{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:47:21Z","timestamp":1776491241497,"version":"3.51.2"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"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":[[2020,3]]},"DOI":"10.1109\/wacv45572.2020.9093494","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"1487-1496","source":"Crossref","is-referenced-by-count":36,"title":["Answering Questions about Data Visualizations using Efficient Bimodal Fusion"],"prefix":"10.1109","author":[{"given":"Kushal","family":"Kafle","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robik","family":"Shrestha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Price","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Cohen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Kanan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.93"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref33","article-title":"A question-answering framework for plots using deep learning","author":"reddy","year":"2018","journal-title":"arXiv preprint arXiv 1806 04655"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13193"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11671","article-title":"FiLM: Visual Reasoning with a General Conditioning Layer","author":"perez","year":"2018","journal-title":"AAAI"},{"key":"ref30","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01072"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047247"},{"key":"ref35","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"2017","journal-title":"NeurIPS"},{"key":"ref34","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.50"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00291"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2019.00028"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref4","article-title":"Don’t just assume; look and answer: Overcoming priors for visual question answering","author":"agrawal","year":"2018","journal-title":"CVPR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"ref6","article-title":"Deep compositional question answering with neural module networks","author":"andreas","year":"2016","journal-title":"CVPR"},{"key":"ref29","article-title":"The visual QA devil in the details: The impact of early fusion and batch norm on clevr","author":"malinowski","year":"2018","journal-title":"arXiv preprint arXiv 1809 04482"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1078"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018076"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71249-9_9"},{"key":"ref1","article-title":"VQD: Visual query detection in natural scenes","author":"acharya","year":"2019","journal-title":"NAACL"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3529"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2013.6637202"},{"key":"ref21","article-title":"FigureQA: An annotated figure dataset for visual reasoning","author":"kahou","year":"2017","journal-title":"arXiv preprint arXiv 1710 07300"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref41","article-title":"Understanding neural networks through deep visualization","author":"yosinski","year":"2015","journal-title":"arXiv preprint arXiv 1506 06579"},{"key":"ref23","article-title":"Show, ask, attend, and answer: A strong baseline for visual question answering","author":"kazemi","year":"2017","journal-title":"arXiv preprint arXiv 1704 03162"},{"key":"ref26","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"NeurIPS"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","location":"Snowmass Village, CO, USA","start":{"date-parts":[[2020,3,1]]},"end":{"date-parts":[[2020,3,5]]}},"container-title":["2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9087828\/9093261\/09093494.pdf?arnumber=9093494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T19:44:07Z","timestamp":1666554247000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093494","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}