{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:36:11Z","timestamp":1776101771959,"version":"3.50.1"},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":[[2019,6]]},"DOI":"10.1109\/cvpr.2019.00901","type":"proceedings-article","created":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T21:06:13Z","timestamp":1578603973000},"page":"8799-8809","source":"Crossref","is-referenced-by-count":59,"title":["Social-IQ: A Question Answering Benchmark for Artificial Social Intelligence"],"prefix":"10.1109","author":[{"given":"Amir","family":"Zadeh","sequence":"first","affiliation":[{"name":"CMU LTI"}]},{"given":"Michael","family":"Chan","sequence":"additional","affiliation":[{"name":"CMU"}]},{"given":"Paul Pu","family":"Liang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon Univ."}]},{"given":"Edmund","family":"Tong","sequence":"additional","affiliation":[{"name":"CMU"}]},{"given":"Louis-Philippe","family":"Morency","sequence":"additional","affiliation":[{"name":"Carnegie Mellon Univ."}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1080\/1359813990100202"},{"key":"ref38","first-page":"193","article-title":"Mctest: A challenge dataset for the open-domain machine comprehension of text","author":"richardson","year":"2013","journal-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing"},{"key":"ref33","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"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00710"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref30","first-page":"10","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc of Workshop on Text Summarization Branches Out at ACL"},{"key":"ref37","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"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref35","article-title":"easurement of social intelligence","author":"o\u2019sullivan","year":"1965"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00896"},{"key":"ref60","article-title":"Leveraging video descriptions to learn video question answering","author":"zeng","year":"2016"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref63","first-page":"4995","article-title":"Visual7w: Grounded question answering in images","author":"zhu","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(82)90005-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1490365"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(92)90005-R"},{"key":"ref20","article-title":"Densely connected convolutional networks","author":"huang","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2245653"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/h0075832"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01267-0_41","article-title":"Multimodal dual attention memory for video story question answering","author":"kim","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807947.017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1162\/tacl_a_00023","article-title":"The narrativeqa reading comprehension challenge","volume":"6","author":"ko?isk?","year":"2018","journal-title":"Transactions of the Association of Computational Linguistics"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1009"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref56","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12021","article-title":"Memory fusion network for multi-view sequential learning","author":"zadeh","year":"2018","journal-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref55","article-title":"Tensor fusion network for mul-timodal sentiment analysis","author":"zadeh","year":"2017","journal-title":"Empirical Methods in Natural Language Processing-EMNLP"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0065-2458(08)60390-3","article-title":"Semantics and quantification in natural language question answering","volume":"17","author":"a woods","year":"1978","journal-title":"Advances in Computers"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.paid.2006.04.027"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511810831.005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref40","author":"rossmann","year":"2010","journal-title":"Theory of reasoned action-theory of planned behavior"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1973","DOI":"10.21437\/Interspeech.2011-519","article-title":"Joint robust voicing detection and pitch estimation based on residual harmonics","author":"drugman","year":"2011","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2170835"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00630"},{"key":"ref15","first-page":"2296","article-title":"Are you talking to a machine? dataset and methods for multilingual image question","author":"gao","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1037\/0021-9010.76.2.299"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1460690.1460714"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08043-7_2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00769"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(97)00020-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.54.4.541"},{"key":"ref7","article-title":"Multimodal machine learning: A survey and taxonomy","author":"baltru\u0161aitis","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref49","article-title":"Movie question answering: Remembering the textual cues for layered visual contents","author":"wang","year":"2018","journal-title":"AAAI"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.402044"},{"key":"ref46","article-title":"Learning factorized multimodal representations","author":"tsai","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1037\/h0053850"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.2466\/pr0.1973.33.3.839"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1080\/00224545.1933.9921556"},{"key":"ref42","author":"sztompka","year":"2002","journal-title":"Socjologia znak"},{"key":"ref41","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref44","article-title":"Intelligence and its uses","author":"l thorndike","year":"1920","journal-title":"Harper’s Magazine"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"}],"event":{"name":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Long Beach, CA, USA","start":{"date-parts":[[2019,6,15]]},"end":{"date-parts":[[2019,6,20]]}},"container-title":["2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8938205\/8953184\/08953344.pdf?arnumber=8953344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T18:43:39Z","timestamp":1753901019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8953344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2019.00901","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}