{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T14:21:35Z","timestamp":1774621295315,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000857","name":"Loughborough University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000857","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10223172","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"2220-2224","source":"Crossref","is-referenced-by-count":6,"title":["A Multi-Modal Transformer Approach for Football Event Classification"],"prefix":"10.1109","author":[{"given":"Yixiao","family":"Zhang","sequence":"first","affiliation":[{"name":"Loughborough University,Department of Computer Science,United Kingdom,LE11 3TU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baihua","family":"Li","sequence":"additional","affiliation":[{"name":"Loughborough University,Department of Computer Science,United Kingdom,LE11 3TU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Fang","sequence":"additional","affiliation":[{"name":"Loughborough University,Department of Computer Science,United Kingdom,LE11 3TU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinggang","family":"Meng","sequence":"additional","affiliation":[{"name":"Loughborough University,Department of Computer Science,United Kingdom,LE11 3TU"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-08806-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA52953.2021.00054"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103557"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247917"},{"key":"ref5","article-title":"Automated camera ranking and selection using video content and scene context","volume-title":"Ph.D. thesis","author":"Daniyal","year":"2012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-020-00957-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1213\/2\/022009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00508"},{"key":"ref9","article-title":"Truly multi-modal youtube-8m video classification with video, audio, and text","author":"Wang","year":"2017"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00511"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechmachtheory.2022.105090"},{"key":"ref18","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462877"},{"key":"ref20","article-title":"Yolov4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2023,10,8]]},"end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10223172.pdf?arnumber=10223172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T20:55:58Z","timestamp":1709326558000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10223172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10223172","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}