{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:45:14Z","timestamp":1772325914968,"version":"3.50.1"},"reference-count":77,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088102"],"award-info":[{"award-number":["62088102"]}],"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":["61773312"],"award-info":[{"award-number":["61773312"]}],"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":[[2023]]},"DOI":"10.1109\/tmm.2022.3185900","type":"journal-article","created":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T19:31:20Z","timestamp":1656012680000},"page":"5002-5013","source":"Crossref","is-referenced-by-count":15,"title":["LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8241-4877","authenticated-orcid":false,"given":"Jingjing","family":"Jiang","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shannxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2407-9599","authenticated-orcid":false,"given":"Ziyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shannxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1608-8257","authenticated-orcid":false,"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shannxi, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref58","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","first-page":"1025","article-title":"Inductive representation learning on large graphs","author":"hamilton","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","article-title":"Graph attention networks","author":"veli?kovi?","year":"0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1159"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref54","article-title":"Simple BERT models for relation extraction and semantic role labeling","author":"shi","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350969"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3320061"},{"key":"ref51","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016"},{"key":"ref50","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"defferrard","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475350"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"ref48","article-title":"Deep convolutional networks on graph-structured data","author":"henaff","year":"2015"},{"key":"ref47","article-title":"Spectral networks and locally connected networks on graphs","author":"bruna","year":"0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011288"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3011866"},{"key":"ref49","first-page":"2449","article-title":"Spectral representations for convolutional neural networks","author":"rippel","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_34"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351065"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref40","first-page":"8334","article-title":"Learning conditioned graph structures for interpretable visual question answering","author":"norcliffe-brown","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"Probabilistic neural-symbolic models for interpretable visual question answering","author":"vedantam","year":"2019"},{"key":"ref34","article-title":"Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning","author":"garcez","year":"2019"},{"key":"ref37","first-page":"4967","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"Neuro-symbolic visual reasoning: Disentangling ‘visual’ from “reasoning","author":"amizadeh","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00853"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093592"},{"key":"ref74","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01276"},{"key":"ref77","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref39","article-title":"Mucko: Multilayer cross-modal knowledge reasoning for fact-based visualquestion answering","author":"zhu","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.08.009"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6713"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16822"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.435"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref69","first-page":"16872","article-title":"Look before you speak: Visually contextualized utterances","author":"seo","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01012"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_41"},{"key":"ref66","first-page":"91","article-title":"Faster R-CNN: Toward real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref65","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190771"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206815"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09805683.pdf?arnumber=9805683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:59:25Z","timestamp":1701115165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9805683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3185900","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}