{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T13:33:11Z","timestamp":1725715991258},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"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":[[2021,10]]},"DOI":"10.1109\/iccvw54120.2021.00353","type":"proceedings-article","created":{"date-parts":[[2021,11,24]],"date-time":"2021-11-24T15:40:09Z","timestamp":1637768409000},"page":"3147-3150","source":"Crossref","is-referenced-by-count":3,"title":["Visual Question Answering with Textual Representations for Images"],"prefix":"10.1109","author":[{"given":"Yusuke","family":"Hirota","sequence":"first","affiliation":[]},{"given":"Noa","family":"Garcia","sequence":"additional","affiliation":[]},{"given":"Mayu","family":"Otani","sequence":"additional","affiliation":[]},{"given":"Chenhui","family":"Chu","sequence":"additional","affiliation":[]},{"given":"Yuta","family":"Nakashima","sequence":"additional","affiliation":[]},{"given":"Ittetsu","family":"Taniguchi","sequence":"additional","affiliation":[]},{"given":"Takao","family":"Onoye","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref12","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"li","year":"2019","journal-title":"CoRR"},{"key":"ref13","article-title":"Microsoft COCO: common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref14","article-title":"Roberta: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref6","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"ref7","article-title":"Don’t take the easy way out: Ensemble based methods for avoiding known dataset biases","author":"clark","year":"2019","journal-title":"EMNLP\/IJCNLP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref1","article-title":"Don’t just assume; look and answer: Overcoming priors for visual question answering","author":"agrawal","year":"2018","journal-title":"CVPR"},{"key":"ref9","article-title":"Learning by abstraction: The neural state machine","author":"hudson","year":"2019","journal-title":"NeurIPS"},{"key":"ref20","article-title":"Qanet: Combining local convolution with global self-attention for reading comprehension","author":"yu","year":"2018","journal-title":"ICLRE"}],"event":{"name":"2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","start":{"date-parts":[[2021,10,11]]},"location":"Montreal, BC, Canada","end":{"date-parts":[[2021,10,17]]}},"container-title":["2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9607382\/9607383\/09607679.pdf?arnumber=9607679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:51:43Z","timestamp":1652187103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9607679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iccvw54120.2021.00353","relation":{},"subject":[],"published":{"date-parts":[[2021,10]]}}}