{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T09:38:43Z","timestamp":1780479523406,"version":"3.54.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8968118","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"7702-7709","source":"Crossref","is-referenced-by-count":17,"title":["Analyzing Liquid Pouring Sequences via Audio-Visual Neural Networks"],"prefix":"10.1109","author":[{"given":"Justin","family":"Wilson","sequence":"first","affiliation":[{"name":"UNC Chapel Hill,Department of Computer Science,Chapel Hill,NC,USA,27599"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Auston","family":"Sterling","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill,Department of Computer Science,Chapel Hill,NC,USA,27599"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming C.","family":"Lin","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill,Department of Computer Science,Chapel Hill,NC,USA,27599"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","volume":"two","author":"rayleigh","year":"1945","journal-title":"The Theory of Sound"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.07.011"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2012-70638"},{"key":"ref32","author":"van den oord","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1805964.1805965"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9123-1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116251"},{"key":"ref35","article-title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","author":"perez","year":"0","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1609\/icaps.v26i1.13787","article-title":"Robot Motion Planning for Pouring Liquids","author":"pan","year":"2016","journal-title":"International Conference on Automated Planning and Scheduling (ICAPS)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref29","article-title":"Recognition and Pose Estimation of Rigid Transparent Objects with a Kinect Sensor","author":"lysenkov","year":"2008","journal-title":"Robotics Science and Systems (RSS)"},{"key":"ref2","first-page":"269","article-title":"The missing link: Modal synthesis","author":"adrien","year":"1991","journal-title":"Representations of Musical Signals"},{"key":"ref1","author":"abadi","year":"2015","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref20","author":"jaitly","year":"2013","journal-title":"Vocal Tract Length Perturbation (VTLP) improves speech recognition"},{"key":"ref22","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2897826.2927375"},{"key":"ref24","first-page":"282","article-title":"Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data","author":"lafferty","year":"2001","journal-title":"Proceedings of the Eighteenth International Conference on Machine Learning"},{"key":"ref23","first-page":"1097","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25"},{"key":"ref26","article-title":"Temporal Convolutional Networks for Action Segmentation and Detection","author":"lea","year":"2016","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21236\/AD0639109"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2016.2600527"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/RoMoCo.2013.6614613"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759326"},{"key":"ref13","first-page":"382","author":"van den doel","year":"1996","journal-title":"The sounds of physical shapes"},{"key":"ref14","article-title":"Artificial Neural Networks: Formal Models and Their Applications -ICANN 2005","author":"duch","year":"2005","journal-title":"15th International Conference Warsaw Poland September 11-15 2005 Proceedings Part II volume 3697 of Lecture Notes in Computer Science"},{"key":"ref15","article-title":"Object categorization in the sink: Learning behavior-grounded object categories with water","author":"griffith","year":"2012","journal-title":"ICRA Workshop on Semantic Perception 2012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(99)00002-0"},{"key":"ref18","article-title":"Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks","volume":"abs 1706 7156","author":"huzaifah","year":"2017","journal-title":"CoRR"},{"key":"ref19","author":"jain","year":"1999","journal-title":"Recurrent Neural Networks Design and Applications"},{"key":"ref4","article-title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","author":"bai","year":"2018","journal-title":"CoRR"},{"key":"ref3","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref6","author":"boyer","year":"2015","journal-title":"Continuous Auditory Feedback for Sensorimotor Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref8","author":"chollet","year":"2015","journal-title":"Keras"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964979"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1833349.1778806"},{"key":"ref9","article-title":"Learning Audio Feedback for Estimating Amount and Flow of Granular Material. Conference on Robot Learning","author":"clarke","year":"2018","journal-title":"Machine Learning Research"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2014.7041472"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_21"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843615500309"},{"key":"ref42","article-title":"ISNN: Impact Sound Neural Network for Audio-Visual Object Classification","author":"sterling","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989307"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/s101210663"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Macau, China","start":{"date-parts":[[2019,11,3]]},"end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08968118.pdf?arnumber=8968118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:08:19Z","timestamp":1757095699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8968118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8968118","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}