{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T21:13:09Z","timestamp":1778274789062,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0101900"],"award-info":[{"award-number":["2018AAA0101900"]}]},{"name":"Zhejiang NSF","award":["LR21F020004"],"award-info":[{"award-number":["LR21F020004"]}]},{"DOI":"10.13039\/501100012455","name":"Chinese Knowledge Center of Engineering Science and Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012455","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3425222","type":"journal-article","created":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T18:29:03Z","timestamp":1720549743000},"page":"9648-9660","source":"Crossref","is-referenced-by-count":4,"title":["Ask Questions With Double Hints: Visual Question Generation With Answer-Awareness and Region-Reference"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3564-0281","authenticated-orcid":false,"given":"Kai","family":"Shen","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3660-651X","authenticated-orcid":false,"given":"Lingfei","family":"Wu","sequence":"additional","affiliation":[{"name":"Anytime AI, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7356-9711","authenticated-orcid":false,"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangli","family":"Xu","sequence":"additional","affiliation":[{"name":"Anytime AI, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Long","sequence":"additional","affiliation":[{"name":"Meta AI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2200-8711","authenticated-orcid":false,"given":"Jian","family":"Pei","sequence":"additional","affiliation":[{"name":"Duke University, Durham, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2754246"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00603"},{"key":"ref5","article-title":"Towards automatic generation of question answer pairs from images","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshop","author":"Mora"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00211"},{"key":"ref7","first-page":"1802","article-title":"Generating natural questions about an image","volume-title":"Proc. 54th Annu. Meeting Assoc. Comput. Linguistics","author":"Mostafazadeh"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004830"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2943456"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2880185"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.575"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/592"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00898"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00681"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2986029"},{"key":"ref16","first-page":"2713","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref17","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref18","article-title":"Graph2Seq: Graph to sequence learning with attention-based neural networks","author":"Xu","year":"2018"},{"key":"ref19","first-page":"10176","article-title":"Reinforcement learning based graph-to-sequence model for natural question generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00121"},{"key":"ref21","first-page":"8334","article-title":"Learning conditioned graph structures for interpretable visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Norcliffe-Brown"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/171"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref26","first-page":"19314","article-title":"Iterative deep graph learning for graph neural networks: Better and robust node embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref28","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref30","first-page":"2953","article-title":"Exploring models and data for image question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref38","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref39","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref40","first-page":"3950","article-title":"Towards a better metric for evaluating question generation systems","volume-title":"Proc. Conf. Empir. Methods Natural Lang. Process.","author":"Nema"},{"key":"ref41","article-title":"Bilinear attention networks","author":"Kim","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref43","article-title":"Zero-shot transfer VQA dataset","author":"Li","year":"2018"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10591342.pdf?arnumber=10591342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:25:41Z","timestamp":1732663541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10591342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":43,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3425222","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}