{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:56:59Z","timestamp":1781150219527,"version":"3.54.1"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neunet.2026.108983","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T08:15:02Z","timestamp":1775808902000},"page":"108983","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Multi-scale pyramid fusion with overlap density attention module for crowd counting"],"prefix":"10.1016","volume":"201","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6581-8901","authenticated-orcid":false,"given":"Avinash","family":"Rohra","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoqun","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aakash","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajeet Kumar","family":"Bhatia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hazrat","family":"Bilal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanzhe","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2219-3845","authenticated-orcid":false,"given":"Munawar","family":"Ali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108983_bib0043","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"872","article-title":"Localization in the crowd with topological constraints","volume":"35","author":"Abousamra","year":"2021"},{"key":"10.1016\/j.neunet.2026.108983_bib0012","series-title":"2018 25th IEEE international conference on image processing (ICIP)","first-page":"948","article-title":"A-CCNN: Adaptive CCNN for density estimation and crowd counting","author":"Amirgholipour","year":"2018"},{"issue":"6","key":"10.1016\/j.neunet.2026.108983_bib0018","doi-asserted-by":"crossref","first-page":"1221","DOI":"10.1049\/ipr2.12099","article-title":"Crowd counting with segmentation attention convolutional neural network","volume":"15","author":"Chen","year":"2021","journal-title":"IET Image Processing"},{"issue":"2","key":"10.1016\/j.neunet.2026.108983_bib0003","first-page":"3","article-title":"Feature mining for localised crowd counting","volume":"1","author":"Chen","year":"2012","journal-title":"Bmvc"},{"key":"10.1016\/j.neunet.2026.108983_bib0022","series-title":"Proceedings of the 27th ACM international conference on multimedia","first-page":"1897","article-title":"Improving the learning of multi-column convolutional neural network for crowd counting","author":"Cheng","year":"2019"},{"key":"10.1016\/j.neunet.2026.108983_bib0008","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition workshops","first-page":"195","article-title":"An aggregated multicolumn dilated convolution network for perspective-free counting","author":"Deb","year":"2018"},{"issue":"1","key":"10.1016\/j.neunet.2026.108983_bib0039","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1609\/aaai.v37i1.25131","article-title":"Domain-general crowd counting in unseen scenarios","volume":"37","author":"Du","year":"2023","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"9","key":"10.1016\/j.neunet.2026.108983_bib0006","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","article-title":"Object detection with discriminatively trained part-based models","volume":"32","author":"Felzenszwalb","year":"2009","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"10","key":"10.1016\/j.neunet.2026.108983_bib0025","doi-asserted-by":"crossref","first-page":"3486","DOI":"10.1109\/TCSVT.2019.2919139","article-title":"Pcc net: Perspective crowd counting via spatial convolutional network","volume":"30","author":"Gao","year":"2019","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.108983_bib0053","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7542","article-title":"Bi-level alignment for cross-domain crowd counting","author":"Gong","year":"2022"},{"key":"10.1016\/j.neunet.2026.108983_bib0016","series-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"4072","article-title":"Bba-net: A bi-branch attention network for crowd counting","author":"Hou","year":"2020"},{"key":"10.1016\/j.neunet.2026.108983_bib0002","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2547","article-title":"Multi-source multi-scale counting in extremely dense crowd images","author":"Idrees","year":"2013"},{"key":"10.1016\/j.neunet.2026.108983_bib0032","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"532","article-title":"Composition loss for counting, density map estimation and localization in dense crowds","author":"Idrees","year":"2018"},{"key":"10.1016\/j.neunet.2026.108983_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2022.104597","article-title":"Revisiting crowd counting: State-of-the-art, trends, and future perspectives","volume":"129","author":"Khan","year":"2023","journal-title":"Image and Vision Computing"},{"issue":"3","key":"10.1016\/j.neunet.2026.108983_bib0029","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1002\/aaai.12117","article-title":"Visual crowd analysis: Open research problems","volume":"44","author":"Khan","year":"2023","journal-title":"AI Magazine"},{"key":"10.1016\/j.neunet.2026.108983_bib0050","series-title":"2023 IEEE 20th Consumer Communications & Networking Conference (CCNC)","first-page":"455","article-title":"Dronenet: Crowd density estimation using self-onns for drones","author":"Khan","year":"2023"},{"key":"10.1016\/j.neunet.2026.108983_bib0047","first-page":"421","article-title":"Robust crowd counting via image enhancement and dynamic feature selection","author":"Kim","year":"2021","journal-title":"BMVC"},{"key":"10.1016\/j.neunet.2026.108983_bib0020","series-title":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","first-page":"290","article-title":"HTNet: A hybrid model boosted by triple self-attention for crowd counting","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.108983_bib0024","series-title":"Proceedings of the 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.neunet.2026.108983_bib0038","series-title":"European Conference on Computer Vision","first-page":"38","article-title":"An end-to-end transformer model for crowd localization","author":"Liang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108983_bib0017","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19628","article-title":"Boosting crowd counting via multifaceted attention","author":"Lin","year":"2022"},{"issue":"8","key":"10.1016\/j.neunet.2026.108983_bib0013","doi-asserted-by":"crossref","first-page":"1862","DOI":"10.1109\/TPAMI.2019.2899857","article-title":"Exploiting unlabeled data in cnns by self-supervised learning to rank","volume":"41","author":"Liu","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108983_bib0014","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5099","article-title":"Context-aware crowd counting","author":"Liu","year":"2019"},{"key":"10.1016\/j.neunet.2026.108983_bib0037","series-title":"Proceedings of the 2022 ACM SIGSAC conference on computer and communications security","first-page":"2055","article-title":"Harnessing perceptual adversarial patches for crowd counting","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108983_bib0051","series-title":"Proceedings of the IEEE\/CVF 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.neunet.2026.108983_bib0044","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2319","article-title":"Learning to count via unbalanced optimal transport","volume":"35","author":"Ma","year":"2021"},{"key":"10.1016\/j.neunet.2026.108983_bib0048","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"28025","article-title":"Single domain generalization for crowd counting","author":"Peng","year":"2024"},{"issue":"1","key":"10.1016\/j.neunet.2026.108983_bib0049","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s10044-024-01385-7","article-title":"MSFFNet: Multi-scale feature fusion network with semantic optimization for crowd counting","volume":"28","author":"Rohra","year":"2025","journal-title":"Pattern Analysis and Applications"},{"key":"10.1016\/j.neunet.2026.108983_bib0027","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3618","article-title":"Divide and grow: Capturing huge diversity in crowd images with incrementally growing cnn","author":"Sam","year":"2018"},{"key":"10.1016\/j.neunet.2026.108983_bib0007","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"1861","article-title":"Generating high-quality crowd density maps using contextual pyramid cnns","author":"Sindagi","year":"2017"},{"issue":"5","key":"10.1016\/j.neunet.2026.108983_bib0033","first-page":"2594","article-title":"Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method","volume":"44","author":"Sindagi","year":"2020","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"10.1016\/j.neunet.2026.108983_bib0052","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3365","article-title":"Rethinking counting and localization in crowds: A purely point-based framework","author":"Song","year":"2021"},{"key":"10.1016\/j.neunet.2026.108983_bib0021","series-title":"Proceedings of the 2024 8th International Conference on Control Engineering and Artificial Intelligence","first-page":"37","article-title":"Fusion attention mechanic crowd counting network based on Transformer","author":"Su","year":"2024"},{"key":"10.1016\/j.neunet.2026.108983_bib0045","doi-asserted-by":"crossref","first-page":"2714","DOI":"10.1109\/TIP.2019.2952083","article-title":"Padnet: Pan-density crowd counting","volume":"29","author":"Tian","year":"2019","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108983_bib0005","series-title":"IEEE transactions on pattern analysis and machine intelligence","first-page":"1713","article-title":"Pedestrian detection via classification on riemannian manifolds","volume":"30","author":"Tuzel","year":"2008"},{"key":"10.1016\/j.neunet.2026.108983_bib0040","first-page":"3386","article-title":"Modeling noisy annotations for crowd counting","volume":"33","author":"Wan","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108983_bib0036","series-title":"Proceedings of the IEEE\/CVF 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"},{"issue":"1","key":"10.1016\/j.neunet.2026.108983_bib0023","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/TPAMI.2018.2875002","article-title":"Detecting coherent groups in crowd scenes by multiview clustering","volume":"42","author":"Wang","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108983_bib0035","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.1007\/s11042-019-08208-6","article-title":"Multi-scale dilated convolution of convolutional neural network for crowd counting","volume":"79","author":"Wang","year":"2020","journal-title":"Multimedia Tools and Applications"},{"key":"10.1016\/j.neunet.2026.108983_bib0046","first-page":"1595","article-title":"Distribution matching for crowd counting","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"10.1016\/j.neunet.2026.108983_bib0015","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.neucom.2021.01.112","article-title":"Interlayer and intralayer scale aggregation for scale-invariant crowd counting","volume":"441","author":"Wang","year":"2021","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.neunet.2026.108983_bib0026","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s11263-020-01365-4","article-title":"Pixel-wise crowd understanding via synthetic data","volume":"129","author":"Wang","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.108983_bib0041","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"167","article-title":"Dynamic mixture of counter network for location-agnostic crowd counting","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.108983_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2021.104242","article-title":"CFFNet: Coordinated feature fusion network for crowd counting","volume":"112","author":"Xia","year":"2021","journal-title":"Image and Vision Computing"},{"key":"10.1016\/j.neunet.2026.108983_bib0042","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Super-resolution information enhancement for crowd counting","author":"Xie","year":"2023"},{"issue":"21","key":"10.1016\/j.neunet.2026.108983_bib0030","doi-asserted-by":"crossref","first-page":"18930","DOI":"10.1109\/JIOT.2023.3268226","article-title":"Scale-context perceptive network for crowd counting and localization in smart city system","volume":"10","author":"Zhai","year":"2023","journal-title":"IEEE Internet of Things Journal"},{"key":"10.1016\/j.neunet.2026.108983_bib0009","series-title":"IEEE Transactions on Circuits and Systems for Video Technology","article-title":"Zero-shot object counting with vision-language prior guidance network","author":"Zhai","year":"2024"},{"key":"10.1016\/j.neunet.2026.108983_bib0010","series-title":"IEEE Transactions on Circuits and Systems for Video Technology","article-title":"Multi-view gait recognition with joint local multi-scale and global contextual spatio-temporal features","author":"Zhai","year":"2024"},{"issue":"3","key":"10.1016\/j.neunet.2026.108983_bib0031","doi-asserted-by":"crossref","first-page":"5536","DOI":"10.1109\/TCE.2024.3378166","article-title":"Region-aware quantum network for crowd counting","volume":"70","author":"Zhai","year":"2024","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"10.1016\/j.neunet.2026.108983_bib0011","doi-asserted-by":"crossref","DOI":"10.1109\/TITS.2025.3606994","article-title":"Privacy-preserving object counting in lightweight intelligent transportation system","author":"Zhai","year":"2025","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.108983_bib0034","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"833","article-title":"Cross-scene crowd counting via deep convolutional neural networks","author":"Zhang","year":"2015"},{"key":"10.1016\/j.neunet.2026.108983_bib0001","series-title":"Proceedings of the 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"},{"issue":"7","key":"10.1016\/j.neunet.2026.108983_bib0004","doi-asserted-by":"crossref","first-page":"1198","DOI":"10.1109\/TPAMI.2007.70770","article-title":"Segmentation and tracking of multiple humans in crowded environments","volume":"30","author":"Zhao","year":"2008","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004442?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004442?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:04:15Z","timestamp":1781147055000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026004442"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":53,"alternative-id":["S0893608026004442"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108983","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-scale pyramid fusion with overlap density attention module for crowd counting","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108983","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108983"}}