{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:07:08Z","timestamp":1761898028733},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10688342","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["CoVLR: Coordinating Cross-Modal Consistency and Intra-Modal Relations for Vision-Language Retrieval"],"prefix":"10.1109","author":[{"given":"Fengqiang","family":"Wan","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Guan","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"VSE++: improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2018","journal-title":"BMVC"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2932666"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3080293"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/454"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3530-7"},{"key":"ref10","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref11","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref12","first-page":"6704","article-title":"Cyclip: Cyclic contrastive language-image pretraining","author":"Goel","year":"2022","journal-title":"NeurIPS"},{"key":"ref13","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017","journal-title":"ICML"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01637"},{"key":"ref15","first-page":"1","article-title":"Multimodal model-agnostic meta-learning via task-aware modulation","author":"Vuorio","year":"2019","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10688342.pdf?arnumber=10688342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:41:38Z","timestamp":1727764898000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10688342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10688342","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}