{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T13:49:23Z","timestamp":1725716963973},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"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":[[2022,12,17]]},"DOI":"10.1109\/bigdata55660.2022.10020823","type":"proceedings-article","created":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T19:35:23Z","timestamp":1674761723000},"page":"2133-2139","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Video BERT for Fast Video Advertisement Retrieval"],"prefix":"10.1109","author":[{"given":"Yi","family":"Yang","sequence":"first","affiliation":[{"name":"Baidu Inc.,Baidu Search Ads (Phoenix Nest),Beijing,China,100193"}]},{"given":"Tan","family":"Yu","sequence":"additional","affiliation":[{"name":"Baidu Research,Cognitive Computing Lab,Washington,USA,98004"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Baidu Search Ads (Phoenix Nest),Beijing,China,100193"}]},{"given":"Zhipeng","family":"Jin","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Baidu Search Ads (Phoenix Nest),Beijing,China,100193"}]},{"given":"Xuewu","family":"Jiao","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Baidu Search Ads (Phoenix Nest),Beijing,China,100193"}]},{"given":"Yi","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Baidu Search Ads (Phoenix Nest),Beijing,China,100193"}]},{"given":"Shuanglong","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Baidu Search Ads (Phoenix Nest),Beijing,China,100193"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Research,Cognitive Computing Lab,Washington,USA,98004"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1007\/978-3-642-15561-1_2"},{"volume-title":"BMVC","author":"Faghri","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1145\/997817.997857"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/cvpr.2015.7298862"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1609\/aaai.v30i1.10235"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/tpami.2010.57"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1609\/aaai.v30i1.10455"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1007\/978-3-030-01246-5_12"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/tpami.2014.2361319"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1007\/BF01759061"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1145\/3219819.3219826"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/tpami.2018.2889473"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ICCV.2019.00756"},{"volume-title":"NIPS","author":"Lu","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","key":"ref14"},{"volume-title":"NIPS","author":"Frome","article-title":"Devise: A deep visual-semantic embedding model","key":"ref15"},{"volume-title":"NIPS","author":"De Vries","article-title":"Modulating early visual processing by language","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICCV.2015.301"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2017.347"},{"volume-title":"NAACL","author":"Devlin","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.18653\/v1\/D19-1514"},{"year":"2019","author":"Li","article-title":"Visualbert: A simple and performant baseline for vision and language","key":"ref21"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58577-8_7","article-title":"Uniter: Learning universal image-text representations","volume-title":"ECCV","author":"Chen"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1609\/aaai.v34i07.6795"},{"volume-title":"ICLR","author":"Su","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","key":"ref24"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume-title":"NIPS","author":"Ren"},{"volume-title":"NIPS","author":"Vaswani","article-title":"Attention is all you need","key":"ref26"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1007\/s11263-016-0981-7"}],"event":{"name":"2022 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2022,12,17]]},"location":"Osaka, Japan","end":{"date-parts":[[2022,12,20]]}},"container-title":["2022 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10020192\/10020156\/10020823.pdf?arnumber=10020823","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:01:20Z","timestamp":1707811280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10020823\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,17]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/bigdata55660.2022.10020823","relation":{},"subject":[],"published":{"date-parts":[[2022,12,17]]}}}