{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T13:28:42Z","timestamp":1756992522251,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197566","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"1588-1594","source":"Crossref","is-referenced-by-count":5,"title":["Self-Supervised Learning for Alignment of Objects and Sound"],"prefix":"10.1109","author":[{"given":"Xinzhu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuchun","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibo","family":"Min","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","author":"ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention &#x2013; MICCAI 2015"},{"key":"ref30","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2009.09.005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref13","article-title":"Sound source separation using sparse coding with temporal continuity objective","volume":"2003","author":"virtanen","year":"2003","journal-title":"Proc ICMC"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2971713"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.277"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2007.4414315"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794166"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385565"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00398"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759215"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759213"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27526-6_36"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-015-0313-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461267"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794231"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179045"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487652"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2878157"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952687"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","volume":"37","author":"ephrat","year":"2018","journal-title":"ACM Transactions on Graphics (Proc SIGGRAPH)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref26","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2020,5,31]]},"location":"Paris, France","end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197566.pdf?arnumber=9197566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:54Z","timestamp":1656375114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197566\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197566","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}