{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:09:52Z","timestamp":1780052992645,"version":"3.54.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["4192059"],"award-info":[{"award-number":["4192059"]}]},{"name":"Beijing Natural Science Foundation","award":["JQ20022"],"award-info":[{"award-number":["JQ20022"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61922086"],"award-info":[{"award-number":["61922086"]}],"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":["61872366"],"award-info":[{"award-number":["61872366"]}],"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":["61872364"],"award-info":[{"award-number":["61872364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3026892","type":"journal-article","created":{"date-parts":[[2020,9,25]],"date-time":"2020-09-25T20:40:52Z","timestamp":1601066452000},"page":"3518-3529","source":"Crossref","is-referenced-by-count":42,"title":["Visual Question Answering With Dense Inter- and Intra-Modality Interactions"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2994-3534","authenticated-orcid":false,"given":"Fei","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0903-9131","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwei","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanqing","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_10"},{"key":"ref39","article-title":"ABC-CNN: An attention based convolutional neural network for visual question answering","author":"chen","year":"2015","journal-title":"arXiv 1511 05960"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref30","first-page":"7944","article-title":"Layer-wise coordination between encoder and decoder for neural machine translation","author":"he","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882225"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350993"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803670"},{"key":"ref34","article-title":"Reciprocal attention fusion for visual question answering","author":"farazi","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref62","article-title":"Co-attending free-form regions and detections with multi-modal multiplicative feature embedding for visual question answering","author":"lu","year":"0","journal-title":"Proc Assoc Advancement Artif Intell"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00807"},{"key":"ref28","article-title":"Pyramid attention network for semantic segmentation","author":"li","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2018.8499452"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_2"},{"key":"ref65","first-page":"275","article-title":"Chain of reasoning for visual question answering","author":"wu","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref68","article-title":"Learning to count objects in natural images for visual question answering","author":"zhang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref69","article-title":"Pythia v0.1: The winning entry to the VQA challenge 2018","author":"jiang","year":"2018","journal-title":"arXiv 1807 09956"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref21","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/122"},{"key":"ref50","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv 1502 03167"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017"},{"key":"ref58","article-title":"On the convergence of adam and beyond","author":"reddi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref57","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806216"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2124295.2124363"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2014.115"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref14","first-page":"361","article-title":"Multimodal residual learning for visual QA","author":"kim","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref15","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref18","first-page":"2296","article-title":"Are you talking to a machine? dataset and methods for multilingual image question","author":"gao","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-012-9193-0"},{"key":"ref3","first-page":"201","article-title":"Stacked cross attention for image-text matching","author":"lee","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587643"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2998574"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783296"},{"key":"ref7","first-page":"793","article-title":"Link prediction across networks by biased cross-network sampling","author":"qi","year":"0","journal-title":"Proc Int Council Open Distance Educ"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref9","first-page":"850","article-title":"Exploring context and content links in social media: A latent space method","volume":"34","author":"qi","year":"2011","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289464"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref42","first-page":"1564","article-title":"Bilinear attention networks","author":"kim","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref41","first-page":"451","article-title":"Ask, attend and answer: Exploring question-guided spatial attention for visual question answering","author":"xu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45465-9_59"},{"key":"ref43","article-title":"Simple baseline for visual question answering","author":"zhou","year":"2015","journal-title":"arXiv 1512 02167"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09206083.pdf?arnumber=9206083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:27Z","timestamp":1652194287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206083\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3026892","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}