{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T04:48:30Z","timestamp":1767156510755,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0108800"],"award-info":[{"award-number":["2020AAA0108800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62137002","61937001","62192781","62176209","62176207","62106190","62250009"],"award-info":[{"award-number":["62137002","61937001","62192781","62176209","62176207","62106190","62250009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Innovative Research Group of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61721002"],"award-info":[{"award-number":["61721002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Research Team of Ministry of Education","award":["IRT_17R86"],"award-info":[{"award-number":["IRT_17R86"]}]},{"DOI":"10.13039\/501100019069","name":"Consulting Research Project of Chinese Academy of Engineering The Online and Offline Mixed Educational Service System for The Belt and Road Training in MOOC China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019069","id-type":"DOI","asserted-by":"publisher"}]},{"name":"LENOVO-XJTU Intelligent Industry Joint Laboratory Project"},{"name":"CCF-Lenovo Blue Ocean Research Fund"},{"DOI":"10.13039\/501100012455","name":"Project of China Knowledge Centre for Engineering Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012455","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of Key National Defense Science and Technology Laboratory","award":["6142101210201"],"award-info":[{"award-number":["6142101210201"]}]},{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi","doi-asserted-by":"publisher","award":["2023-JC-YB-293"],"award-info":[{"award-number":["2023-JC-YB-293"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Innovation Team of Shaanxi Universities"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/tcsvt.2022.3231463","type":"journal-article","created":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T18:55:14Z","timestamp":1671648914000},"page":"3214-3228","source":"Crossref","is-referenced-by-count":9,"title":["Spatial-Semantic Collaborative Graph Network for Textbook Question Answering"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-3658","authenticated-orcid":false,"given":"Yaxian","family":"Wang","sequence":"first","affiliation":[{"name":"Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bifan","family":"Wei","sequence":"additional","affiliation":[{"name":"Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering and the School of Computer Science and Technology, 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":"Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5650-0600","authenticated-orcid":false,"given":"Qika","family":"Lin","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, 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":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8830-8250","authenticated-orcid":false,"given":"Yaqiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Lenovo Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"FigureQA: An annotated figure dataset for visual reasoning","author":"kahou","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1171"},{"key":"ref14","first-page":"4967","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref52","article-title":"MINE: Mutual information neural estimation","author":"belghazi","year":"2018","journal-title":"arXiv 1801 04062"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.9146"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00102"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0734-189X(85)90020-9"},{"key":"ref54","first-page":"91","article-title":"Faster R-CNN: Towards real time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.46"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00078"},{"key":"ref18","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.maiworkshop-1.13"},{"key":"ref50","first-page":"684","article-title":"Exploring visual relationship for image captioning","author":"yao","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref46","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent (ICLR)"},{"key":"ref45","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume":"30","author":"hamilton","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107451"},{"key":"ref41","article-title":"XTQA: Span-level explanations of the textbook question answering","author":"ma","year":"2020","journal-title":"arXiv 2011 12662"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547820"},{"key":"ref43","first-page":"3940","article-title":"Category-level adversarial adaptation for semantic segmentation using purified features","volume":"44","author":"luo","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref49","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"arXiv 1907 11692"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00608"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060713"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180563"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00385"},{"key":"ref34","first-page":"1","article-title":"MoQA—A multi-modal question answering architecture","author":"haurilet","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref37","article-title":"Relation-aware fine-grained reasoning network for textbook question answering","author":"ma","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1347"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1214"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486468"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1638"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/app10217640"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86380-7_8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.441"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"ref23","first-page":"69","article-title":"Unsupervised learning of visual representations by solving jigsaw puzzles","author":"noroozi","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref26","article-title":"Selfie: Self-supervised pretraining for image embedding","author":"trinh","year":"2019","journal-title":"arXiv 1906 02940"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3141051"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3114209"},{"key":"ref28","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc ACL Conf NAACL HLT"},{"key":"ref27","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"},{"key":"ref29","article-title":"CERT: Contrastive self-supervised learning for language understanding","author":"fang","year":"2020","journal-title":"arXiv 2005 12766"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10170754\/09996417.pdf?arnumber=9996417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:55:45Z","timestamp":1689616545000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9996417\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":55,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3231463","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}