{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T10:11:53Z","timestamp":1769163113744,"version":"3.49.0"},"reference-count":45,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100012542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2021YFQ0003"],"award-info":[{"award-number":["2021YFQ0003"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2019YJ0189"],"award-info":[{"award-number":["2019YJ0189"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3074937","type":"journal-article","created":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T20:09:28Z","timestamp":1619122168000},"page":"91476-91486","source":"Crossref","is-referenced-by-count":130,"title":["Improving Visual Reasoning Through Semantic Representation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8486-1654","authenticated-orcid":false,"given":"Wenfeng","family":"Zheng","sequence":"first","affiliation":[]},{"given":"Xiangjun","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3072-4379","authenticated-orcid":false,"given":"Xubin","family":"Ni","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5022-610X","authenticated-orcid":false,"given":"Lirong","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Recurrent convolutional neural networks for text classification","volume":"29","author":"lai","year":"2015","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref38","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn (PMLR)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2004.824224"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(94)90060-4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref30","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539963"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref34","first-page":"1075","article-title":"Segmentation of 3D head MR images using morphological reconstruction under constraints and automatic selection of markers","volume":"3","author":"dokladal","year":"2001","journal-title":"Proc Int Conf Image Process"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-015-1957-6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1142\/S0219691315500113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1515\/geo-2017-0026"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s12040-018-1040-2"},{"key":"ref14","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume":"27","author":"malinowski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref16","first-page":"2953","article-title":"Exploring models and data for image question answering","volume":"28","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref19","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/2150704X.2015.1034885"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/app11031316"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102367"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34995-0_31"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105344"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2814012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.538"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1051\/matecconf\/201927702006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2019.134244"},{"key":"ref20","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume":"29","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref42","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","first-page":"1031","article-title":"Neural-symbolic VQA: Disentangling reasoning from vision and language understanding","volume":"31","author":"yi","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref23","first-page":"4974","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"2017","journal-title":"Proc NIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref43","first-page":"577","article-title":"Attention-based models for speech recognition","volume":"28","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09410599.pdf?arnumber=9410599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:45Z","timestamp":1639770945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9410599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3074937","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}