{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:27:09Z","timestamp":1750220829954,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,14]],"date-time":"2019-10-14T00:00:00Z","timestamp":1571011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1722822"],"award-info":[{"award-number":["1722822"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,14]]},"DOI":"10.1145\/3340555.3356090","type":"proceedings-article","created":{"date-parts":[[2019,10,17]],"date-time":"2019-10-17T12:49:48Z","timestamp":1571316588000},"page":"477-481","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Coalescing Narrative and Dialogue for Grounded Pose Forecasting"],"prefix":"10.1145","author":[{"given":"Chaitanya","family":"Ahuja","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, USA"}]}],"member":"320","published-online":{"date-parts":[[2019,10,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925893"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353725"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"e_1_3_2_1_5_1","unstructured":"Yu-Wei Chao Jimei Yang Brian\u00a0L Price Scott Cohen and Jia Deng. [n. d.]. Forecasting Human Dynamics from Static Images.  Yu-Wei Chao Jimei Yang Brian\u00a0L Price Scott Cohen and Jia Deng. [n. d.]. Forecasting Human Dynamics from Static Images."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23974-8_14"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21996-7_17"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.494"},{"key":"e_1_3_2_1_9_1","unstructured":"S. Ginosar A. Bar G. Kohavi C. Chan A. Owens and J. Malik. [n. d.]. Learning Individual Styles of Conversational Gesture. In Computer Vision and Pattern Recognition (CVPR).  S. Ginosar A. Bar G. Kohavi C. Chan A. Owens and J. Malik. [n. d.]. Learning Individual Styles of Conversational Gesture. In Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_10_1","volume-title":"A Recurrent Variational Autoencoder for Human Motion Synthesis. BMVC17","author":"Habibie Ikhsanul","year":"2017","unstructured":"Ikhsanul Habibie , Daniel Holden , Jonathan Schwarz , Joe Yearsley , and Taku Komura . 2017. A Recurrent Variational Autoencoder for Human Motion Synthesis. BMVC17 ( 2017 ). Ikhsanul Habibie, Daniel Holden, Jonathan Schwarz, Joe Yearsley, and Taku Komura. 2017. A Recurrent Variational Autoencoder for Human Motion Synthesis. BMVC17 (2017)."},{"key":"e_1_3_2_1_11_1","volume-title":"Irish Conference on Artificial Intelligence and Cognitive Science. Springer, 144\u2013153","author":"Hanser Eva","year":"2009","unstructured":"Eva Hanser , Paul Mc\u00a0Kevitt , Tom Lunney , and Joan Condell . 2009 . Scenemaker: Intelligent multimodal visualisation of natural language scripts . In Irish Conference on Artificial Intelligence and Cognitive Science. Springer, 144\u2013153 . Eva Hanser, Paul Mc\u00a0Kevitt, Tom Lunney, and Joan Condell. 2009. Scenemaker: Intelligent multimodal visualisation of natural language scripts. In Irish Conference on Artificial Intelligence and Cognitive Science. Springer, 144\u2013153."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1996.503568"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01113"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/11821830_20"},{"key":"e_1_3_2_1_15_1","unstructured":"Angela\u00a0S Lin Lemeng Wu Rodolfo Corona Kevin Tai Qixing Huang and Raymond\u00a0J Mooney. 2018. 1. Generating Animated Videos of Human Activities from Natural Language Descriptions. Learning 2018(2018).  Angela\u00a0S Lin Lemeng Wu Rodolfo Corona Kevin Tai Qixing Huang and Raymond\u00a0J Mooney. 2018. 1. Generating Animated Videos of Human Activities from Natural Language Descriptions. Learning 2018(2018)."},{"key":"e_1_3_2_1_16_1","unstructured":"Xiao Lin and Mohamed\u00a0R Amer. 2018. Human motion modeling using dvgans. arXiv preprint arXiv:1804.10652(2018).  Xiao Lin and Mohamed\u00a0R Amer. 2018. Human motion modeling using dvgans. arXiv preprint arXiv:1804.10652(2018)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-007-9042-5"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Michael McAuliffe Michaela Socolof Sarah Mihuc Michael Wagner and Morgan Sonderegger. 2017. Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi.. In Interspeech. 498\u2013502.  Michael McAuliffe Michaela Socolof Sarah Mihuc Michael Wagner and Morgan Sonderegger. 2017. Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi.. In Interspeech. 498\u2013502.","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"e_1_3_2_1_20_1","unstructured":"Dario Pavllo David Grangier and Michael Auli. 2018. QuaterNet: A Quaternion-based Recurrent Model for Human Motion. arXiv preprint arXiv:1805.06485(2018).  Dario Pavllo David Grangier and Michael Auli. 2018. QuaterNet: A Quaternion-based Recurrent Model for Human Motion. arXiv preprint arXiv:1805.06485(2018)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3125739.3132594"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Petra Wagner Zofia Malisz and Stefan Kopp. 2014. Gesture and speech in interaction: An overview.  Petra Wagner Zofia Malisz and Stefan Kopp. 2014. Gesture and speech in interaction: An overview.","DOI":"10.1016\/j.specom.2013.09.008"}],"event":{"name":"ICMI '19: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","acronym":"ICMI '19","location":"Suzhou China"},"container-title":["2019 International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3340555.3356090","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3340555.3356090","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3340555.3356090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:29Z","timestamp":1750202009000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3340555.3356090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,14]]},"references-count":23,"alternative-id":["10.1145\/3340555.3356090","10.1145\/3340555"],"URL":"https:\/\/doi.org\/10.1145\/3340555.3356090","relation":{},"subject":[],"published":{"date-parts":[[2019,10,14]]},"assertion":[{"value":"2019-10-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}