{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:38:10Z","timestamp":1757309890182,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":57,"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":[{"name":"Anhui Provincial Natural Science Foundation","award":["2208085QF190"],"award-info":[{"award-number":["2208085QF190"]}]},{"name":"the National Nature Science Foundation of China","award":["62121002, 62232006, 62102384, 62272436"],"award-info":[{"award-number":["62121002, 62232006, 62102384, 62272436"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611990","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"3181-3189","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Frequency-based Zero-Shot Learning with Phase Augmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0341-9862","authenticated-orcid":false,"given":"Wanting","family":"Yin","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-5315","authenticated-orcid":false,"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2839-8693","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2580-9055","authenticated-orcid":false,"given":"Jiannan","family":"Ge","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0717-8659","authenticated-orcid":false,"given":"Pandeng","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2840-6235","authenticated-orcid":false,"given":"Chuanbin","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]}],"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\/TMM.2019.2954747"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_11"},{"key":"e_1_3_2_1_3_1","volume-title":"Momentdiff: Generative video moment retrieval from random to real. arXiv preprint arXiv:2307.02869","author":"Li Pandeng","year":"2023","unstructured":"Pandeng Li, Chen-Wei Xie, Hongtao Xie, Liming Zhao, Lei Zhang, Yun Zheng, Deli Zhao, and Yongdong Zhang. Momentdiff: Generative video moment retrieval from random to real. arXiv preprint arXiv:2307.02869, 2023."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351092"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547889"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_4"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.111"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"e_1_3_2_1_9_1","first-page":"26","article-title":"A deep visual-semantic embedding model","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc'Aurelio Ranzato, and Tomas Mikolov. Devise: A deep visual-semantic embedding model. NeurIPS, 26, 2013.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_10_1","volume-title":"Attribute-based classification for zero-shot visual object categorization","author":"Lampert Christoph H","year":"2013","unstructured":"Christoph H Lampert, Hannes Nickisch, and Stefan Harmeling. Attribute-based classification for zero-shot visual object categorization. IEEE transactions on pattern analysis and machine intelligence, 36(3):453--465, 2013."},{"key":"e_1_3_2_1_11_1","volume-title":"Zero-shot learning by convex combination of semantic embeddings. arXiv preprint arXiv:1312.5650","author":"Norouzi Mohammad","year":"2013","unstructured":"Mohammad Norouzi, Tomas Mikolov, Samy Bengio, Yoram Singer, Jonathon Shlens, Andrea Frome, Greg S Corrado, and Jeffrey Dean. Zero-shot learning by convex combination of semantic embeddings. arXiv preprint arXiv:1312.5650, 2013."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01200"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00961"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01268"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16230"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1981.12022"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1068\/p110337"},{"key":"e_1_3_2_1_18_1","first-page":"26","article-title":"Zero-shot learning through cross-modal transfer","author":"Socher Richard","year":"2013","unstructured":"Richard Socher, Milind Ganjoo, Christopher D Manning, and Andrew Ng. Zero-shot learning through cross-modal transfer. NeurIPS, 26, 2013.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_19_1","volume-title":"Zero-shot recognition with unreliable attributes. Advances in neural information processing systems, 27","author":"Jayaraman Dinesh","year":"2014","unstructured":"Dinesh Jayaraman and Kristen Grauman. Zero-shot recognition with unreliable attributes. Advances in neural information processing systems, 27, 2014."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00758"},{"key":"e_1_3_2_1_21_1","volume-title":"Attribute prototype network for zero-shot learning. arXiv preprint arXiv:2008.08290","author":"Xu Wenjia","year":"2020","unstructured":"Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele, and Zeynep Akata. Attribute prototype network for zero-shot learning. arXiv preprint arXiv:2008.08290, 2020."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_5"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00240"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_25_1","first-page":"10275","volume-title":"CVPR","author":"Xian Yongqin","year":"2019","unstructured":"Yongqin Xian, Saurabh Sharma, Bernt Schiele, and Zeynep Akata. f-vaegan-d2: A feature generating framework for any-shot learning. In CVPR, pages 10275--10284, 2019."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00722"},{"key":"e_1_3_2_1_27_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00089"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00859"},{"key":"e_1_3_2_1_30_1","first-page":"31","article-title":"Faster neural networks straight from jpeg","author":"Gueguen Lionel","year":"2018","unstructured":"Lionel Gueguen, Alex Sergeev, Ben Kadlec, Rosanne Liu, and Jason Yosinski. Faster neural networks straight from jpeg. NeurIPS, 31, 2018.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00414"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01367"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00712"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3203612"},{"key":"e_1_3_2_1_35_1","volume-title":"NeurIPS","author":"Rao Yongming","year":"2021","unstructured":"Yongming Rao, Wenliang Zhao, Zheng Zhu, Jiwen Lu, and Jie Zhou. Global filter networks for image classification. NeurIPS, 2021."},{"key":"e_1_3_2_1_36_1","volume-title":"ICCV","author":"Chen Guangyao","year":"2021","unstructured":"Guangyao Chen, Peixi Peng, Li Ma, Jia Li, Lin Du, and Yonghong Tian. Amplitude-phase recombination: Rethinking robustness of convolutional neural networks in frequency domain. In ICCV, 2021."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00788"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01515"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00019"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.20002"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00115"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01194"},{"key":"e_1_3_2_1_43_1","volume-title":"Advances in Neural Information Processing Systems","author":"Huynh Dat","year":"2020","unstructured":"Dat Huynh and Ehsan Elhamifar. Compositional zero-shot learning via fine-grained dense feature composition. Advances in Neural Information Processing Systems, 2020."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00454"},{"key":"e_1_3_2_1_45_1","volume-title":"Class normalization for (continual)? generalized zero-shot learning. arXiv preprint arXiv:2006.11328","author":"Skorokhodov Ivan","year":"2020","unstructured":"Ivan Skorokhodov and Mohamed Elhoseiny. Class normalization for (continual)? generalized zero-shot learning. arXiv preprint arXiv:2006.11328, 2020."},{"key":"e_1_3_2_1_46_1","first-page":"16622","article-title":"Hierarchical semantic-visual adaptation for zero-shot learning","volume":"34","author":"Chen Shiming","year":"2021","unstructured":"Shiming Chen, GuoSen Xie, Yang Liu, Qinmu Peng, Baigui Sun, Hao Li, Xinge You, and Ling Shao. Hsva: Hierarchical semantic-visual adaptation for zero-shot learning. NeurIPS, 34:16622-16634, 2021.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19909"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00746"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00913"},{"key":"e_1_3_2_1_50_1","volume-title":"The caltech-ucsd birds-200--2011 dataset","author":"Wah Catherine","year":"2011","unstructured":"Catherine Wah, Steve Branson, Peter Welinder, Pietro Perona, and Serge Belongie. The caltech-ucsd birds-200--2011 dataset. 2011."},{"key":"e_1_3_2_1_51_1","volume-title":"TPAMI","author":"Xian Yongqin","year":"2018","unstructured":"Yongqin Xian, Christoph H Lampert, Bernt Schiele, and Zeynep Akata. Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. TPAMI, 2018."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00581"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_29"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.473"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00986"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611990","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:12:29Z","timestamp":1755821549000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611990"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":57,"alternative-id":["10.1145\/3581783.3611990","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611990","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"}}]}}