{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:28:26Z","timestamp":1770917306513,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412268","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"7699-7706","source":"Crossref","is-referenced-by-count":26,"title":["RMS-Net: Regression and Masking for Soccer Event Spotting"],"prefix":"10.1109","author":[{"given":"Matteo","family":"Tomei","sequence":"first","affiliation":[]},{"given":"Lorenzo","family":"Baraldi","sequence":"additional","affiliation":[]},{"given":"Simone","family":"Calderara","sequence":"additional","affiliation":[]},{"given":"Simone","family":"Bronzin","sequence":"additional","affiliation":[]},{"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref31","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref30","author":"wang","year":"2019","journal-title":"Comprehensive soccer video understanding Towards human-comparable video understanding system in constrained environment"},{"key":"ref35","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","author":"abu-ei-haija","year":"2016","journal-title":"Youtube-8m A large-scale video classification benchmark"},{"key":"ref11","author":"kay","year":"2017","journal-title":"The kinetics human action video dataset"},{"key":"ref12","article-title":"Large-scale video classification with convolutional neural networks","author":"karpathy","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref13","article-title":"Learning spatiotemporal features with 3d convolutional networks","author":"tran","year":"0","journal-title":"Proceedings of the International Conference on Computer Vision"},{"key":"ref14","article-title":"Quo vadis, action recognition? a new model and the kinetics dataset","author":"carreira","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref15","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","article-title":"Long-term temporal convolutions for action recognition","volume":"40","author":"varol","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref17","article-title":"Convolutional two-stream network fusion for video action recognition","author":"feichtenhofer","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref18","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref28","first-page":"896","article-title":"Improved soccer action spotting using both audio and video streams","author":"vanderplaetse","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops"},{"key":"ref4","article-title":"Semantic annotation and transcoding of soccer videos","author":"bertini","year":"0","journal-title":"Asian Conference on Computer Vision"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.16.CVAS-344"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00223"},{"key":"ref6","first-page":"13 126","article-title":"A context-aware loss function for action spotting in soccer videos","author":"cioppa","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2018.00090"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00449"},{"key":"ref8","article-title":"Hmdb: a large video database for human motion recognition","author":"kuehne","year":"0","journal-title":"Proceedings of the International Conference on Computer Vision"},{"key":"ref7","author":"devlin","year":"2018","journal-title":"BERT Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref2","article-title":"A multigrid method for efficiently training video models","author":"wu","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref9","author":"soomro","year":"2012","journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref21","first-page":"3","article-title":"Bsn: Boundary sensitive network for temporal action proposal generation","author":"lin","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2016.0081"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15822-3_20"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","location":"Milan, Italy","start":{"date-parts":[[2021,1,10]]},"end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412268.pdf?arnumber=9412268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:45Z","timestamp":1652197245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412268\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412268","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}