{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T04:09:12Z","timestamp":1768709352907,"version":"3.49.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["62372136"],"award-info":[{"award-number":["62372136"]}],"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":[[2025,6]]},"DOI":"10.1109\/tcsvt.2025.3528657","type":"journal-article","created":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T15:19:09Z","timestamp":1736781549000},"page":"6170-6183","source":"Crossref","is-referenced-by-count":1,"title":["Graph-Based Group Division Network for Referring Expression Comprehension"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2262-6261","authenticated-orcid":false,"given":"Jingcheng","family":"Ke","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0998-251X","authenticated-orcid":false,"given":"Jia","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5214-7114","authenticated-orcid":false,"given":"Waikeung","family":"Wong","sequence":"additional","affiliation":[{"name":"School of Fashion and Textiles, The Hong Kong Polytechnic University, Hong Kong, China"}]},{"given":"Anne","family":"Toomey","sequence":"additional","affiliation":[{"name":"School of Design, Royal College of Art, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9554-2379","authenticated-orcid":false,"given":"Jie","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]}],"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.2021.3085907"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2895511"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2802648"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref13","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1142\/S0219467824500190"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3604557"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3548688"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3297312"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413902"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref25","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Gan"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01837"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3334099"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681071"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3064379"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262578"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174136"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00438"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref39","first-page":"1","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Ordonez"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.181"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref44","article-title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","author":"Johnson","year":"2019","journal-title":"arXiv:1901.07042"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01509"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref47","article-title":"TransVG++: End-to-end visual grounding with language conditioned vision transformer","author":"Deng","year":"2022","journal-title":"arXiv:2206.06619"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref50","article-title":"Crossing the format boundary of text and boxes: Towards unified vision-language modeling","author":"Yang","year":"2021","journal-title":"arXiv:2111.12085"},{"key":"ref51","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Su"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref53","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147385"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3374786"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3407785"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19983"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547765"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28580"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref63","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11027896\/10838591.pdf?arnumber=10838591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:42:11Z","timestamp":1767638531000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10838591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":63,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3528657","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}