{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T17:03:21Z","timestamp":1772211801379,"version":"3.50.1"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"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":[[2022,6]]},"DOI":"10.1109\/cvpr52688.2022.00501","type":"proceedings-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:56:41Z","timestamp":1664308601000},"page":"5057-5067","source":"Crossref","is-referenced-by-count":66,"title":["Transform-Retrieve-Generate: Natural Language-Centric Outside-Knowledge Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Feng","family":"Gao","sequence":"first","affiliation":[{"name":"University of California,Los Angeles"}]},{"given":"Qing","family":"Ping","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Govind","family":"Thattai","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Aishwarya","family":"Reganti","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"given":"Ying Nian","family":"Wu","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}]},{"given":"Prem","family":"Natarajan","sequence":"additional","affiliation":[{"name":"Amazon"}]}],"member":"263","reference":[{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00043"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6364"},{"key":"ref33","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref32","first-page":"3","article-title":"Kagnet: Knowledge-aware graph networks for common-sense reasoning","author":"lin","year":"2019","journal-title":"Arxiv preprint arXiv"},{"key":"ref31","first-page":"1, 2","article-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"li","year":"2020","journal-title":"ECCV 2020"},{"key":"ref30","first-page":"1","article-title":"Unimo: Towards unified-modal understanding and generation via cross-modal contrastive learning","author":"li","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.517"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.240"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220036"},{"key":"ref34","first-page":"1","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic represen-tations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Arxiv preprint arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1599"},{"key":"ref62","first-page":"72","article-title":"End-to-end open-domain question answering with bertserini","author":"yang","year":"0","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)"},{"key":"ref61","first-page":"2, 3","article-title":"Multi-modal answer validation for knowledge-based vqa","author":"wu","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_25"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"ref64","first-page":"3, 6","article-title":"An empirical study of gpt-3 for few-shot knowledge-based vqa","author":"yang","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.45"},{"key":"ref66","first-page":"8","article-title":"Neural-symbolic vqa: Disentangling reasoning from vision and language under-standing","author":"yi","year":"2018","journal-title":"Arxiv preprint arXiv"},{"key":"ref29","first-page":"2, 3","article-title":"La-tent retrieval for weakly supervised open domain question answering","author":"lee","year":"2019","journal-title":"Arxiv preprint arXiv"},{"key":"ref67","first-page":"6281","article-title":"Deep modular co-attention networks for visual question an-swering","author":"yu","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref69","first-page":"1","article-title":"Vinv1: Making visual representations matter in vision-language models","author":"zhang","year":"2021","journal-title":"CVPR 2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref20","first-page":"3","article-title":"Se-lect, substitute, search: A new benchmark for knowledge-augmented visual question answering","author":"jain","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref22","first-page":"4","article-title":"Billion-scale similarity search with gpus","author":"johnson","year":"2017","journal-title":"Arxiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref26","first-page":"2","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","author":"krishna","year":"2016","journal-title":"Arxiv preprint arXiv"},{"key":"ref25","first-page":"2","article-title":"Bilin-ear attention networks","author":"kim","year":"0","journal-title":"NeurIPS"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref51","first-page":"4","article-title":"Con-ceptnet 5. 5: An open multilingual graph of general knowl-edge","author":"speer","year":"0","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"7208","DOI":"10.1609\/aaai.v33i01.33017208","article-title":"Im-proving natural language inference using external know l-edge in the science questions domain","volume":"33","author":"wang","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref58","first-page":"1","article-title":"Explicit knowledge-based rea-soning for visual question answering","author":"wang","year":"2015","journal-title":"ar Xiv preprint arXiv"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref56","first-page":"6428","article-title":"Probabilistic neu-ral symbolic models for interpretable visual question an-swering","author":"vedantam","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref55","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1455"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.99"},{"key":"ref11","first-page":"2","article-title":"Large-scale adversarial training for vision-and-language representation learning","author":"gan","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref12","first-page":"489","article-title":"Conceptbert: Concept-aware represen-tation for visual question answering","author":"garderes","year":"0","journal-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing Findings"},{"key":"ref13","first-page":"3","article-title":"Kat: A knowl-edge augmented transformer for vision-and-language","author":"gui","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3104937"},{"key":"ref15","first-page":"3","article-title":"Image scene graph gen-eration (sgg) benchmark","author":"han","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref18","first-page":"7","article-title":"Distilling knowledge from reader to retriever for question answering","author":"izacard","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref19","first-page":"2, 3","article-title":"Leveraging passage re-trieval with generative models for open domain question an-swering","author":"izacard","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref4","first-page":"7","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref3","first-page":"4","article-title":"Genericskb: A knowledge base of generic statements","author":"bhakthavatsalam","year":"2020","journal-title":"Arxiv preprint arXiv"},{"key":"ref6","first-page":"1","article-title":"Uniter: Learning universal image-text representations","author":"chen","year":"2019","journal-title":"Arxiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1171"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.001"},{"key":"ref7","first-page":"2","article-title":"Simple and effective multi-paragraph reading comprehension","author":"clark","year":"2017","journal-title":"Arxiv preprint arXiv"},{"key":"ref49","first-page":"1, 3","article-title":"Reasoning over vision and language: Exploring the benefits of supplemental knowledge","author":"shevchenko","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref9","first-page":"4","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"Arxiv preprint arXiv"},{"key":"ref46","first-page":"3","author":"robertson","year":"2009","journal-title":"The Probabilistic Relevance Framework BM25 and Beyond"},{"key":"ref45","first-page":"2","article-title":"Squad: 100, 000+ questions for machine com-prehension of text","author":"rajpurkar","year":"0","journal-title":"EMNLP"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref47","first-page":"6","article-title":"Image captioning for ef-fective use of language models in knowledge-based visual question answering","author":"salaberria","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref42","first-page":"4","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"raffel","year":"2019","journal-title":"Arxiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462987"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"ref43","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"raffel","year":"2020","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"New Orleans, LA, USA","start":{"date-parts":[[2022,6,18]]},"end":{"date-parts":[[2022,6,24]]}},"container-title":["2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9878378\/9878366\/09879942.pdf?arnumber=9879942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:57:39Z","timestamp":1665781059000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9879942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/cvpr52688.2022.00501","relation":{},"subject":[],"published":{"date-parts":[[2022,6]]}}}