{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:50:46Z","timestamp":1776441046420,"version":"3.51.2"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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":[{"name":"Taizhou Shenzhen Innovation Center Project","award":["TSC202501"],"award-info":[{"award-number":["TSC202501"]}]},{"name":"Guangdong Provincial Key Laboratory of Intellectual Property and Big Data","award":["2018B030322016"],"award-info":[{"award-number":["2018B030322016"]}]},{"name":"Key Discipline Research Capacity Improvement Project of Guangdong Province","award":["2022ZDJS013"],"award-info":[{"award-number":["2022ZDJS013"]}]},{"name":"Key Discipline Research Capacity Improvement Project of Guangdong Province","award":["2024ZDJS022"],"award-info":[{"award-number":["2024ZDJS022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3620129","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:40:31Z","timestamp":1760636431000},"page":"6911-6924","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Perspective Cross-Modal Object Encoding for Referring Expression Comprehension"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2262-6261","authenticated-orcid":false,"given":"Jingcheng","family":"Ke","sequence":"first","affiliation":[{"name":"Institute for Interdisciplinary Studies, Guangdong Provincial Key Laboratory of Intellectual Property and Big Data, Guangdong Polytechnic Normal University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-060X","authenticated-orcid":false,"given":"Huiting","family":"Wang","sequence":"additional","affiliation":[{"name":"Allied Health Department, Osaka University, Osaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1940-7962","authenticated-orcid":false,"given":"Wen-Huang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3556088"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2557642.2563669"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3546638"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3367877"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1142\/s0219467827500458"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3334099"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4312-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2930176"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3212317"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3531372"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1142\/s0219467827500690"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2802648"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.248"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3227466"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01276"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3532612"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111222"},{"key":"ref23","article-title":"Box it to bind it: Unified layout control and attribute binding in T2I diffusion models","author":"Taghipour","year":"2024","journal-title":"arXiv:2402.17910"},{"key":"ref24","article-title":"Faster image2video generation: A closer look at clip image embedding\u2019s impact on spatio-temporal cross-attentions","author":"Taghipour","year":"2024","journal-title":"arXiv:2407.19205"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2979010"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01837"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681071"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref38","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Gan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3101356"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.01.131"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413902"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3548688"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3604557"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521844"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00438"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6964"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00738"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2023.3343919"},{"key":"ref52","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kim"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.181"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref57","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Ord\u00f3\u00f1ez"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296823"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147385"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3374786"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3407785"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28363"},{"key":"ref65","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Su"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19983"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547765"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28580"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25331"},{"key":"ref71","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11206016.pdf?arnumber=11206016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:47:19Z","timestamp":1762195639000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11206016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3620129","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}