{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:25:34Z","timestamp":1771514734809,"version":"3.50.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"ARC Discovery","award":["DP200100938"],"award-info":[{"award-number":["DP200100938"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2020.2967584","type":"journal-article","created":{"date-parts":[[2020,1,23]],"date-time":"2020-01-23T16:23:08Z","timestamp":1579796588000},"page":"3984-3992","source":"Crossref","is-referenced-by-count":26,"title":["Revisiting EmbodiedQA: A Simple Baseline and Beyond"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1680-8253","authenticated-orcid":false,"given":"Yu","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0286-8439","authenticated-orcid":false,"given":"Lu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00623"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref32","first-page":"1","article-title":"Don’t just assume; look and answer: Overcoming priors for visual question answering","author":"agrawal","year":"2018","journal-title":"Proc CVPR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref30","first-page":"1","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc NIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref35","first-page":"1","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question","author":"gao","year":"2015","journal-title":"Proc NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00043"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2859820"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821921"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3652-9"},{"key":"ref1","first-page":"2054","article-title":"Embodied Question Answering","author":"das","year":"2018","journal-title":"Proc CVPR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2602938"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref24","article-title":"Show, ask, attend, and answer: A strong baseline for visual question answering","author":"kazemi","year":"2017","journal-title":"arXiv 1704 03162"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref50","first-page":"1","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc NIPS-W"},{"key":"ref51","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/21.44033"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/70.88137"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref12","first-page":"1","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"Proc ICLR"},{"key":"ref13","first-page":"1","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"2017","journal-title":"Proc ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref15","first-page":"1","article-title":"Memory augmented control networks","author":"khan","year":"2018","journal-title":"Proc ICLR"},{"key":"ref16","first-page":"1","article-title":"Neural map: Structured memory for deep reinforcement learning","author":"parisotto","year":"2018","journal-title":"Proc ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.329"},{"key":"ref18","first-page":"2661","article-title":"Zero-shot task generalization with multi-task deep reinforcement learning","author":"oh","year":"2017","journal-title":"Proc ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2237023"},{"key":"ref4","first-page":"2772","article-title":"Listen, attend, and walk: Neural mapping of navigational instructions to action sequences","author":"mei","year":"2016","journal-title":"Proc AAAI"},{"key":"ref3","author":"thrun","year":"2005","journal-title":"Probabilistic Robotics"},{"key":"ref6","article-title":"Neural modular control for embodied question answering","author":"das","year":"2018","journal-title":"arXiv 1810 11181"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.60"},{"key":"ref7","first-page":"1","article-title":"Blindfold baselines for embodied QA","author":"anand","year":"2018","journal-title":"Proc NIPS"},{"key":"ref49","first-page":"1","article-title":"Building generalizable agents with a realistic and rich 3D environment","author":"wu","year":"2018","journal-title":"Proc ICLR-W"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2868851"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref48","first-page":"1","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2014","journal-title":"Proc NIPS-W"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_11"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref43","first-page":"1","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015","journal-title":"Proc ICLR"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/08967238.pdf?arnumber=8967238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:56:10Z","timestamp":1641988570000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.2967584","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}