{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:28:17Z","timestamp":1740101297723,"version":"3.37.3"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,11,26]],"date-time":"2022-11-26T00:00:00Z","timestamp":1669420800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,26]],"date-time":"2022-11-26T00:00:00Z","timestamp":1669420800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013096","name":"Science and Technology Project of State Grid","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013096","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,11,26]]},"DOI":"10.1109\/ccis57298.2022.10016349","type":"proceedings-article","created":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T19:08:53Z","timestamp":1674155333000},"page":"383-390","source":"Crossref","is-referenced-by-count":0,"title":["InterCLIP: Adapting CLIP To Interactive Image Retrieval with Triplet Similarity"],"prefix":"10.1109","author":[{"given":"Xi","family":"Chen","sequence":"first","affiliation":[{"name":"State Grid Hebei Information and Telecommunication Branch,Hebei,China,050000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Xin","sequence":"additional","affiliation":[{"name":"State Grid Hebei Information and Telecommunication Branch,Hebei,China,050000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Lu","sequence":"additional","affiliation":[{"name":"State Grid Hebei Information and Telecommunication Branch,Hebei,China,050000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhonghong","family":"Ou","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shi","family":"Lii","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijing","family":"Tian","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghao","family":"Shi","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shihui","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Southampton,Southampton,British"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meina","family":"Song","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Fashion outfit complementary item retrieval","volume":"abs\/1912.08967","author":"Lin","year":"2019","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403372"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299135"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093403"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.244"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00804"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.652"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01156"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01194"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00126"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_19"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.93"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00980"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00840"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00483"},{"key":"ref19","article-title":"Mural: multimodal, multitask retrieval across languages","author":"Jain","year":"2021","journal-title":"arXivpreprint arXiv:2109.05125"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on Machine Learning","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"article-title":"Learning transferable visual models from natural language supervision","year":"2021","author":"Radford","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01115"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref35","article-title":"Rtic: Residual learning for text and image composition using graph convolutional network","author":"Shin","year":"2021","journal-title":"arXiv preprint arXiv:2104.03015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref37"},{"key":"ref38","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv preprint arXiv:1908.03557"},{"key":"ref39","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_43"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_27"},{"issue":"8","key":"ref44","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref46","article-title":"Multimodal residual learning for visual qa","volume":"29","author":"Kim","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref48","first-page":"arXiv:2007.00145","article-title":"Modality-Agnostic Attention Fusion for visual search with text feedback","author":"Dodds","year":"2020","journal-title":"arXiv e-prints"},{"article-title":"The fashion iq dataset: Retrieving images\u2019 by combining side information and relative natural language feedback","year":"2019","author":"Guo","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2665038"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3274-6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3077025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3038776"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2021.09.016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3217397"}],"event":{"name":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","start":{"date-parts":[[2022,11,26]]},"location":"Chengdu, China","end":{"date-parts":[[2022,11,28]]}},"container-title":["2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10016307\/10016308\/10016349.pdf?arnumber=10016349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:41:46Z","timestamp":1707806506000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10016349\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,26]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/ccis57298.2022.10016349","relation":{},"subject":[],"published":{"date-parts":[[2022,11,26]]}}}