{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T03:31:16Z","timestamp":1779247876026,"version":"3.51.4"},"reference-count":71,"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":[{"name":"IEEE Publication Technology Department"},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0118201"],"award-info":[{"award-number":["2022ZD0118201"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972217"],"award-info":[{"award-number":["61972217"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32071459"],"award-info":[{"award-number":["32071459"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176249"],"award-info":[{"award-number":["62176249"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006133"],"award-info":[{"award-number":["62006133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271465"],"award-info":[{"award-number":["62271465"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province in China","doi-asserted-by":"publisher","award":["2019B1515120049"],"award-info":[{"award-number":["2019B1515120049"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3276570","type":"journal-article","created":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T18:16:11Z","timestamp":1685556971000},"page":"3367-3382","source":"Crossref","is-referenced-by-count":23,"title":["Weakly-Supervised 3D Spatial Reasoning for Text-Based Visual Question Answering"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3200-0270","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"first","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinfa","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9287-6410","authenticated-orcid":false,"given":"Peng","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5452-3697","authenticated-orcid":false,"given":"Guoli","family":"Song","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3631-256X","authenticated-orcid":false,"given":"Qi","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Adelaide, North Terrace, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"SP-ViT: Learning 2D spatial priors for vision transformers","author":"zhou","year":"2022","journal-title":"arXiv 2206 07662"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01605"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1217"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00297"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475425"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413924"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/423"},{"key":"ref52","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-585-28322-7_1"},{"key":"ref55","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00192"},{"key":"ref54","article-title":"A holistic representation guided attention network for scene text recognition","author":"yang","year":"2019","journal-title":"arXiv 1904 01375"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120544"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859766"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.278"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1186\/s13673-018-0157-2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.02.001"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00597"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054775"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00695"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_23"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00114"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref49","article-title":"3D question answering","author":"ye","year":"2021","journal-title":"arXiv 2112 08359"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_41"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132034"},{"key":"ref9","first-page":"1","article-title":"Reasoning with transformer-based models: Deep learning, but shallow reasoning","author":"helwe","year":"2021","journal-title":"Proc 3rd Conf Automated Knowl Base Construction"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00088"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref6","article-title":"Simple is not easy: A simple strong baseline for TextVQA and TextCaps","author":"zhu","year":"2020","journal-title":"arXiv 2012 05153"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475606"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01276"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_25"},{"key":"ref37","first-page":"1","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume":"27","author":"eigen","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"1","article-title":"Learning depth from single monocular images","volume":"18","author":"saxena","year":"2005","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref33","article-title":"TokenLearner: What can 8 learned tokens do for images and videos?","author":"ryoo","year":"2021","journal-title":"arXiv 2106 11297"},{"key":"ref32","first-page":"1","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","volume":"31","author":"narasimhan","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref39","first-page":"4009","article-title":"Adabins: Depth estimation using adaptive bins","author":"bhat","year":"2021","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.365"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref24","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"lu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref26","article-title":"Improving GAN equilibrium by raising spatial awareness","author":"wang","year":"2021","journal-title":"arXiv 2112 00718"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"ref69","first-page":"1","article-title":"A package for automatic evaluation of summaries","author":"rouge","year":"2004","journal-title":"Proc Workshop Text Summarization ACL"},{"key":"ref20","article-title":"Pythia v0.1: The winning entry to the VQA challenge 2018","author":"jiang","year":"2018","journal-title":"arXiv 1807 09956"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16389"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref65","article-title":"Uit together research group","author":"nguyen","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"ref27","first-page":"1","article-title":"Learning to compose visual relations","volume":"34","author":"liu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-020-01730-0"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10141570.pdf?arnumber=10141570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T19:51:40Z","timestamp":1689018700000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10141570\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3276570","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}