{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:35:42Z","timestamp":1740101742047,"version":"3.37.3"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-009"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-001"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096999","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Recurrent Fine-Grained Self-Attention Network for Video Crowd Counting"],"prefix":"10.1109","author":[{"given":"Jifan","family":"Zhang","sequence":"first","affiliation":[{"name":"Peking University,School of Electronic and Computer Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Wu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoli","family":"Song","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University,School of Electronic and Computer Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050059"},{"key":"ref12","first-page":"250","article-title":"Enhanced 3D convolutional networks for crowd counting","author":"zou","year":"2019","journal-title":"Proceedings of the British Machine Vision Conference"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_43"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00145"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.551"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.396"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.70"},{"key":"ref17","first-page":"5998","article-title":"Attention is All you Need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"3","article-title":"Video-Based Crowd Counting Using a Multi-Scale Optical Flow Pyramid Network","author":"hossain","year":"2020","journal-title":"Proceedings of the Asian Conference on Computer Vision"},{"key":"ref19","article-title":"Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting","volume":"abs 2104 13946","author":"bai","year":"2021","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190701"},{"key":"ref24","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"simonyan","year":"2015","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref23","first-page":"68","article-title":"Stand-Alone Self-Attention in Vision Models","volume":"32","author":"ramachandran","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref25","first-page":"1956","article-title":"PHNet: Parasite-Host Network for Video Crowd Counting","author":"meng","year":"2020","journal-title":"Proceedings of the International Conference on Pattern Recognition"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref22","article-title":"Universal Transformers","author":"dehghani","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref21","first-page":"1324","article-title":"Learning To Count Objects in Images","author":"lempitsky","year":"2010","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.21"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00443"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00745"},{"key":"ref9","first-page":"2633","article-title":"Crowd Counting via Perspective-Guided Fractional-Dilation Convolution","author":"yan","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00120"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3043122"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00465"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350881"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096999.pdf?arnumber=10096999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T17:53:39Z","timestamp":1698083619000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096999","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}