{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T04:19:24Z","timestamp":1778559564079,"version":"3.51.4"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0106400"],"award-info":[{"award-number":["2020AAA0106400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tnnls.2021.3105280","type":"journal-article","created":{"date-parts":[[2021,8,31]],"date-time":"2021-08-31T19:56:56Z","timestamp":1630439816000},"page":"1367-1379","source":"Crossref","is-referenced-by-count":11,"title":["Question-Guided Erasing-Based Spatiotemporal Attention Learning for Video Question Answering"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2994-3534","authenticated-orcid":false,"given":"Fei","family":"Liu","sequence":"first","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0903-9131","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Computer and Information, Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanqing","family":"Lu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878970"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2655449"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3093419"},{"key":"ref5","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. NeurIPS","author":"Kim"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/122"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/492"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref17","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume-title":"Proc. NeurIPS","author":"Sohn"},{"key":"ref18","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume-title":"Proc. NeurIPS","author":"Malinowski"},{"key":"ref19","article-title":"ABC-CNN: An attention based convolutional neural network for visual question answering","volume-title":"arXiv:1511.05960","author":"Chen","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref21","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. NeurIPS","author":"Lu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref23","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. ICLR","author":"Kim"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2943456"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3444685.3446256"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref32","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556245"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3045034"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080655"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/513"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963950"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922062"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1142\/9789812797926_0003"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref51","first-page":"412","article-title":"Learning a nonlinear embedding by preserving class neighbourhood structure","volume-title":"Proc. Artif. Intell. Statist.","author":"Salakhutdinov"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.130"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02172-5_2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477035"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00535"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.324"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350993"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref66","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. ACL","author":"Chen"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1063\/1.4902458"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016391"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351065"},{"key":"ref75","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv:1810.04805","author":"Devlin","year":"2018"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10056374\/09525823.pdf?arnumber=9525823","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:38:12Z","timestamp":1705016292000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9525823\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":75,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3105280","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}