{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T21:59:53Z","timestamp":1725746393658},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956129","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"2532-2538","source":"Crossref","is-referenced-by-count":1,"title":["PETA: Photo Albums Event Recognition using Transformers Attention"],"prefix":"10.1109","author":[{"given":"Tamar","family":"Glaser","sequence":"first","affiliation":[{"name":"Alibaba Group,DAMO Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuel","family":"Ben-Baruch","sequence":"additional","affiliation":[{"name":"Alibaba Group,DAMO Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gilad","family":"Sharir","sequence":"additional","affiliation":[{"name":"Alibaba Group,DAMO Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadav","family":"Zamir","sequence":"additional","affiliation":[{"name":"Alibaba Group,DAMO Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asaf","family":"Noy","sequence":"additional","affiliation":[{"name":"Alibaba Group,DAMO Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihi","family":"Zelnik-Manor","sequence":"additional","affiliation":[{"name":"Alibaba Group,DAMO Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Gaussian error linear units (gelus)","author":"hendrycks","year":"2016","journal-title":"arXiv preprint arXiv 1606 08415"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","article-title":"An Image is Worth 16x16 Words, What is a Video Worth?","author":"sharir","year":"2021","journal-title":"arXiv preprint arXiv 2103 13111"},{"key":"ref32","article-title":"Stand-alone self-attention in vision models","author":"ramachandran","year":"2019","journal-title":"arXiv preprint arXiv 1906 05190"},{"key":"ref31","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recog-nition at Scale","author":"dosovitskiy","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref30","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00144"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777664"},{"key":"ref40","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv preprint arXiv 1607 06450"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2018.2.VIPC-173"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.07.009"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207675"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.11.078"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-020-00119-z"},{"year":"2011","author":"tsai","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.151"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.520"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3199668"},{"journal-title":"ImageNet-21K Pretraining for the Masses","year":"2021","author":"ridnik","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3306240"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-44584-3_33"},{"key":"ref29","article-title":"Places: A 10 million Image Database for Scene Recognition","author":"zhou","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2019.05.012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2016.7906036"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093547"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451334"},{"key":"ref9","first-page":"1","article-title":"Event recognition in personal photo collections using hierarchical model and multiple features","author":"guo","year":"2015","journal-title":"2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001417540040"},{"key":"ref20","article-title":"Recog-nizing and Curating Photo Albums via Event-Specific Image Importance","author":"wang","year":"2017","journal-title":"BMVC"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.80"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00297"},{"key":"ref41","article-title":"Asymmetric loss for multi-label classification","author":"ben-baruch","year":"2020","journal-title":"arXiv preprint arXiv 2009 14406"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298768"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956129.pdf?arnumber=9956129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:04:05Z","timestamp":1671480245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956129","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}