{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T14:23:50Z","timestamp":1780410230894,"version":"3.54.1"},"reference-count":91,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62072021"],"award-info":[{"award-number":["62072021"]}],"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":[[2025,1]]},"DOI":"10.1109\/tcsvt.2024.3452418","type":"journal-article","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T18:01:47Z","timestamp":1725040907000},"page":"75-90","source":"Crossref","is-referenced-by-count":4,"title":["A Masked Reference Token Supervision-Based Iterative Visual-Language Framework for Robust Visual Grounding"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8955-9964","authenticated-orcid":false,"given":"Chunlei","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Electronics and Information Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5180-7889","authenticated-orcid":false,"given":"Wenquan","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9769-7083","authenticated-orcid":false,"given":"Shuchang","family":"Lyu","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8686-9513","authenticated-orcid":false,"given":"Guangliang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Liverpool, Liverpool, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0550-8247","authenticated-orcid":false,"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[{"name":"S-Laboratory, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6590-0016","authenticated-orcid":false,"given":"Binghao","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3508-027X","authenticated-orcid":false,"given":"Qi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref2","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00206"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/96"},{"key":"ref7","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. NeurIPS","author":"Karpathy"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00236-021-00400-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105734"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00501"},{"key":"ref20","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. NeurIPS","author":"Lu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060713"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2023","journal-title":"arXiv:2304.06718"},{"key":"ref28","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv:2306.14824"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3267115"},{"key":"ref31","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv:2104.13921"},{"key":"ref32","article-title":"Open-vocabulary object detection upon frozen vision and language models","volume-title":"Proc. ICLR","author":"Kuo"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263468"},{"key":"ref38","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"Chen","year":"2018","journal-title":"arXiv:1812.03426"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref40","article-title":"TransVG++: End-to-end visual grounding with language conditioned vision transformer","author":"Deng","year":"2022","journal-title":"arXiv:2206.06619"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01244"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01277"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25331"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01276"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3374786"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328185"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339628"},{"key":"ref48","article-title":"OV-VG: A benchmark for open-vocabulary visual grounding","author":"Wang","year":"2023","journal-title":"arXiv:2310.14374"},{"key":"ref49","first-page":"47052","article-title":"A spectral theory of neural prediction and alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Canatar"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3371348"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00747"},{"key":"ref52","article-title":"Benchmarking the robustness of instance segmentation models","author":"Altindis","year":"2021","journal-title":"arXiv:2109.01123"},{"key":"ref53","article-title":"Towards robust referring image segmentation","author":"Wu","year":"2022","journal-title":"arXiv:2209.09554"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00885"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref56","article-title":"Transformer-based visual segmentation: A survey","author":"Li","year":"2023","journal-title":"arXiv:2304.09854"},{"key":"ref57","article-title":"EATFormer: Improving vision transformer inspired by evolutionary algorithm","author":"Zhang","year":"2022","journal-title":"arXiv:2206.09325"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01280"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"ref61","article-title":"PanopticPartFormer++: A unified and decoupled view for panoptic part segmentation","author":"Li","year":"2023","journal-title":"arXiv:2301.00954"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref63","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. NeurIPS","author":"Cheng"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_31"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3099483"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3271905"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00445"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00218"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref71","article-title":"Uni-perceiver: Pre-training unified architecture for generic perception for zero-shot and few-shot tasks","author":"Zhu","year":"2021","journal-title":"arXiv:2112.01522"},{"key":"ref72","article-title":"Uni-Perceiver-MoE: Learning sparse generalist models with conditional MoEs","author":"Zhu","year":"2022","journal-title":"arXiv:2206.04674"},{"key":"ref73","article-title":"Towards open vocabulary learning: A survey","author":"Wu","year":"2023","journal-title":"arXiv:2306.15880"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02005"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3274228"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3103922"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3594670"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD57460.2023.10152629"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref85","volume-title":"Natural Language Processing With Python","author":"Bird","year":"2009"},{"key":"ref86","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","volume":"1","author":"Devlin"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref90","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. AISTATS","author":"Glorot"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10857816\/10659810.pdf?arnumber=10659810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T05:46:06Z","timestamp":1738215966000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10659810\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":91,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3452418","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}