{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T13:00:51Z","timestamp":1776430851010,"version":"3.51.2"},"reference-count":54,"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":"National Science and Technology Council","award":["112-2634-F-002-005"],"award-info":[{"award-number":["112-2634-F-002-005"]}]},{"name":"National Science and Technology Council","award":["12-2221-E-A49-090-MY3"],"award-info":[{"award-number":["12-2221-E-A49-090-MY3"]}]},{"DOI":"10.13039\/100005144","name":"Qualcomm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005144","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Taiwan University Research Collaboration Project","award":["NAT-487844-4"],"award-info":[{"award-number":["NAT-487844-4"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521844","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T19:21:58Z","timestamp":1735068118000},"page":"1950-1961","source":"Crossref","is-referenced-by-count":3,"title":["Make Graph-Based Referring Expression Comprehension Great Again Through Expression-Guided Dynamic Gating and Regression"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2262-6261","authenticated-orcid":false,"given":"Jingcheng","family":"Ke","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and the Institute of Communications Engineering, National Tsing Hua University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0127-9766","authenticated-orcid":false,"given":"Dele","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and the Institute of Communications Engineering, National Tsing Hua University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0209-8932","authenticated-orcid":false,"given":"Jun-Cheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3893-3758","authenticated-orcid":false,"given":"I-Hong","family":"Jhuo","sequence":"additional","affiliation":[{"name":"Microsoft, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9097-2318","authenticated-orcid":false,"given":"Chia-Wen","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and the Institute of Communications Engineering, National Tsing Hua University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7183-6070","authenticated-orcid":false,"given":"Yen-Yu","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01815"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_10"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120194"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00271"},{"key":"ref6","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"Chen","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413850"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6833"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3297312"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147385"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00180"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref19","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.","volume":"162","author":"Wang","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2811621"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3219642"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3548688"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3604557"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413902"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01509"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.2307\/2001990"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref35","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Ordonez","year":"2011"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.181"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296823"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01837"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3334099"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3374786"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147385"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19983"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10814706.pdf?arnumber=10814706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T21:56:18Z","timestamp":1744062978000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10814706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521844","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}