{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:24:00Z","timestamp":1774419840699,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889372","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Conditional Convolutions for End-to-End Single-Stage Video Text Detection"],"prefix":"10.1109","author":[{"given":"Xiaoge","family":"Song","sequence":"first","affiliation":[{"name":"Nanjing University,Department of Computer Science and Technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danhuai","family":"Zhao","sequence":"additional","affiliation":[{"name":"China Mobile Zijin Innovation Institute,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhu","sequence":"additional","affiliation":[{"name":"China Mobile Zijin Innovation Institute,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kang","family":"Zheng","sequence":"additional","affiliation":[{"name":"China Mobile Zijin Innovation Institute,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Lu","sequence":"additional","affiliation":[{"name":"Nanjing University,Department of Computer Science and Technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206051"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.207"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00764-5_28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333727"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2443556"},{"key":"ref6","article-title":"Condconv: Conditionally parameterized convolutions for efficient inference","author":"Yang","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351093"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2014.6836024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107791"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.62"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116563"},{"key":"ref15","first-page":"2647","article-title":"Scene text detection in video by learning locally and globally","author":"Tian","year":"2016","journal-title":"IJCAI"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2068553"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.03.018"},{"key":"ref24","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889372.pdf?arnumber=10889372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:59Z","timestamp":1774416299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889372\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889372","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}