{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:26:14Z","timestamp":1783099574305,"version":"3.54.6"},"reference-count":65,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3251111","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T18:25:41Z","timestamp":1677695141000},"page":"9330-9342","source":"Crossref","is-referenced-by-count":5,"title":["InterREC: An Interpretable Method for Referring Expression Comprehension"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9710-0136","authenticated-orcid":false,"given":"Wenbin","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maurice","family":"Pagnucco","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8860-7701","authenticated-orcid":false,"given":"Chengpei","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Minerals and Energy Resources Engineering, University of New South Wales, Kensington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1283-1672","authenticated-orcid":false,"given":"Yang","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRPMS.2021.3066428"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00427"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3463945.3469055"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref19","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Li","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2123"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00226"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref33","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Gan","year":"2020"},{"key":"ref34","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Cho","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref36","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst","author":"Lu","year":"2019"},{"key":"ref37","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6833"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref45","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst","author":"Vaswani","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3099165"},{"key":"ref47","first-page":"23 318","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","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3139234"},{"key":"ref49","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548341"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.707"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"ref53","volume-title":"Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference","author":"Pearl","year":"1988"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.138"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2964154"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/rs12020216"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.286"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19997"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10057171.pdf?arnumber=10057171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:45:43Z","timestamp":1705020343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10057171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3251111","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}