{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T02:34:17Z","timestamp":1792290857180,"version":"4.4.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6220223"],"award-info":[{"award-number":["6220223"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008045","name":"Nanjing University of Information Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008045","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1016\/j.patcog.2023.109891","type":"journal-article","created":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T20:45:24Z","timestamp":1692045924000},"page":"109891","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":19,"special_numbering":"C","title":["Motional foreground attention-based video crowd counting"],"prefix":"10.1016","volume":"144","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6638-0152","authenticated-orcid":false,"given":"Miaogen","family":"Ling","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhang","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9360-8653","authenticated-orcid":false,"given":"Yi","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5083-7552","authenticated-orcid":false,"given":"Ke","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7729-0622","authenticated-orcid":false,"given":"Xin","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2023.109891_b1","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"589","article-title":"Single-image crowd counting via multi-column convolutional neural network","author":"Zhang","year":"2016"},{"key":"10.1016\/j.patcog.2023.109891_b2","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1091","article-title":"Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes","author":"Li","year":"2018"},{"key":"10.1016\/j.patcog.2023.109891_b3","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"19628","article-title":"Boosting crowd counting via multifaceted attention","author":"Lin","year":"2022"},{"key":"10.1016\/j.patcog.2023.109891_b4","series-title":"IEEE International Conference on Computer Vision","first-page":"5151","article-title":"Spatiotemporal modeling for crowd counting in videos","author":"Xiong","year":"2017"},{"key":"10.1016\/j.patcog.2023.109891_b5","series-title":"IEEE International Conference on Multimedia and Expo","first-page":"814","article-title":"Locality-constrained spatial transformer network for video crowd counting","author":"Fang","year":"2019"},{"issue":"11","key":"10.1016\/j.patcog.2023.109891_b6","doi-asserted-by":"crossref","first-page":"5691","DOI":"10.1109\/TIP.2019.2922818","article-title":"Indoor crowd counting by mixture of gaussians label distribution learning","volume":"28","author":"Ling","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2023.109891_b7","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4036","article-title":"Residual regression with semantic prior for crowd counting","author":"Wan","year":"2019"},{"key":"10.1016\/j.patcog.2023.109891_b8","series-title":"Proceedings of the Asian Conference on Computer Vision","article-title":"Video-based crowd counting using a multi-scale optical flow pyramid network","author":"Hossain","year":"2020"},{"key":"10.1016\/j.patcog.2023.109891_b9","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"11976","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.patcog.2023.109891_b10","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.patcog.2023.109891_b11","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3225","article-title":"Adcrowdnet: An attention-injective deformable convolutional network for crowd understanding","author":"Liu","year":"2019"},{"key":"10.1016\/j.patcog.2023.109891_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109506","article-title":"Multi-task semi-supervised crowd counting via global to local self-correction","volume":"140","author":"Chen","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2023.109891_b13","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1109\/TIP.2019.2928634","article-title":"Ha-ccn: Hierarchical attention-based crowd counting network","volume":"29","author":"Sindagi","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2023.109891_b14","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4706","article-title":"Attention scaling for crowd counting","author":"Jiang","year":"2020"},{"key":"10.1016\/j.patcog.2023.109891_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109585","article-title":"Crowd counting from single images using recursive multi-pathway zooming and foreground enhancement","volume":"141","author":"Ma","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2023.109891_b16","series-title":"IEEE International Conference on Computer Vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"issue":"12","key":"10.1016\/j.patcog.2023.109891_b17","doi-asserted-by":"crossref","first-page":"9056","DOI":"10.1109\/TPAMI.2021.3124956","article-title":"Locating and counting heads in crowds with a depth prior","volume":"44","author":"Lian","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2023.109891_b18","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1821","article-title":"Density map regression guided detection network for rgb-d crowd counting and localization","author":"Lian","year":"2019"},{"key":"10.1016\/j.patcog.2023.109891_b19","series-title":"IEEE International Conference on Computer Vision","first-page":"1130","article-title":"Adaptive density map generation for crowd counting","author":"Wan","year":"2019"},{"key":"10.1016\/j.patcog.2023.109891_b20","series-title":"IEEE International Conference on Computer Vision","first-page":"6142","article-title":"Bayesian loss for crowd count estimation with point supervision","author":"Ma","year":"2019"},{"key":"10.1016\/j.patcog.2023.109891_b21","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1974","article-title":"A generalized loss function for crowd counting and localization","author":"Wan","year":"2021"},{"key":"10.1016\/j.patcog.2023.109891_b22","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1093","article-title":"Flow mosaicking: Real-time pedestrian counting without scene-specific learning","author":"Cong","year":"2009"},{"key":"10.1016\/j.patcog.2023.109891_b23","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2539","article-title":"Crossing the line: Crowd counting by integer programming with local features","author":"Ma","year":"2013"},{"issue":"10","key":"10.1016\/j.patcog.2023.109891_b24","doi-asserted-by":"crossref","first-page":"3016","DOI":"10.1016\/j.patcog.2015.04.001","article-title":"Large scale crowd analysis based on convolutional neural network","volume":"48","author":"Cao","year":"2015","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2023.109891_b25","series-title":"European Conference on Computer Vision","first-page":"712","article-title":"Crossing-line crowd counting with two-phase deep neural networks","author":"Zhao","year":"2016"},{"key":"10.1016\/j.patcog.2023.109891_b26","series-title":"Advances in Neural Information Processing Systems, Vol. 28","article-title":"Spatial transformer networks","author":"Jaderberg","year":"2015"},{"key":"10.1016\/j.patcog.2023.109891_b27","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3054","article-title":"Video prediction recalling long-term motion context via memory alignment learning","author":"Lee","year":"2021"},{"key":"10.1016\/j.patcog.2023.109891_b28","series-title":"Machine Vision, Vol. 5","author":"Jain","year":"1995"},{"issue":"3","key":"10.1016\/j.patcog.2023.109891_b29","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2023.109891_b30","series-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"10.1016\/j.patcog.2023.109891_b31","series-title":"IEEE International Conference on Computer Vision","first-page":"1026","article-title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","author":"He","year":"2015"},{"key":"10.1016\/j.patcog.2023.109891_b32","series-title":"International Conference on Learning Representations","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2018"},{"issue":"3","key":"10.1016\/j.patcog.2023.109891_b33","doi-asserted-by":"crossref","first-page":"1357","DOI":"10.1109\/TPAMI.2020.3022878","article-title":"Kernel-based density map generation for dense object counting","volume":"44","author":"Wan","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2023.109891_b34","series-title":"Advances in Neural Information Processing Systems, Vol. 33","first-page":"1595","article-title":"Distribution matching for crowd counting","author":"Wang","year":"2020"},{"key":"10.1016\/j.patcog.2023.109891_b35","series-title":"British Machine Vision Conference, Vol. 1","first-page":"3","article-title":"Feature mining for localised crowd counting","author":"Chen","year":"2012"},{"key":"10.1016\/j.patcog.2023.109891_b36","series-title":"IEEE International Conference on Computer Vision","first-page":"3253","article-title":"Count forest: Co-voting uncertain number of targets using random forest for crowd density estimation","author":"Pham","year":"2015"},{"issue":"8","key":"10.1016\/j.patcog.2023.109891_b37","doi-asserted-by":"crossref","first-page":"1788","DOI":"10.1109\/TCSVT.2016.2637379","article-title":"Crowd counting via weighted VLAD on a dense attribute feature map","volume":"28","author":"Sheng","year":"2016","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2023.109891_b38","series-title":"IEEE Winter Conference on Applications of Computer Vision","first-page":"1","article-title":"Crowd density estimation based on rich features and random projection forest","author":"Xu","year":"2016"},{"key":"10.1016\/j.patcog.2023.109891_b39","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1","article-title":"Privacy preserving crowd monitoring: Counting people without people models or tracking","author":"Chan","year":"2008"},{"key":"10.1016\/j.patcog.2023.109891_b40","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5744","article-title":"Switching convolutional neural network for crowd counting","author":"Babu Sam","year":"2017"},{"key":"10.1016\/j.patcog.2023.109891_b41","series-title":"International Conference on Machine Learning","first-page":"1012","article-title":"Learning Gaussian processes from multiple tasks","author":"Yu","year":"2005"},{"key":"10.1016\/j.patcog.2023.109891_b42","series-title":"IEEE International Conference on Computer Vision","first-page":"2256","article-title":"From semi-supervised to transfer counting of crowds","author":"Change Loy","year":"2013"},{"key":"10.1016\/j.patcog.2023.109891_b43","series-title":"IEEE International Conference on Computer Vision","first-page":"4175","article-title":"Bayesian model adaptation for crowd counts","author":"Liu","year":"2015"}],"updated-by":[{"DOI":"10.1016\/j.patcog.2026.113153","type":"erratum","label":"Erratum","source":"publisher","updated":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000}}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320323005897?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320323005897?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:50:00Z","timestamp":1777434600000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320323005897"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":43,"alternative-id":["S0031320323005897"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2023.109891","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2023,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Motional foreground attention-based video crowd counting","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2023.109891","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"109891"}}