{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T10:14:48Z","timestamp":1773310488189,"version":"3.50.1"},"reference-count":44,"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\/wacv45572.2020.9093592","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"1526-1534","source":"Crossref","is-referenced-by-count":29,"title":["Figure Captioning with Relation Maps for Reasoning"],"prefix":"10.1109","author":[{"given":"Charles","family":"Chen","sequence":"first","affiliation":[]},{"given":"Ruiyi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Eunyee","family":"Koh","sequence":"additional","affiliation":[]},{"given":"Sungchul","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Scott","family":"Cohen","sequence":"additional","affiliation":[]},{"given":"Ryan","family":"Rossi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref33","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2016","journal-title":"ICLRE"},{"key":"ref32","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"ACL"},{"key":"ref31","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"mao","year":"2014","journal-title":"arXiv preprint arXiv 1412 6632"},{"key":"ref30","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":"NIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_41"},{"key":"ref36","first-page":"4967","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"2017","journal-title":"NIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019436"},{"key":"ref34","article-title":"Self-critical sequence training for image captioning","author":"rennie","year":"2016","journal-title":"CVPR"},{"key":"ref10","first-page":"1292","article-title":"Image description using visual dependency representations","author":"elliott","year":"2013","journal-title":"EMNLP"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref14","first-page":"2296","article-title":"Are you talking to a machine? dataset and methods for multilingual image question","author":"gao","year":"2015","journal-title":"NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref17","article-title":"A focused dynamic attention model for visual question answering","author":"ilievski","year":"2016","journal-title":"arXiv preprint arXiv 1604 01485"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.538"},{"key":"ref28","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref27","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Workshop on Text Summarization Branches Out"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref6","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref5","article-title":"An actor-critic algorithm for sequence prediction","author":"bahdanau","year":"2017","journal-title":"ICLRE"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1181"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref1","article-title":"Bottom-up and top-down attention for image captioning and vqa","author":"anderson","year":"2017","journal-title":"CVPR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"ref22","article-title":"Figureqa: An annotated figure dataset for visual reasoning","author":"kahou","year":"2017","journal-title":"arXiv preprint arXiv 1710 07300"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref42","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"ICML"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref41","first-page":"451","article-title":"Ask, attend and answer: Exploring question-guided spatial attention for visual question answering","author":"xu","year":"2016","journal-title":"ECCV"},{"key":"ref23","first-page":"361","article-title":"Multimodal residual learning for visual qa","author":"kim","year":"2016","journal-title":"NIPS"},{"key":"ref44","article-title":"Simple baseline for visual question answering","author":"zhou","year":"2015","journal-title":"arXiv preprint arXiv 1512 00327"},{"key":"ref26","article-title":"Simple image description generator via a linear phrase-based approach","author":"lebret","year":"2014","journal-title":"arXiv preprint arXiv 1412 8419"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"}],"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\/09093592.pdf?arnumber=9093592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:17:03Z","timestamp":1656602223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093592\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093592","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}