{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:23:41Z","timestamp":1750220621626,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3414023","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:26:53Z","timestamp":1602505613000},"page":"3911-3919","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Look, Listen and Infer"],"prefix":"10.1145","author":[{"given":"Ruijian","family":"Jia","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanmin","family":"Pang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianru","family":"Xue","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"volume-title":"Soundnet: Learning sound representations from unlabeled video. In Advances in Neural Information Processing Systems. 892--900.","year":"2016","author":"Aytar Yusuf","key":"e_1_3_2_2_3_1"},{"key":"e_1_3_2_2_4_1","unstructured":"Yusuf Aytar Carl Vondrick and Antonio Torralba. 2017. See hear and read: Deep aligned representations. arXiv preprint arXiv:1706.00932 (2017).  Yusuf Aytar Carl Vondrick and Antonio Torralba. 2017. See hear and read: Deep aligned representations. arXiv preprint arXiv:1706.00932 (2017)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.321"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539924"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"e_1_3_2_2_10_1","unstructured":"Vittorio Ferrari and Andrew Zisserman. 2008. Learning visual attributes. In Advances in Neural Information Processing Systems. 433--440.  Vittorio Ferrari and Andrew Zisserman. 2008. Learning visual attributes. In Advances in Neural Information Processing Systems. 433--440."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_2_2_12_1","unstructured":"David Harwath Antonio Torralba and James Glass. 2016. Unsupervised learning of spoken language with visual context. In Advances in Neural Information Processing Systems. 1858--1866.  David Harwath Antonio Torralba and James Glass. 2016. Unsupervised learning of spoken language with visual context. In Advances in Neural Information Processing Systems. 1858--1866."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2528--2531","year":"2018","author":"Hori Chiori","key":"e_1_3_2_2_16_1"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325019"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.473"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"volume-title":"Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence. 646--651","year":"2008","author":"Larochelle Hugo","key":"e_1_3_2_2_20_1"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.483"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"e_1_3_2_2_25_1","unstructured":"Shichen Liu Mingsheng Long Jianmin Wang and Michael I Jordan. 2018. Generalized zero-shot learning with deep calibration network. In Advances in Neural Information Processing Systems. 2005--2015.  Shichen Liu Mingsheng Long Jianmin Wang and Michael I Jordan. 2018. Generalized zero-shot learning with deep calibration network. In Advances in Neural Information Processing Systems. 2005--2015."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Danny Merkx Stefan L Frank and Mirjam Ernestus. 2019. Language learning using Speech to Image retrieval. arXiv preprint arXiv:1909.03795 (2019).  Danny Merkx Stefan L Frank and Mirjam Ernestus. 2019. Language learning using Speech to Image retrieval. arXiv preprint arXiv:1909.03795 (2019).","DOI":"10.21437\/Interspeech.2019-3067"},{"key":"e_1_3_2_2_27_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119.  Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2510--2513","year":"2018","author":"Qiu Yue","key":"e_1_3_2_2_29_1"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2018.8517977"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"volume-title":"Proceedings of the European Conference on Computer Vision. 0--0.","year":"2018","author":"Sur'is Didac","key":"e_1_3_2_2_35_1"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"e_1_3_2_2_37_1","unstructured":"Xinsheng Wang Shanmin Pang and Jihua Zhu. 2020. Domain segmentation and adjustment for generalized zero-shot learning. arXiv preprint arXiv:2002.00226 (2020).  Xinsheng Wang Shanmin Pang and Jihua Zhu. 2020. Domain segmentation and adjustment for generalized zero-shot learning. arXiv preprint arXiv:2002.00226 (2020)."},{"key":"e_1_3_2_2_38_1","unstructured":"Xinsheng Wang Shanmin Pang Jihua Zhu Zhongyu Li Zhiqiang Tian and Yaochen Li. 2019. Visual space optimization for zero-shot learning. arXiv preprint arXiv:1907.00330 (2019).  Xinsheng Wang Shanmin Pang Jihua Zhu Zhongyu Li Zhiqiang Tian and Yaochen Li. 2019. Visual space optimization for zero-shot learning. arXiv preprint arXiv:1907.00330 (2019)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.328"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.321"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.321"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.649"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Seattle WA USA","acronym":"MM '20"},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3414023","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3414023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:23Z","timestamp":1750197683000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3414023"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":45,"alternative-id":["10.1145\/3394171.3414023","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3414023","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}