{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:08:26Z","timestamp":1780765706931,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106022, U19B2036, 62225601"],"award-info":[{"award-number":["62106022, U19B2036, 62225601"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation Project","award":["Z200002"],"award-info":[{"award-number":["Z200002"]}]},{"name":"Youth Innovative Research Team of BUPT","award":["2023QNTD02"],"award-info":[{"award-number":["2023QNTD02"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612274","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"3415-3423","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Hierarchical Visual Attribute Learning in the Wild"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4726-093X","authenticated-orcid":false,"given":"Kongming","family":"Liang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Bejing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8793-2174","authenticated-orcid":false,"given":"Xinran","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Bejing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1119-2004","authenticated-orcid":false,"given":"Haiwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Bejing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-2488","authenticated-orcid":false,"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Bejing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9045-1339","authenticated-orcid":false,"given":"Jun","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Bejing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"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","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. https:\/\/doi.org\/10.48550\/ARXIV.2005.14165","DOI":"10.48550\/ARXIV.2005.14165"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3274593"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01131"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"e_1_3_2_1_7_1","volume-title":"Multi-Label Image Recognition with Graph Convolutional Networks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Chen Zhao-Min","year":"2019","unstructured":"Zhao-Min Chen, Xiu-Shen Wei, Peng Wang, and Yanwen Guo. 2019a. Multi-Label Image Recognition with Graph Convolutional Networks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Roi Cohen Mor Geva Jonathan Berant and Amir Globerson. 2023. Crawling the Internal Knowledge-Base of Language Models. https:\/\/doi.org\/10.48550\/ARXIV.2301.12810","DOI":"10.48550\/ARXIV.2301.12810"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"J. Deng W. Dong R. Socher L.-J. Li K. Li and L. Fei-Fei. 2009. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR09.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_10_1","unstructured":"Ruoyi Du Wenqing Yu Heqing Wang Dongliang Chang Ting-En Lin Yongbin Li and Zhanyu Ma. 2022. Multi-View Active Fine-Grained Recognition. arxiv: 2206.01153 [cs.CV]"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Fabrizio Gilardi Meysam Alizadeh and Ma\u00ebl Kubli. 2023. ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks. arxiv: 2303.15056 [cs.CL]","DOI":"10.1073\/pnas.2305016120"},{"key":"e_1_3_2_1_12_1","volume-title":"Lin (Eds.)","volume":"33","author":"Giunchiglia Eleonora","year":"2020","unstructured":"Eleonora Giunchiglia and Thomas Lukasiewicz. 2020. Coherent Hierarchical Multi-Label Classification Networks. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 9662--9673. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/6dd4e10e3296fa63738371ec0d5df818-Paper.pdf"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00100"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01376"},{"key":"e_1_3_2_1_15_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240649"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2836461"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Kongming Liang Yuhong Guo Hong Chang and Xilin Chen. 2017. Incomplete Attribute Learning with auxiliary labels.. In IJCAI. 2252--2258.","DOI":"10.24963\/ijcai.2017\/313"},{"key":"e_1_3_2_1_19_1","unstructured":"Tsung-Yi Lin Michael Maire Serge Belongie Lubomir Bourdev Ross Girshick James Hays Pietro Perona Deva Ramanan C. Lawrence Zitnick and Piotr Doll\u00e1r. 2015. Microsoft COCO: Common Objects in Context. arxiv: 1405.0312 [cs.CV]"},{"key":"e_1_3_2_1_20_1","unstructured":"Shilong Liu Lei Zhang Xiao Yang Hang Su and Jun Zhu. 2021b. Query2Label: A Simple Transformer Way to Multi-Label Classification. arxiv: 2107.10834 [cs.CV]"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_22_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00479"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"e_1_3_2_1_25_1","volume-title":"Chils: Zero-shot image classification with hierarchical label sets. arXiv preprint arXiv:2302.02551","author":"Novack Zachary","year":"2023","unstructured":"Zachary Novack, Saurabh Garg, Julian McAuley, and Zachary C Lipton. 2023. Chils: Zero-shot image classification with hierarchical label sets. arXiv preprint arXiv:2302.02551 (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. https:\/\/doi.org\/10.48550\/ARXIV.2203.02155","DOI":"10.48550\/ARXIV.2203.02155"},{"key":"e_1_3_2_1_27_1","volume-title":"ICLR 2022 Poster","author":"Patel Dhruvesh","year":"2022","unstructured":"Dhruvesh Patel, Pavitra Dangati, Jay-Yoon Lee, Michael Boratko, and Andrew McCallum. 2022. Modeling label space interactions in multi-label classification using box embeddings. ICLR 2022 Poster (2022)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_6"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_12"},{"key":"e_1_3_2_1_31_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. arxiv: 2103.00020 [cs.CV]"},{"key":"e_1_3_2_1_32_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"e_1_3_2_1_34_1","volume-title":"Learning representations by back-propagating errors. nature","author":"Rumelhart David E","year":"1986","unstructured":"David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. 1986. Learning representations by back-propagating errors. nature, Vol. 323, 6088 (1986), 533--536."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475406"},{"key":"e_1_3_2_1_37_1","volume-title":"Tel Aviv","author":"Uijlings Jasper","year":"2022","unstructured":"Jasper Uijlings, Thomas Mensink, and Vittorio Ferrari. 2022. The Missing Link: Finding label relations across datasets. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part VIII. Springer, 540--556."},{"key":"e_1_3_2_1_38_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_39_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475191"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548336"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00039"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612274","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:07:45Z","timestamp":1755821265000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612274"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":42,"alternative-id":["10.1145\/3581783.3612274","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612274","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}