{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:18:24Z","timestamp":1753600704995},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413599","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"source":"Crossref","is-referenced-by-count":5,"title":["Generating Natural Questions from Images for Multimodal Assistants"],"prefix":"10.1109","author":[{"given":"Alkesh","family":"Patel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akanksha","family":"Bindal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hadas","family":"Kotek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Klein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Williams","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"devlin","year":"2018","journal-title":"BERT Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/592"},{"key":"ref12","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question answering","author":"gao","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref14","article-title":"Exploring Models and Data for Image Question Answering","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","author":"marino","year":"2019","journal-title":"OK-VQA A Visual Question Answering Bench-mark Requiring External Knowledge"},{"key":"ref16","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","author":"narasimhan","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.500"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref19","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015 -Conference Track Proceedings"},{"key":"ref4","author":"marino","year":"2019","journal-title":"OK-VQA A Visual Question Answering Bench-mark Requiring External Knowledge"},{"key":"ref27","author":"li","year":"2019","journal-title":"Unicoder-vl A universal encoder for vision and language by cross-modal pre-training"},{"key":"ref3","article-title":"FVQA: Fact-based Visual Question Answering","author":"wang","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref6","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015 -Conference Track Proceedings"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1170"},{"key":"ref8","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref2","first-page":"1290","article-title":"KB-VQA Explicit knowledge-based reasoning for visual question answering","author":"wang","year":"0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.575"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","first-page":"1","author":"vijayakumar","year":"2016","journal-title":"Diverse beam search Decoding diverse solutions from neural sequence models"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342066"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref26","first-page":"1","author":"su","year":"2020","journal-title":"Vl-bert Pre-training of generic visual-linguistic representations"},{"key":"ref25","first-page":"1","article-title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","author":"lu","year":"2019","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413599.pdf?arnumber=9413599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:56Z","timestamp":1652197256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413599","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}