{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T09:09:40Z","timestamp":1777626580968,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Southeast University Start-Up Grant for New Faculty","award":["RF1028623063"],"award-info":[{"award-number":["RF1028623063"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0117900"],"award-info":[{"award-number":["2022ZD0117900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236010"],"award-info":[{"award-number":["62236010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276261"],"award-info":[{"award-number":["62276261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3286710","type":"journal-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T17:37:16Z","timestamp":1687282636000},"page":"3622-3633","source":"Crossref","is-referenced-by-count":48,"title":["Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1180-3362","authenticated-orcid":false,"given":"Chong","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7094-3838","authenticated-orcid":false,"given":"Yuqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9464-1778","authenticated-orcid":false,"given":"Hongsong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4141-7833","authenticated-orcid":false,"given":"Weihua","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7320-1119","authenticated-orcid":false,"given":"Fan","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8239-7229","authenticated-orcid":false,"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4930-8976","authenticated-orcid":false,"given":"Yi-Dong","family":"Shen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-8647","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref59","first-page":"4514","article-title":"Probing inter-modality: Visual parsing with self-attention for vision-and-language pre-training","volume":"34","author":"xue","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3499027"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"ref55","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume":"33","author":"gan","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.43"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00800"},{"key":"ref50","first-page":"29406","article-title":"Learning with noisy correspondence for cross-modal matching","volume":"34","author":"huang","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"ref45","first-page":"2250","article-title":"Matching image and sentence with multi-faceted representations","volume":"30","author":"ma","year":"2020","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2985716"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.374"},{"key":"ref44","year":"0","journal-title":"State-of-the-Art Natural Language Processing for Jax PyTorch and TensorFlow"},{"key":"ref43","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127346"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3293318"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.11"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2837386"},{"key":"ref3","first-page":"3848","article-title":"TN-ZSTAD: Transferable network for zero-shot temporal activity detection","volume":"45","author":"zhang","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137605"},{"key":"ref5","first-page":"3918","article-title":"Video pivoting unsupervised multi-modal machine translation","volume":"45","author":"li","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_43"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref34","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref31","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"arXiv 2103 00020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3123553"},{"key":"ref33","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"li","year":"2019","journal-title":"arXiv 1908 03557"},{"key":"ref32","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"jia","year":"2021","journal-title":"arXiv 2102 05918"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref39","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref67","first-page":"1","article-title":"Contrastive language-image pre-training with knowledge graphs","author":"pan","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref63","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"li","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531826"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038354"},{"key":"ref60","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","author":"kim","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"ref61","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"huang","year":"2020","journal-title":"arXiv 2004 00849"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10158512.pdf?arnumber=10158512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T18:01:07Z","timestamp":1690221667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10158512\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3286710","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}