{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:21:24Z","timestamp":1772907684636,"version":"3.50.1"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"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":[[2020,3]]},"DOI":"10.1109\/wacv45572.2020.9093616","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"2959-2968","source":"Crossref","is-referenced-by-count":70,"title":["See the Sound, Hear the Pixels"],"prefix":"10.1109","author":[{"given":"Janani","family":"Ramaswamy","sequence":"first","affiliation":[]},{"given":"Sukhendu","family":"Das","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/385308a0"},{"key":"ref33","first-page":"5","article-title":"Image question answering: A visual semantic embedding model and a new dataset","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref32","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":"ref31","first-page":"801","article-title":"Ambient sound provides supervision for visual learning","author":"owens","year":"2016","journal-title":"Proceedings of the European Confference on Computer Vision (ECCV)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref37","article-title":"Audiovisual scene analysis: evidence for a “ very-early” integration process in audio-visual speech perception","author":"schwartz","year":"2002","journal-title":"Seventh International Conference on Spoken Language Processing"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01283"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2007.1910"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref29","first-page":"631","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"Proceedings of the European Confference on Computer Vision (ECCV)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2228476"},{"key":"ref22","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.274"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref23","first-page":"7763","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","author":"korbar","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2911488"},{"key":"ref53","first-page":"570","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"Proceedings of the European Confference on Computer Vision (ECCV)"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref12","first-page":"35","article-title":"Learning to separate object sounds by watching unlabeled video","author":"gao","year":"2018","journal-title":"Proceedings of the European Confference on Computer Vision (ECCV)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00398"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref15","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"813","article-title":"Audio vision: Using audiovisual synchrony to locate sounds","author":"hershey","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref18","first-page":"2352","article-title":"End-to-end audio visual scene-aware dialog using mul-timodal attention-based video features","author":"hori","year":"2019","journal-title":"IEEE Int Conf Acoust Speech an Signal Process (ICASSP)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00947"},{"key":"ref4","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":"ref3","first-page":"435","article-title":"Objects that sound","author":"arandjelovic","year":"2018","journal-title":"Proceedings of the European Confference on Computer Vision (ECCV)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383344"},{"key":"ref5","article-title":"See, hear, and read: Deep aligned representations","author":"aytar","year":"2017"},{"key":"ref8","first-page":"251","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Asian Conf Computer Vision"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2746267"},{"key":"ref9","first-page":"772","article-title":"Learning joint statistical models for audio-visual fusion and segregation","author":"fisher iii","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298968"},{"key":"ref45","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proceedings of the European Confference on Computer Vision (ECCV)"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00097"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"ref41","first-page":"662","article-title":"Separating style and content","author":"tenenbaum","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref44","first-page":"247","article-title":"Audio-visual event localization in unconstrained videos","author":"tian","year":"2018","journal-title":"Proceedings of the European Confference on Computer Vision (ECCV)"},{"key":"ref43","article-title":"An attempt towards interpretable audio-visual video captioning","author":"tian","year":"2018"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","location":"Snowmass Village, CO, USA","start":{"date-parts":[[2020,3,1]]},"end":{"date-parts":[[2020,3,5]]}},"container-title":["2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9087828\/9093261\/09093616.pdf?arnumber=9093616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:18:25Z","timestamp":1656602305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093616\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093616","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}