{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:56:04Z","timestamp":1786038964411,"version":"3.56.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3205210","type":"journal-article","created":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T19:35:05Z","timestamp":1663184105000},"page":"6032-6047","source":"Crossref","is-referenced-by-count":25,"title":["Video Crowd Localization With Multifocus Gaussian Neighborhood Attention and a Large-Scale Benchmark"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8175-5381","authenticated-orcid":false,"given":"Haopeng","family":"Li","sequence":"first","affiliation":[{"name":"School of Computing and Information Systems, The University of Melbourne, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8179-6685","authenticated-orcid":false,"given":"Lingbo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2724-7268","authenticated-orcid":false,"given":"Kunlin","family":"Yang","sequence":"additional","affiliation":[{"name":"SenseTime Group Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, The University of Melbourne, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-8168","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0294-8538","authenticated-orcid":false,"given":"Bin","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8132-6250","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Graduate School at Shenzhen, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Hou","sequence":"additional","affiliation":[{"name":"SenseTime Group Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-008-0132-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_42"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2837153"},{"key":"ref4","article-title":"NWPU-crowd: A large-scale benchmark for crowd counting and localization","author":"Wang","year":"2020","journal-title":"arXiv:2001.03360"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00186"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00524"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00581"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00104"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6839"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_10"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2928634"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref15","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015","journal-title":"arXiv:1506.01497"},{"key":"ref16","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"Dai","year":"2016","journal-title":"arXiv:1605.06409"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.166"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093445"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00545"},{"key":"ref21","article-title":"CNN-based density estimation and crowd counting: A survey","author":"Gao","year":"2020","journal-title":"arXiv:2003.12783"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00663"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2974830"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00131"},{"key":"ref25","article-title":"Drone-based joint density map estimation, localization and tracking with space-time multi-scale attention network","author":"Wen","year":"2019","journal-title":"arXiv:1912.01811"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.551"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00145"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_43"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.270"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639113"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/PETS-WINTER.2009.5399556"},{"key":"ref35","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref37","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref38","article-title":"A survey on vision transformer","author":"Han","year":"2020","journal-title":"arXiv:2012.12556"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186506"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref41","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref42","first-page":"1","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zaheer"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2740160"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/118"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00120"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2952083"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00465"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049938"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2994410"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009030"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055631"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3043122"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.70"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00624"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16170"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"ref59","article-title":"Counting people by estimating people flows","author":"Liu","year":"2020","journal-title":"arXiv:2012.00452"},{"key":"ref60","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref61","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref62","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004729"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref66","article-title":"Stand-alone self-attention in vision models","author":"Ramachandran","year":"2019","journal-title":"arXiv:1906.05909"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2778563"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2891104"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59722-1_54"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00418"},{"key":"ref72","article-title":"Pre-trained image processing transformer","author":"Chen","year":"2020","journal-title":"arXiv:2012.00364"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM49941.2020.9313305"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref75","first-page":"1","article-title":"Scale mixtures of Gaussians and the statistics of natural images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Wainwright"},{"key":"ref76","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref78","first-page":"1595","article-title":"Distribution matching for crowd counting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013269"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09893023.pdf?arnumber=9893023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:06:49Z","timestamp":1705957609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3205210","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}