{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:07:49Z","timestamp":1780589269619,"version":"3.54.1"},"reference-count":15,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Science and Technology Innovation 2030 \u201cNew Generation Artificial Intelligence\u201d Project","award":["2021ZD0112904"],"award-info":[{"award-number":["2021ZD0112904"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. II"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tcsii.2023.3302801","type":"journal-article","created":{"date-parts":[[2023,8,8]],"date-time":"2023-08-08T13:48:42Z","timestamp":1691502522000},"page":"475-479","source":"Crossref","is-referenced-by-count":2,"title":["Enhanced Cross-Modal Transformer Model for Video Semantic Similarity Measurement"],"prefix":"10.1109","volume":"71","author":[{"given":"Da","family":"Li","sequence":"first","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7867-2112","authenticated-orcid":false,"given":"Boqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5997-5169","authenticated-orcid":false,"given":"Kele","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3222-2268","authenticated-orcid":false,"given":"Sen","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Microbiology and Epidemiology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaimin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"CIKM 2021 AnalytiCup track 1 multimodal video understanding datasets","author":"Demartini","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2753232"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1152"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref5","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref6","article-title":"Learning spatiotemporal features via video and text pair discrimination","author":"Li","year":"2020","journal-title":"arXiv:2001.05691"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_19"},{"key":"ref8","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Su"},{"key":"ref9","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3379998"},{"key":"ref11","article-title":"ImageBERT: Cross-modal pre-training with large-scale weak-supervised image-text data","author":"Qi","year":"2020","journal-title":"arXiv:2001.07966"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref14","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"arXiv:2203.12602"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450043"}],"container-title":["IEEE Transactions on Circuits and Systems II: Express Briefs"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8920\/10385034\/10210718.pdf?arnumber=10210718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:09:28Z","timestamp":1769494168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10210718\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":15,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsii.2023.3302801","relation":{},"ISSN":["1549-7747","1558-3791"],"issn-type":[{"value":"1549-7747","type":"print"},{"value":"1558-3791","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}