{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T19:46:45Z","timestamp":1786132005244,"version":"build-2736575974"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"EPSRC Programme","award":["EP\/T028572\/1"],"award-info":[{"award-number":["EP\/T028572\/1"]}]},{"name":"Royal Society Research Professorship","award":["RP\/R1\/191132"],"award-info":[{"award-number":["RP\/R1\/191132"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tpami.2026.3690989","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T19:40:57Z","timestamp":1778096457000},"page":"11111-11123","source":"Crossref","is-referenced-by-count":0,"title":["The Sound of Water: Inferring Physical Properties From Pouring Liquids"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7533-5337","authenticated-orcid":false,"given":"Piyush","family":"Bagad","sequence":"first","affiliation":[{"name":"University of Oxford","place":["Oxford, U.K."]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8800-9015","authenticated-orcid":false,"given":"Makarand","family":"Tapaswi","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad","place":["Hyderabad, Telangana, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[{"name":"University of Amsterdam","place":["Amsterdam, WP, The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8945-8573","authenticated-orcid":false,"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"University of Oxford","place":["Oxford, U.K."]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/\/0096-1523.26.1.313"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0956797618813319"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/joss.12052"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.31234\/osf.io\/eb9pj","article-title":"Hearing water temperature: Characterizing the development of nuanced perception of auditory events","volume-title":"Proc. Annu. Meeting Cogn. Sci. Soc.","author":"Agrawal"},{"key":"ref5","article-title":"You can hear the difference between hot and cold water","author":"Scott","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4324\/9781315740218"},{"key":"ref7","volume-title":"The Theory of Sound","volume":"2","author":"Rayleigh","year":"1896"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1119\/1.12960"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1119\/1.13147"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/s101210663"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.13.171"},{"key":"ref12","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.39"},{"key":"ref16","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889950"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/105474600566907"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.32470\/CCN.2018.1057-0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.26.1.279"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9280.00040"},{"key":"ref23","first-page":"95","article-title":"Size, shape, and material properties of sound models","volume-title":"The Sounding Object","author":"Rocchesso","year":"2003"},{"key":"ref24","volume-title":"Psychoacoustics: Facts and Models","author":"Zwicker","year":"2013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1068\/p080311"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1080\/25742442.2023.2218262"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-013-0424-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989307"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v26i1.13787"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103692"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206626"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967802"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967911"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981195"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593654"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811898"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759326"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.207"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1039\/d1dd00014d"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00883"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812000"},{"key":"ref42","article-title":"Detection and tracking of liquids with fully convolutional networks","author":"Schenck","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50115-4_43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00029"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917734052"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968118"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68793-9_33"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968303"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340859"},{"key":"ref50","article-title":"Pouring dynamics estimation using gated recurrent units","author":"Zheng","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_21"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747349"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968303"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340859"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref58","article-title":"Contrastive audio-visual masked autoencoder","author":"Gong","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00791"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01479"},{"key":"ref61","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022"},{"key":"ref62","article-title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Asano"},{"key":"ref63","article-title":"Active contrastive learning of audio-visual video representations","author":"Ma","year":"2020"},{"key":"ref64","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Akbari"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0894"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref67","first-page":"7774","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Korbar"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"ref70","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alwassel"},{"key":"ref71","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Aytar"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref76","article-title":"Listen, think, and understand","author":"Gong","year":"2023"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_28"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1943"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00240"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447380"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_3"},{"key":"ref84","article-title":"Qwen3-Omni technical report","author":"Xu","year":"2025"},{"key":"ref85","article-title":"Video models are zero-shot learners and reasoners","author":"Wiedemer","year":"2025"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.31.267"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916116"},{"key":"ref88","article-title":"End corrections, natural frequencies, tone colour and physical modelling of organ pipes","author":"Pykett","year":"2013"},{"key":"ref89","article-title":"Tuning of musical glasses","author":"Guignard","year":"2003"},{"key":"ref90","article-title":"DDSP: Differentiable digital signal processing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Engel"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref92","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref96","first-page":"535","article-title":"PESTO: Pitch estimation with self-supervised transposition-equivariant objective","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Riou"},{"issue":"11","key":"ref97","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1038\/012449a0"},{"key":"ref100","article-title":"Why can you hear a difference between pouring hot and cold water? An investigation of temperature dependence in psychoacoustics","volume-title":"Proc. 145th Audio Eng. Soc. Conv.","author":"Peng"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11643729\/11509639.pdf?arnumber=11509639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T19:05:42Z","timestamp":1786129542000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11509639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":100,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3690989","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}