{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T10:07:27Z","timestamp":1784282847326,"version":"3.55.0"},"reference-count":22,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icmew56448.2022.9859304","type":"proceedings-article","created":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T15:52:02Z","timestamp":1661269922000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Transformer Based Multimodal Scene Recognition in Soccer Videos"],"prefix":"10.1109","author":[{"given":"Yaozong","family":"Gan","sequence":"first","affiliation":[{"name":"Hokkaido University,Graduate School of Information Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ren","family":"Togo","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takahiro","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miki","family":"Haseyama","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2016"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"2021"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proceedings of International Conference on Learning Representations"},{"key":"ref14","article-title":"A survey on visual transformer","author":"han","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00508"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.812758"},{"key":"ref17","first-page":"ii","article-title":"Creating audio keywords for event detection in soccer video","volume":"2","author":"xu","year":"2003","journal-title":"Proceedings of the International Conference on Multimedia and Expo"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref19","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","author":"akbari","year":"2021","journal-title":"Proceedings of the Thirty-Fifth Conference on Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00307"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.03.008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3347318.3355515"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00227"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3444685.3446280"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00506"},{"key":"ref2","article-title":"Global sports market - total revenue from 2005 to 2017","author":"kearney","year":"2017"},{"key":"ref1","article-title":"Market size of the european professional soccer market from 2006\/07 to 2019\/20","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00456"},{"key":"ref20","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref22","first-page":"4489","article-title":"Learning spatiotemporal features with 3d convolutional networks","author":"tran","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","location":"Taipei City, Taiwan","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859264\/9859265\/09859304.pdf?arnumber=9859304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T15:59:43Z","timestamp":1662998383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icmew56448.2022.9859304","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}