{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T20:13:35Z","timestamp":1778184815576,"version":"3.51.4"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441235"],"award-info":[{"award-number":["62441235"]}],"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":["62176178"],"award-info":[{"award-number":["62176178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tcsvt.2025.3642691","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T18:34:28Z","timestamp":1765391668000},"page":"5839-5851","source":"Crossref","is-referenced-by-count":0,"title":["Cyclic Pseudo-Label Generation and Refinement for Weakly Supervised Referring Expression Grounding"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1185-5848","authenticated-orcid":false,"given":"Jiahe","family":"Wu","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2197-3739","authenticated-orcid":false,"given":"Zhong","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8299-5844","authenticated-orcid":false,"given":"Yaodong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4361-956X","authenticated-orcid":false,"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233554"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_25"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3162650"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01851"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281507"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106200"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3348297"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3374786"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058684"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186410"},{"key":"ref16","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref17","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01507"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.802"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00265"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321501"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3551766"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3462100"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3407785"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref27","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3139467"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00425"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3433547"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00476"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01835"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01387"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161294"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111437"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"ref40","first-page":"18123","article-title":"Counterfactual contrastive learning for weakly-supervised vision-language grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Zhang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3311917"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2979010"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.63317\/26mpc9xpon84"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.177"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147385"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00589"},{"key":"ref52","article-title":"DisCLIP: Open-vocabulary referring expression generation","author":"Bracha","year":"2023","journal-title":"arXiv:2305.19108"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref54","first-page":"1","article-title":"PaLI: A jointly-scaled multilingual language-image model","volume-title":"Proc. Int. Conf. Learn. Repr. (ICLR)","author":"Chen"},{"key":"ref55","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Li"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref57","article-title":"LLaMA-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv:2304.15010"},{"key":"ref58","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023","journal-title":"arXiv:2303.16199"},{"key":"ref59","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"issue":"70","key":"ref61","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref62","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Madaan"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535323"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3717574"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324916000334"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2009.03.008"},{"key":"ref73","article-title":"CPT: Colorful prompt tuning for pre-trained vision-language models","author":"Yao","year":"2021","journal-title":"arXiv:2109.11797"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111318"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00263"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00556"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11296906.pdf?arnumber=11296906","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T19:55:58Z","timestamp":1778183758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11296906\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":77,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3642691","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}