{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:25:40Z","timestamp":1740101140552,"version":"3.37.3"},"reference-count":24,"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"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956260","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"1536-1542","source":"Crossref","is-referenced-by-count":0,"title":["Post-Attention Modulator for Dense Video Captioning"],"prefix":"10.1109","author":[{"given":"Zixin","family":"Guo","sequence":"first","affiliation":[{"name":"Aalto University,School of Science,Department of Computer Science,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tzu-Jui Julius","family":"Wang","sequence":"additional","affiliation":[{"name":"Aalto University,School of Science,Department of Computer Science,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jorma","family":"Laaksonen","sequence":"additional","affiliation":[{"name":"Aalto University,School of Science,Department of Computer Science,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"958","article-title":"Multi-modal dense video captioning","author":"iashin","year":"2020","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref13","article-title":"COOT: Cooperative hierarchical transformer for video-text representation learning","author":"ging","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1117"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref17"},{"article-title":"Attention is not all you need: Pure attention loses rank doubly exponentially with depth","year":"2021","author":"dong","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref8","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-2122-1"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref9","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long and Short Papers)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref22","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLR (Poster)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"}],"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\/09956260.pdf?arnumber=9956260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:03:32Z","timestamp":1671480212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956260","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}