{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T11:31:16Z","timestamp":1763724676592,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,28]]},"DOI":"10.1109\/ro-man57019.2023.10309342","type":"proceedings-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:07:48Z","timestamp":1699902468000},"page":"363-369","source":"Crossref","is-referenced-by-count":2,"title":["Open-Ended Multi-Modal Relational Reasoning for Video Question Answering"],"prefix":"10.1109","author":[{"given":"Haozheng","family":"Luo","sequence":"first","affiliation":[{"name":"Northwestern University,Department of Electrical Engineering and Computer Science,Evanston"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiyang","family":"Qin","sequence":"additional","affiliation":[{"name":"University of Notre Dame,Department of Computer Science and Engineering,Notre Dame,IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Electrical Engineering and Computer Science,Evanston"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guo","family":"Ye","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Electrical Engineering and Computer Science,Evanston"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zening","family":"Luo","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Electrical Engineering and Computer Science,Evanston"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICHMS49158.2020.9209377"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3570731"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSMC.2015.2501167"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5772\/60416"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.677"},{"issue":"3.2. Kobe","key":"ref6","first-page":"5","article-title":"Ros: an open-source robot operating system","volume-title":"ICRA workshop on open source software","volume":"3","author":"Quigley"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref10","first-page":"5753","article-title":"Xlnet: Generalized autoregressive pre-training for language understanding","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","first-page":"1039","article-title":"Neural-symbolic vqa: Disentangling reasoning from vision and language understanding","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Yi"},{"key":"ref12","article-title":"Question classification with deep contextualized transformer","author":"Luo","year":"2019","journal-title":"arXiv preprint arXiv:1910.10492"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.128"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.55"},{"key":"ref15","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume":"26","author":"Mikolov","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"article-title":"How to design sample and computationally efficient vqa models","year":"2021","author":"Samel","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Ibert: Idiom cloze-style reading comprehension with attention","year":"2021","author":"Qin","key":"ref21"},{"article-title":"Sciannotate: A tool for integrating weak labeling sources for sequence labeling","year":"2022","author":"Liu","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab083"},{"key":"ref24","article-title":"Cater: A diagnostic dataset for compositional actions and temporal reasoning","volume":"abs\/1910.04744","author":"Girdhar","year":"2020","journal-title":"ArXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1117\/12.2502012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"article-title":"Robust speech recognition via large-scale weak supervision","year":"2022","author":"Radford","key":"ref31"},{"article-title":"Ibert: Idiom cloze-style reading comprehension with attention","year":"2021","author":"Qin","key":"ref32"},{"article-title":"Attention is all you need","year":"2017","author":"Vaswani","key":"ref33"},{"article-title":"Layer normalization","year":"2016","author":"Ba","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-2074"},{"key":"ref36","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"article-title":"Ajax: A new approach to web applications","year":"2005","author":"Garrett","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00853"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852087"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093596"},{"key":"ref42","article-title":"iperceive: Applying common-sense reasoning to multi-modal dense video captioning and video question answering","author":"Chadha","year":"2020","journal-title":"arXiv preprint arXiv:2011.07735"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"}],"event":{"name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2023,8,28]]},"location":"Busan, Korea, Republic of","end":{"date-parts":[[2023,8,31]]}},"container-title":["2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10309296\/10309265\/10309342.pdf?arnumber=10309342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T13:48:05Z","timestamp":1709387285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10309342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,28]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ro-man57019.2023.10309342","relation":{},"subject":[],"published":{"date-parts":[[2023,8,28]]}}}