ref73","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref74","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref75","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3062481"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10857816\/10680129.pdf?arnumber=10680129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:30Z","timestamp":1767638490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10680129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":76,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3460482","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}