{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:43:25Z","timestamp":1732041805794,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2020B1515020048"],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976250,U1811463"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859777","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"1-6","source":"Crossref","is-referenced-by-count":11,"title":["Multimodal Crowd Counting with Mutual Attention Transformers"],"prefix":"10.1109","author":[{"given":"Zhengtao","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}]},{"given":"Lingbo","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}]},{"given":"Mingzhi","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}]},{"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}]},{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3124956"},{"key":"ref11","first-page":"3052","article-title":"JI-dcf: Joint learning and densely-cooperative fusion framework for rgb-d salient object detection","author":"fu","year":"2020","journal-title":"CVPR"},{"key":"ref12","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"NIPS"},{"journal-title":"ICLRE","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2021","author":"dosovitskiy","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref15","first-page":"532","article-title":"Composition loss for counting, density map estimation and localization in dense crowds","author":"idrees","year":"2018","journal-title":"ECCV"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00624"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00861"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_15"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_17"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00849"},{"key":"ref4","first-page":"1774","article-title":"Crowd counting with deep structured scale integration net-work","author":"liu","year":"2019","journal-title":"ICCV"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19390-8_48"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/118"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.042"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00545"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00259"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00479"},{"key":"ref7","first-page":"2645","article-title":"Efficient crowd counting via structured knowledge trans-fer","author":"liu","year":"2020","journal-title":"ACM MM"},{"key":"ref2","first-page":"1091","article-title":"Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes","author":"li","year":"2018","journal-title":"CVPR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00192"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.70"},{"key":"ref20","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"ECCV"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00468"},{"key":"ref21","first-page":"8741","article-title":"End-to-end video instance seg-mentation with transformers","author":"wang","year":"2021","journal-title":"CVPR"},{"journal-title":"ICLRE","article-title":"Very deep convolutional networks for large-scale image recognition","year":"2015","author":"simonyan","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00147"},{"journal-title":"ICLRE","article-title":"Adam: A method for stochastic optimization","year":"2015","author":"kingma","key":"ref26"},{"journal-title":"ArXiv Preprint","article-title":"Layer normalization","year":"2016","author":"ba","key":"ref25"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2022,7,18]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859777.pdf?arnumber=9859777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:23:59Z","timestamp":1663619039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859777","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}