{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T06:29:14Z","timestamp":1725604154208},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412062","type":"proceedings-article","created":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T22:15:54Z","timestamp":1620252954000},"page":"6501-6508","source":"Crossref","is-referenced-by-count":1,"title":["Unsupervised Sound Source Localization From Audio-Image Pairs Using Input Gradient Map"],"prefix":"10.1109","author":[{"given":"Tomohiro","family":"Tanaka","sequence":"first","affiliation":[]},{"given":"Takahiro","family":"Shinozaki","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Deep co-clustering for unsupervised audiovisual learning","year":"2018","author":"hu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8655(95)00050-Q"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref13","article-title":"Coherent dialogue with attention-based language models","author":"mei","year":"0","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref14","first-page":"360","article-title":"Self-supervised generation of spatial audio for 360° video","author":"morgado","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"631","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"International Conference on Learning Representations"},{"journal-title":"Striving for simplicity The all convolutional net","year":"2014","author":"springenberg","key":"ref19"},{"journal-title":"Looking to listen at the cocktail party A speaker-independent audio-visual model for speech separation","year":"2018","author":"ephrat","key":"ref4"},{"key":"ref3","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"journal-title":"2 5 D visual sound","year":"2018","author":"gao","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref8","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"0","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053326"},{"journal-title":"End-to-end continuous speech recognition using attention-based recurrent nn First results","year":"2014","author":"chorowski","key":"ref2"},{"key":"ref1","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref22","first-page":"570","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412062.pdf?arnumber=9412062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:47Z","timestamp":1652182847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412062","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}