{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T13:12:04Z","timestamp":1744290724641,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"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":[[2020,6]]},"DOI":"10.1109\/cvpr42600.2020.00971","type":"proceedings-article","created":{"date-parts":[[2020,8,5]],"date-time":"2020-08-05T21:20:05Z","timestamp":1596662405000},"page":"9687-9695","source":"Crossref","is-referenced-by-count":78,"title":["Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing"],"prefix":"10.1109","author":[{"given":"Vedika","family":"Agarwal","sequence":"first","affiliation":[]},{"given":"Rakshith","family":"Shetty","sequence":"additional","affiliation":[]},{"given":"Mario","family":"Fritz","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Re-implementation of show ask attend and answer A strong baseline for visual question answering [17] in pytorch","year":"2017","author":"zhang","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"journal-title":"Official code release for explainable neural computation via stack neural module networks","year":"2018","author":"hu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref13","article-title":"Compositional attention networks for machine reasoning","author":"hudson","year":"2018","journal-title":"ICLRE"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3529"},{"key":"ref17","article-title":"Show, ask, attend, and answer: A strong baseline for visual question answering","volume":"abs 1704 3162","author":"kazemi","year":"2017","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref19","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref28","article-title":"Adversarial scene editing: Automatic object removal from weak supervision","author":"shetty","year":"2018","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00681"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref6","article-title":"Are you talking to a machine? dataset and methods for multilingual image question answering","author":"gao","year":"2015","journal-title":"NeurIPS"},{"key":"ref29","article-title":"Visual question answering: A survey of methods and datasets","volume":"7","author":"wu","year":"2016","journal-title":"CVIU"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"journal-title":"Deeper LSTM and normalized CNN Visual Question Answering model","year":"2015","author":"lu","key":"ref20"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10442","article-title":"Learning to answer questions from image using convolutional neural network","author":"ma","year":"2016","journal-title":"AAAI"},{"key":"ref21","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref23","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":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1596"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00979"}],"event":{"name":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2020,6,13]]},"location":"Seattle, WA, USA","end":{"date-parts":[[2020,6,19]]}},"container-title":["2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9142308\/9156271\/09156407.pdf?arnumber=9156407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T21:51:26Z","timestamp":1667685086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9156407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/cvpr42600.2020.00971","relation":{},"subject":[],"published":{"date-parts":[[2020,6]]}}}