{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:22Z","timestamp":1750309522997,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"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":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680793","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"4832-4840","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Label Learning with Block Diagonal Labels"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7742-9142","authenticated-orcid":false,"given":"Leqi","family":"Shen","sequence":"first","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5843-6411","authenticated-orcid":false,"given":"Sicheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5023-9288","authenticated-orcid":false,"given":"Yifeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"jd.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4180-5801","authenticated-orcid":false,"given":"Hui","family":"Chen","sequence":"additional","affiliation":[{"name":"BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4043-8693","authenticated-orcid":false,"given":"Jundong","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6031-5245","authenticated-orcid":false,"given":"Pengzhang","family":"Liu","sequence":"additional","affiliation":[{"name":"jd.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7816-0587","authenticated-orcid":false,"given":"Yongjun","family":"Bao","sequence":"additional","affiliation":[{"name":"jd.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0137-9975","authenticated-orcid":false,"given":"Guiguang","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00472"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3025814"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19910"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00099"},{"key":"e_1_3_2_1_8_1","volume-title":"Autoaugment: Learning augmentation policies from data. arXiv:1805.09501","author":"Cubuk Ekin D","year":"2018","unstructured":"Ekin D Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, and Quoc V Le. 2018. Autoaugment: Learning augmentation policies from data. arXiv:1805.09501 (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557011"},{"key":"e_1_3_2_1_11_1","volume-title":"Improved regularization of convolutional neural networks with cutout. arXiv:1708.04552","author":"DeVries Terrance","year":"2017","unstructured":"Terrance DeVries and Graham W Taylor. 2017. Improved regularization of convolutional neural networks with cutout. arXiv:1708.04552 (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00331"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00074"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00944"},{"key":"e_1_3_2_1_17_1","volume-title":"Large Loss Matters in Weakly Supervised Multi-Label Classification. In IEEE Conference on Computer Vision and Pattern Recognition. 14156--14165","author":"Kim Youngwook","year":"2022","unstructured":"Youngwook Kim, Jae Myung Kim, Zeynep Akata, and Jungwoo Lee. 2022. Large Loss Matters in Weakly Supervised Multi-Label Classification. In IEEE Conference on Computer Vision and Pattern Recognition. 14156--14165."},{"key":"e_1_3_2_1_18_1","volume-title":"Bridging the Gap Between Model Explanations in Partially Annotated Multi-Label Classification. In IEEE Conference on Computer Vision and Pattern Recognition. 3408--3417","author":"Kim Youngwook","year":"2023","unstructured":"Youngwook Kim, Jae Myung Kim, Jieun Jeong, Cordelia Schmid, Zeynep Akata, and Jungwoo Lee. 2023. Bridging the Gap Between Model Explanations in Partially Annotated Multi-Label Classification. In IEEE Conference on Computer Vision and Pattern Recognition. 3408--3417."},{"key":"e_1_3_2_1_19_1","volume-title":"Adam: A method for stochastic optimization. arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781680832136"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_22_1","volume-title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale. arXiv:1811.00982","author":"Kuznetsova Alina","year":"2018","unstructured":"Alina Kuznetsova, Hassan Rom, Neil Alldrin, Jasper Uijlings, Ivan Krasin, Jordi Pont-Tuset, Shahab Kamali, Stefan Popov, Matteo Malloci, Tom Duerig, and Vittorio Ferrari. 2018. The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale. arXiv:1811.00982 (2018)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_24_1","volume-title":"International Conference on Machine Learning. PMLR, 22249--22265","author":"Liu Biao","year":"2023","unstructured":"Biao Liu, Ning Xu, Jiaqi Lv, and Xin Geng. 2023. Revisiting pseudo-label for single-positive multi-label learning. In International Conference on Machine Learning. PMLR, 22249--22265."},{"key":"e_1_3_2_1_25_1","volume-title":"Query2label: A simple transformer way to multi-label classification. arXiv:2107.10834","author":"Liu Shilong","year":"2021","unstructured":"Shilong Liu, Lei Zhang, Xiao Yang, Hang Su, and Jun Zhu. 2021. Query2label: A simple transformer way to multi-label classification. arXiv:2107.10834 (2021)."},{"key":"e_1_3_2_1_26_1","volume-title":"Decoupled weight decay regularization. arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20105"},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Machine Learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00144"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00012"},{"key":"e_1_3_2_1_32_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_33_1","volume-title":"A disciplined approach to neural network hyper-parameters: Part 1-learning rate, batch size, momentum, and weight decay. arXiv:1803.09820","author":"Smith Leslie N","year":"2018","unstructured":"Leslie N Smith. 2018. A disciplined approach to neural network hyper-parameters: Part 1-learning rate, batch size, momentum, and weight decay. arXiv:1803.09820 (2018)."},{"key":"e_1_3_2_1_34_1","volume-title":"Dualcoop: Fast adaptation to multi-label recognition with limited annotations. In Advances in Neural Information Processing Systems. 30569--30582.","author":"Sun Ximeng","year":"2022","unstructured":"Ximeng Sun, Ping Hu, and Kate Saenko. 2022. Dualcoop: Fast adaptation to multi-label recognition with limited annotations. In Advances in Neural Information Processing Systems. 30569--30582."},{"key":"e_1_3_2_1_35_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Tarvainen Antti","year":"2017","unstructured":"Antti Tarvainen and Harri Valpola. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In Advances in Neural Information Processing Systems, Vol. 30."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611988"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1038\/435439a"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_10"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414046"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467259"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00776"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.37"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00237"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547834"},{"key":"e_1_3_2_1_45_1","volume-title":"Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. In Advances in Neural Information Processing Systems. 18408--18419.","author":"Zhang Bowen","year":"2021","unstructured":"Bowen Zhang, Yidong Wang, Wenxin Hou, Hao Wu, Jindong Wang, Manabu Okumura, and Takahiro Shinozaki. 2021. Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. In Advances in Neural Information Processing Systems. 18408--18419."},{"key":"e_1_3_2_1_46_1","volume-title":"Simple and Robust Loss Design for Multi-Label Learning with Missing Labels. arXiv:2112.07368","author":"Zhang Youcai","year":"2021","unstructured":"Youcai Zhang, Yuhao Cheng, Xinyu Huang, Fei Wen, Rui Feng, Yaqian Li, and Yandong Guo. 2021. Simple and Robust Loss Design for Multi-Label Learning with Missing Labels. arXiv:2112.07368 (2021)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680793","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:07Z","timestamp":1750295887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680793"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":46,"alternative-id":["10.1145\/3664647.3680793","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680793","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}