{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T02:40:34Z","timestamp":1755830434613,"version":"3.44.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683651","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"3252-3256","source":"Crossref","is-referenced-by-count":0,"title":["Adversarial Multi-label Prediction for Spoken and Visual Signal Tagging"],"prefix":"10.1109","author":[{"given":"Yue","family":"Deng","sequence":"first","affiliation":[{"name":"AI Center, Samsung Research America, Mountain View, CA, USA"}]},{"given":"KaWai","family":"Chen","sequence":"additional","affiliation":[{"name":"AI Center, Samsung Research America, Mountain View, CA, USA"}]},{"given":"Yilin","family":"Shen","sequence":"additional","affiliation":[{"name":"AI Center, Samsung Research America, Mountain View, CA, USA"}]},{"given":"Hongxia","family":"Jin","sequence":"additional","affiliation":[{"name":"AI Center, Samsung Research America, Mountain View, CA, USA"}]}],"member":"263","reference":[{"key":"ref10","first-page":"437","author":"nam","year":"2014","journal-title":"Large-Scale Multi-label Text Classification-Revisiting Neural Networks"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10769","article-title":"Learning deep latent spaces for multi-label classification","author":"yeh","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87481-2_4"},{"key":"ref14","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"2172","article-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Deep convolutional ranking for multilabel image annotation","year":"2013","author":"gong","key":"ref17"},{"key":"ref18","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/220"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401971"},{"article-title":"Attention and localization based on a deep convolutional recurrent model for weakly supervised audio tagging","year":"2017","author":"yong","key":"ref3"},{"key":"ref6","first-page":"730","article-title":"Sparse local embeddings for extreme multi-label classification","author":"bhatia","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00320"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2235082"},{"key":"ref7","first-page":"593","article-title":"Large-scale multi-label learning with missing labels","author":"yu","year":"0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966291"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2006.162"},{"key":"ref9","first-page":"405","article-title":"Efficient multi-label classification with many labels","author":"bi","year":"0"},{"article-title":"The chime corpus: a resource and a challenge for computational hearing in multisource environments","year":"0","author":"christensen","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/985692.985733"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"article-title":"The caltech-ucsd birds-200-2011 dataset","year":"2011","author":"wah","key":"ref23"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683651.pdf?arnumber=8683651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:18:52Z","timestamp":1755800332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683651","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}