{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:45:53Z","timestamp":1772909153420,"version":"3.50.1"},"reference-count":50,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521744","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:23:06Z","timestamp":1734981786000},"page":"2141-2154","source":"Crossref","is-referenced-by-count":1,"title":["Alignment-Guided Self-Supervised Learning for Diagram Question Answering"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5536-6515","authenticated-orcid":false,"given":"Shaowei","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Communication Content Cognition, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8136-8795","authenticated-orcid":false,"given":"Lingling","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xian Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9377-9062","authenticated-orcid":false,"given":"Wenjun","family":"Wu","sequence":"additional","affiliation":[{"name":"Ministry of Education, Key Laboratory of Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4874-2567","authenticated-orcid":false,"given":"Tao","family":"Qin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xian Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7658-0116","authenticated-orcid":false,"given":"Xinyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ministry of Education, Key Laboratory of Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6004-0675","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xian Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3061816"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00683"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475193"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6389-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001500"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3122542"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120194"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3522689"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00438"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.441"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475255"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3087000"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/980691.980793"},{"issue":"1","key":"ref18","first-page":"109","article-title":"Telling juxtapositions: Using repetition and alignable difference in diagram understanding","volume":"5","author":"Ferguson","year":"1998","journal-title":"Adv. Anal. Res."},{"key":"ref19","first-page":"510","article-title":"Georep: A flexible tool for spatial representation of line drawings","volume-title":"Proc. 17th Nat. Conf. Artif. Intell. 12th Conf. Innov. Appl. Artif. Intell.","author":"Ferguson","year":"2000"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227811"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.9146"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/228"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00203"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180563"},{"key":"ref25","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen","year":"2020"},{"key":"ref26","article-title":"Gpt-4 technical report","author":"OpenAI","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3231532"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00086"},{"key":"ref33","first-page":"7774","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 31: Annu. Conf. Neural Inf. Process. Syst.","author":"Korbar","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref38","article-title":"Roberta: A robustly optimized BERT pretraining approach","volume-title":"CoRR","volume":"abs\/1907.11692","author":"Liu","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-6471-7_21"},{"key":"ref43","article-title":"PaddleOCR","year":"2022"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref47","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 31: Annu. Conf. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.683"},{"key":"ref50","article-title":"Hallusionbench: You see what you think? Or you think what you see? an image-context reasoning benchmark challenging for gpt-4v (ision), llava-1.5, and other multi-modality models","author":"Liu","year":"2023"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10812784.pdf?arnumber=10812784","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T21:56:07Z","timestamp":1744062967000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10812784\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521744","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}