{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:56:39Z","timestamp":1770339399902,"version":"3.49.0"},"reference-count":49,"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFC3303600"],"award-info":[{"award-number":["2022YFC3303600"]}],"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"],"award-info":[{"award-number":["62137002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293550"],"award-info":[{"award-number":["62293550"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293553"],"award-info":[{"award-number":["62293553"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293554"],"award-info":[{"award-number":["62293554"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61937001"],"award-info":[{"award-number":["61937001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62250066"],"award-info":[{"award-number":["62250066"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176209"],"award-info":[{"award-number":["62176209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106190"],"award-info":[{"award-number":["62106190"]}],"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":"Lenovo-Xi\u2019an Jiaotong University (XJTU) Intelligent Industry Joint Laboratory Project;"},{"DOI":"10.13039\/100015804","name":"China Computer Federation (CCF)-Lenovo Blue Ocean Research Fund;","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015804","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-593"],"award-info":[{"award-number":["2023-JC-YB-593"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Innovation Team of Shaanxi Universities;"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["xhj032021013-02"],"award-info":[{"award-number":["xhj032021013-02"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"XJTU Teaching Reform Research Project \u201cAcquisition Learning Based on Knowledge Forest.\u201d"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3306910","type":"journal-article","created":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T17:32:02Z","timestamp":1692898322000},"page":"4812-4827","source":"Crossref","is-referenced-by-count":5,"title":["DisAVR: Disentangled Adaptive Visual Reasoning Network for Diagram Question Answering"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-3658","authenticated-orcid":false,"given":"Yaxian","family":"Wang","sequence":"first","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}]},{"given":"Bifan","family":"Wei","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6004-0675","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8136-8795","authenticated-orcid":false,"given":"Lingling","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Networks and Network Security, Xi’an Jiaotong University, Ministry of Education, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1629-654X","authenticated-orcid":false,"given":"Jiaxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Networks and Network Security, Xi’an Jiaotong University, Ministry of Education, Xi’an, China"}]},{"given":"Qianying","family":"Wang","sequence":"additional","affiliation":[{"name":"Lenovo Research, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Integrating image data extraction and table parsing methods for chart question answering","author":"masry","year":"2021","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376467"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3529"},{"key":"ref10","first-page":"1","article-title":"FigureQA: An annotated figure dataset for visual reasoning","author":"kahou","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.46"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1171"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"ref46","first-page":"1","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00203"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref47","first-page":"1","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"jang","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref43","first-page":"1571","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3112294"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3522689"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3177318"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.441"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00438"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475255"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180563"},{"key":"ref40","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref37","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"arXiv 1907 11692"},{"key":"ref36","first-page":"1","article-title":"An image is worth 16?16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref33","first-page":"6428","article-title":"Probabilistic neural symbolic models for interpretable visual question answering","author":"vedantam","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","first-page":"1039","article-title":"Neural-symbolic VQA: Disentangling reasoning from vision and language understanding","author":"yi","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref38","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref24","first-page":"8344","article-title":"Learning conditioned graph structures for interpretable visual question answering","author":"norcliffe-brown","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/114"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231463"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2930176"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00504"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10230020.pdf?arnumber=10230020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T18:15:34Z","timestamp":1695060934000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10230020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3306910","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}