{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T12:31:00Z","timestamp":1756384260217,"version":"3.41.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096074","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Outside Knowledge Visual Question Answering Version 2.0"],"prefix":"10.1109","author":[{"given":"Benjamin Z.","family":"Reichman","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Anirudh","family":"Sundar","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Christopher","family":"Richardson","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Tamara","family":"Zubatiy","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Prithwijit","family":"Chowdhury","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Aaryan","family":"Shah","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Jack","family":"Truxal","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Micah","family":"Grimes","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Dristi","family":"Shah","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Woo Ju","family":"Chee","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Saif","family":"Punjwani","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Atishay","family":"Jain","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]},{"given":"Larry","family":"Heck","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Lab"}]}],"member":"263","reference":[{"key":"ref13","article-title":"GQA: a new dataset for compositional question answering over real-world images","author":"hudson","year":"2019","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref15","article-title":"Movieqa: Understanding stories in movies through question-answering","author":"tapaswi","year":"2015","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref11","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref2","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"0","journal-title":"Proceedings of NIPS’14"},{"key":"ref1","first-page":"333","article-title":"Vizwiz: Nearly real-time answers to visual questions","author":"bigham","year":"2010","journal-title":"Proceedings UIST’10"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref16","first-page":"1","article-title":"Bilinear graph networks for visual question answering","author":"guo","year":"2021","journal-title":"IEEE Trans on Neural Networks and Learning Systems"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1145\/3404835.3463259"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/TPAMI.2017.2754246"},{"year":"2021","author":"gui","article-title":"Kat: A knowledge augmented transformer for vision-and-language","key":"ref24"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1609\/aaai.v36i3.20174"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.18653\/v1\/2022.emnlp-main.772"},{"year":"2022","author":"gao","article-title":"A thousand words are worth more than a picture: Natural language-centric outside-knowledge visual question answering","key":"ref25"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1609\/aaai.v33i01.33018876"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.18653\/v1\/2020.findings-emnlp.44"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/978-3-031-20074-8_9"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1609\/aaai.v36i3.20215"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CVPR52688.2022.00503"},{"year":"2022","author":"heck","article-title":"Zero-Shot Visual Slot Filling as Question Answering","key":"ref8"},{"key":"ref7","first-page":"2949","article-title":"Multimodal Learning with Deep Boltzmann Machines","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"year":"2023","author":"richardson","article-title":"Commonsense reasoning for conversational ai: A survey of the state of the art","key":"ref9"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.18653\/v1\/2022.nlp4convai-1.12"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICCV.2015.279"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CVPR.2014.455"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1007\/978-3-319-10590-1_7"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096074.pdf?arnumber=10096074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:13:55Z","timestamp":1750875235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096074","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}