{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:51:26Z","timestamp":1765309886380,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755258","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"3962-3971","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DFCNet: Dual-Factor Compensatory Clustering Network for Modality-Imbalanced Generalized Zero-Shot Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2730-9394","authenticated-orcid":false,"given":"Xiangyu","family":"Shan","sequence":"first","affiliation":[{"name":"College of Information Engineering, Yangzhou University, Yangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8495-9582","authenticated-orcid":false,"given":"Heng","family":"Song","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Yangzhou University, yangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5810-613X","authenticated-orcid":false,"given":"Junwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Yangzhou University, Yangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Culotta (Eds.)","volume":"22","author":"Palatucci Mark","year":"2009","unstructured":"Mark Palatucci, Dean Pomerleau, Geoffrey E Hinton, and Tom M Mitchell. 2009. Zero-shot Learning with Semantic Output Codes. In Advances in Neural Information Processing Systems, Y. Bengio, D. Schuurmans, J. Lafferty, C. Williams, and A. Culotta (Eds.), Vol. 22. Curran Associates, Inc. https:\/\/proceedings.neurips. cc\/paper_files\/paper\/2009\/file\/1543843a4723ed2ab08e18053ae6dc5b-Paper.pdf"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00450"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00313"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_28"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093438"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Wang Hao","year":"2024","unstructured":"Hao Wang, Shengda Luo, Guosheng Hu, and Jianguo Zhang. 2024. Gradientguided modality decoupling for missing-modality robustness. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 15483--15491."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01918"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00612"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3404492"},{"key":"e_1_3_2_1_11_1","volume-title":"Regularizing neural networks by penalizing confident output distributions. arXiv preprint arXiv:1701.06548","author":"Pereyra Gabriel","year":"2017","unstructured":"Gabriel Pereyra, George Tucker, Jan Chorowski, Lukasz Kaiser, and Geoffrey Hinton. 2017. Regularizing neural networks by penalizing confident output distributions. arXiv preprint arXiv:1701.06548 (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.34034"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 10275--10284","author":"Xian Yongqin","year":"2019","unstructured":"Yongqin Xian, Saurabh Sharma, Bernt Schiele, and Zeynep Akata. 2019. fvaegan- d2: A feature generating framework for any-shot learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 10275--10284."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00680"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611759"},{"key":"e_1_3_2_1_16_1","first-page":"21969","article-title":"Attribute prototype network for zero-shot learning","volume":"33","author":"Xu Wenjia","year":"2020","unstructured":"Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele, and Zeynep Akata. 2020. Attribute prototype network for zero-shot learning. Advances in Neural Information Processing Systems 33 (2020), 21969--21980.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01030"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00080"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19931"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28581"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28317"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233042"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00724"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747440"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2024.3434520"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP63160.2024.10849917"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3430080"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611758"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3310870"},{"key":"e_1_3_2_1_30_1","first-page":"7905","article-title":"Learning Optical Flow from Continuous Spike Streams","volume":"35","author":"Zhao Rui","year":"2022","unstructured":"Rui Zhao, Ruiqin Xiong, Jing Zhao, Zhaofei Yu, Xiaopeng Fan, and Tiejun Huang. 2022. Learning Optical Flow from Continuous Spike Streams. In Advances in Neural Information Processing Systems, Vol. 35. 7905--7920.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326294"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02357"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Peng Liu and Hua Huang. 2024. Cross-modal Attention and Bidirectional LSTM for Audio-Visual Generalized Zero-shot Learning. (2024).","DOI":"10.21203\/rs.3.rs-5304592\/v1"},{"key":"e_1_3_2_1_34_1","volume-title":"International conference on machine learning. PMLR, 9226--9259","author":"Huang Yu","year":"2022","unstructured":"Yu Huang, Junyang Lin, Chang Zhou, Hongxia Yang, and Longbo Huang. 2022. Modality competition: What makes joint training of multi-modal network fail in deep learning?(provably). In International conference on machine learning. PMLR, 9226--9259."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_1_36_1","unstructured":"Sami Labbaki and Peter Minary. 2024. Orthogonal Sequential Fusion in Multimodal Learning. (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3394551"},{"key":"e_1_3_2_1_38_1","unstructured":"Yuki M. Asano Mandela Patrick Christian Rupprecht and Andrea Vedaldi. 2020. Labelling unlabelled videos from scratch with multi-modal self-supervision. In Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_39_1","volume-title":"Spikemba: Multi-modal spiking saliency mamba for temporal video grounding. arXiv preprint arXiv:2404.01174","author":"Li Wenrui","year":"2024","unstructured":"Wenrui Li, Xiaopeng Hong, Ruiqin Xiong, and Xiaopeng Fan. 2024. Spikemba: Multi-modal spiking saliency mamba for temporal video grounding. arXiv preprint arXiv:2404.01174 (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_41_1","volume-title":"Multi-scale spiking pyramid wireless communication framework for food recognition","author":"Li Wenrui","year":"2024","unstructured":"Wenrui Li, Jiahui Li, Mengyao Ma, Xiaopeng Hong, and Xiaopeng Fan. 2024. Multi-scale spiking pyramid wireless communication framework for food recognition. IEEE transactions on multimedia (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00466"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32525"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_45_1","volume-title":"Perspective transformer nets: Learning single-view 3d object reconstruction without 3d supervision. Advances in neural information processing systems 29","author":"Yan Xinchen","year":"2016","unstructured":"Xinchen Yan, Jimei Yang, Ersin Yumer, Yijie Guo, and Honglak Lee. 2016. Perspective transformer nets: Learning single-view 3d object reconstruction without 3d supervision. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"e_1_3_2_1_47_1","volume-title":"Joon Son Chung, and Andrew Zisserman","author":"Afouras Triantafyllos","year":"2020","unstructured":"Triantafyllos Afouras, Andrew Owens, Joon Son Chung, and Andrew Zisserman. 2020. Self-Supervised Learning of Audio-Visual Objects from Video. CoRR abs\/2008.04237 (2020). arXiv:2008.04237 https:\/\/arxiv.org\/abs\/2008.04237"},{"key":"e_1_3_2_1_48_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_49_1","volume-title":"Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly","author":"Xian Yongqin","year":"2018","unstructured":"Yongqin Xian, Christoph H Lampert, Bernt Schiele, and Zeynep Akata. 2018. Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. IEEE transactions on pattern analysis and machine intelligence 41, 9 (2018), 2251--2265."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129636"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"e_1_3_2_1_53_1","first-page":"1","article-title":"A dataset of 101 human action classes from videos in the wild","volume":"2","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. A dataset of 101 human action classes from videos in the wild. Center for Research in Computer Vision 2, 11 (2012), 1--7.","journal-title":"Center for Research in Computer Vision"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2165291"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_4"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:48:19Z","timestamp":1765309699000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755258"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":56,"alternative-id":["10.1145\/3746027.3755258","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755258","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}