{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T22:45:50Z","timestamp":1725576350812},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412231","type":"proceedings-article","created":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T22:15:54Z","timestamp":1620252954000},"page":"4324-4331","source":"Crossref","is-referenced-by-count":0,"title":["Dual Path Multi-Modal High-Order Features for Textual Content based Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Yanan","family":"Li","sequence":"first","affiliation":[]},{"given":"Yuetan","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Honghui","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Donghui","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"67","article-title":"Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes","author":"lyu","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00595"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00924"},{"key":"ref32","article-title":"Textboxes: A fast text detector with a single deep neural network","author":"liao","year":"0","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref31","first-page":"56","article-title":"Detecting text in natural image with connectionist text proposal network","author":"tian","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"journal-title":"Synthetic data and artificial neural networks for natural scene text recognition","year":"2014","author":"jaderberg","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref40","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies (NAACL-HLT)"},{"key":"ref11","article-title":"Compositional attention networks for machine reasoning","author":"hudson","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref12","first-page":"333","article-title":"Vizwiz: nearly real-time answers to visual questions","author":"bigham","year":"0","journal-title":"Proceedings of the 23nd Annual ACM Symposium on User Interface Software and Technology (UIST) ACM"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref15","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"0","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"journal-title":"Simple baseline for visual question answering","year":"2015","author":"zhou","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.500"},{"key":"ref3","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref6","article-title":"Gqa: a new dataset for compositional question answering over real-world images","author":"hudson","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref29","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref1","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref20","first-page":"4655","article-title":"Visual question answering with question representation update (qru)","author":"li","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.538"},{"journal-title":"Openimages A public dataset for large-scale multi-label and multi-class image classification","year":"2017","author":"krasin","key":"ref42"},{"key":"ref24","first-page":"4967","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/586"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219861"},{"key":"ref25","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412231.pdf?arnumber=9412231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:52Z","timestamp":1652182852000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412231","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}