{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T14:30:39Z","timestamp":1790001039195,"version":"4.0.1"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Infosys Center for AI, IIIT Delhi"},{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["T1 251RES1820"],"award-info":[{"award-number":["T1 251RES1820"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3351090","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"1304-1312","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Multi-Level Fusion based Class-aware Attention Model for Weakly Labeled Audio Tagging"],"prefix":"10.1145","author":[{"given":"Yifang","family":"Yin","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng-Jiun","family":"Chiou","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenguang","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harsh","family":"Shrivastava","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajiv Ratn","family":"Shah","sequence":"additional","affiliation":[{"name":"IIIT-Delhi, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roger","family":"Zimmermann","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Sound Event Detection Using Weakly Labeled Dataset with Stacked Convolutional and Recurrent Neural Network. Technical Report. DCASE2017 Challenge.","author":"Adavanne Sharath","year":"2017"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"J.-J. Aucouturier B. Defreville and F. Pachet. 2007. The Bag-of-frame Approach to Audio Pattern Recognition: A Sufficient Model for Urban Soundscapes But Not For Polyphonic Music . Journal of the Acoustical Society of America (2007) 881--91.  J.-J. Aucouturier B. Defreville and F. Pachet. 2007. The Bag-of-frame Approach to Audio Pattern Recognition: A Sufficient Model for Urban Soundscapes But Not For Polyphonic Music . Journal of the Acoustical Society of America (2007) 881--91.","DOI":"10.1121\/1.2750160"},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Neural Information Processing Systems. 892--900","author":"Aytar Yusuf","year":"2016"},{"key":"e_1_3_2_1_4_1","volume-title":"Class-aware Self-Attention for Audio Event Recognition. In ACM International Conference on Multimedia Retrieval. 28--36","author":"Chen Shizhe","year":"2018"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/463"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Jinxi Guo Ning Xu Li-Jia Li and Abeer Alwan. 2017. Attention Based CLDNNs for Short-Duration Acoustic Scene Classification. In Interspeech . 469--473.  Jinxi Guo Ning Xu Li-Jia Li and Abeer Alwan. 2017. Attention Based CLDNNs for Short-Duration Acoustic Scene Classification. In Interspeech . 469--473.","DOI":"10.21437\/Interspeech.2017-440"},{"key":"e_1_3_2_1_7_1","volume-title":"Deep Residual Learning for Image Recognition. In The IEEE Conference on Computer Vision and Pattern Recognition. 770--778","author":"He Kaiming","year":"2016"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_2_1_9_1","volume-title":"CNN Architectures for Large-scale Audio Classification. In IEEE International Conference on Acoustics, Speech and Signal Processing. 131--135","author":"Hershey S."},{"key":"e_1_3_2_1_10_1","volume-title":"International Conference on Machine Learning . 2127--2136","author":"Ilse Maximilian","year":"2018"},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Machine Learning. 448--456","author":"Ioffe Sergey","year":"2015"},{"key":"e_1_3_2_1_12_1","volume-title":"Audio Set Classification with Attention Model: A Probabilistic Perspective. In IEEE International Conference on Acoustics, Speech and Signal Processing . 316--320","author":"Kong Q."},{"key":"e_1_3_2_1_13_1","volume-title":"Plumbley","author":"Kong Qiuqiang","year":"2019"},{"key":"e_1_3_2_1_14_1","volume-title":"Cross Validation and Active Learning. In International Conference on Neural Information Processing Systems. 231--238","author":"Krogh Anders","year":"1994"},{"key":"e_1_3_2_1_15_1","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing. 326--330","author":"Kumar A."},{"key":"e_1_3_2_1_16_1","volume-title":"Ensemble of Convolutional Neural Networks for Weakly-Supervised Sound Event Detection Using Multiple Scale Input. Technical Report. DCASE2017 Challenge.","author":"Lee Donmoon","year":"2017"},{"key":"e_1_3_2_1_17_1","first-page":"i","volume":"201","author":"Lee J.","journal-title":"J. Nam."},{"key":"e_1_3_2_1_18_1","volume-title":"Combining Multi-Scale Features Using Sample-Level Deep Convolutional Neural Networks for Weakly Supervised Sound Event Detection. Technical Report. DCASE2017 Challenge.","author":"Lee Jongpil","year":"2017"},{"key":"e_1_3_2_1_19_1","volume-title":"MAM-RNN: Multi-level Attention Model Based RNN for Video Captioning. In International Joint Conference on Artificial Intelligence. 2208--2214","author":"Li Xuelong","year":"2017"},{"key":"e_1_3_2_1_20_1","volume-title":"Bilinear CNN Models for Fine-Grained Visual Recognition. In IEEE International Conference on Computer Vision. 1449--1457","author":"Lin T. Y."},{"key":"e_1_3_2_1_21_1","volume-title":"Event Localization in Music Auto-tagging. In ACM International Conference on Multimedia . 1048--1057","author":"Liu Jen-Yu","year":"2016"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Xianglai Meng Biao Leng and Guanglu Song. 2017. A Multi-level Weighted Representation for Person Re-identification. In Artificial Neural Networks and Machine Learning Alessandra Lintas Stefano Rovetta Paul F.M.J. Verschure and Alessandro E.P. Villa (Eds.). 80--88.  Xianglai Meng Biao Leng and Guanglu Song. 2017. A Multi-level Weighted Representation for Person Re-identification. In Artificial Neural Networks and Machine Learning Alessandra Lintas Stefano Rovetta Paul F.M.J. Verschure and Alessandro E.P. Villa (Eds.). 80--88.","DOI":"10.1007\/978-3-319-68612-7_10"},{"key":"e_1_3_2_1_23_1","volume-title":"DCASE 2017 Challenge Setup: Tasks, Datasets and Baseline System. In DCASE Workshop .","author":"Mesaros Annamaria","year":"2017"},{"key":"e_1_3_2_1_24_1","volume-title":"Efros","author":"Owens Andrew","year":"2018"},{"key":"e_1_3_2_1_25_1","volume-title":"Combining Multiple Sources of Knowledge in Deep CNNs for Action Recognition. In IEEE Winter Conference on Applications of Computer Vision. 1--8.","author":"Park E."},{"key":"e_1_3_2_1_26_1","volume-title":"DCASE 2017 Submission: Multiple Instance Learning for Sound Event Detection. Technical Report. DCASE2017 Challenge.","author":"Salamon Justin","year":"2017"},{"key":"e_1_3_2_1_27_1","volume-title":"Multimodal Analysis of User-generated Multimedia Content","author":"Shah Rajiv"},{"key":"e_1_3_2_1_28_1","volume-title":"AAAI Conference on Artificial Intelligence. 4263--4270","author":"Song Sijie","year":"2017"},{"key":"e_1_3_2_1_29_1","volume-title":"Visualizing Data using t-SNE . Journal of Machine Learning Research","author":"van der Maaten Laurens","year":"2008"},{"key":"e_1_3_2_1_30_1","volume-title":"Deep Learning for DCASE2017 Challenge. Technical Report. DCASE2017 Challenge.","author":"Vu Toan","year":"2017"},{"key":"e_1_3_2_1_31_1","volume-title":"A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling . CoRR","author":"Wang Yun","year":"2018"},{"key":"e_1_3_2_1_32_1","volume-title":"Plumbley","author":"Xu Yong","year":"2017"},{"key":"e_1_3_2_1_33_1","volume-title":"Large-Scale Weakly Supervised Audio Classification Using Gated Convolutional Neural Network. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing . 121--125","author":"Xu Y."},{"key":"e_1_3_2_1_34_1","volume-title":"Laplacian Sparse Coding of Scenes for Video Classification. In IEEE International Symposium on Multimedia. 499--506","author":"Yin Yifang","year":"2016"},{"key":"e_1_3_2_1_35_1","volume-title":"Geographic Information Use in Weakly-supervised Deep Learning for Landmark Recognition. In IEEE International Conference on Multimedia and Expo . 1015--1020","author":"Yin Yifang","year":"2017"},{"key":"e_1_3_2_1_36_1","volume-title":"Learning and Fusing Multimodal Deep Features for Acoustic Scene Categorization. In ACM International Conference on Multimedia. 1892--1900","author":"Yin Yifang","year":"2018"},{"key":"e_1_3_2_1_37_1","volume-title":"Multi-level Attention Model for Weakly Supervised Audio Classification. In Detection and Classification of Acoustic Scenes and Events 2018 Workshop . 188--192","author":"Yu Changsong","year":"2018"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","location":"Nice France","acronym":"MM '19","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351090","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:12Z","timestamp":1750201992000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":37,"alternative-id":["10.1145\/3343031.3351090","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351090","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}