{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T21:54:48Z","timestamp":1769378088390,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":["62276120"],"award-info":[{"award-number":["62276120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Yunnan Fundamental Research Projects","award":["202301AV070004"],"award-info":[{"award-number":["202301AV070004"]}]},{"name":"Yunnan Fundamental Research Projects","award":["202401AS070106"],"award-info":[{"award-number":["202401AS070106"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3696409.3700200","type":"proceedings-article","created":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T09:55:23Z","timestamp":1735379723000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Robust discriminative and modal-consistent feature learning for fine-grained sketch-based image retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8739-2486","authenticated-orcid":false,"given":"Junchao","family":"Ge","sequence":"first","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2462-6174","authenticated-orcid":false,"given":"Huafeng","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2347-5642","authenticated-orcid":false,"given":"Yafei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Ayan\u00a0Kumar Bhunia. 2022. Towards practicality of sketch-based visual understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.15146 (2022)."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00423"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00980"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547993"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Yangdong Chen Zhaolong Zhang Yanfei Wang Yuejie Zhang Rui Feng Tao Zhang and Weiguo Fan. 2022. AE-Net: Fine-grained sketch-based image retrieval via attention-enhanced network. Pattern Recognition 122 (2022) 108291.","DOI":"10.1016\/j.patcog.2021.108291"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.290"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Dawei Dai Yingge Liu Yutang Li Shiyu Fu Shuyin Xia and Guoyin Wang. 2024. LGRL: Local-Global Representation Learning for On-the-Fly FG-SBIR. IEEE Transactions on Big Data 10 4 (2024) 543\u2013555.","DOI":"10.1109\/TBDATA.2024.3356393"},{"key":"e_1_3_3_1_9_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et\u00a0al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020)."},{"key":"e_1_3_3_1_10_2","unstructured":"Yunpeng Gong Liqing Huang and Lifei Chen. 2021. Eliminate deviation with deviation for data augmentation and a general multi-modal data learning method. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2101.08533 (2021)."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Shaojun Gui Yu Zhu Xiangxiang Qin and Xiaofeng Ling. 2020. Learning multi-level domain invariant features for sketch re-identification. Neurocomputing 403 (2020) 294\u2013303.","DOI":"10.1016\/j.neucom.2020.04.060"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"e_1_3_3_1_13_2","unstructured":"Jianan Jiang Di Wu Zhilin Jiang and Weiren Yu. 2024. Simple Yet Efficient: Towards Self-Supervised FG-SBIR with Unified Sample Feature Alignment. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.11551 (2024)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Huafeng Li Yiwen Chen Dapeng Tao Zhengtao Yu and Guanqiu Qi. 2021. Attribute-Aligned Domain-Invariant Feature Learning for Unsupervised Domain Adaptation Person Re-Identification. IEEE Transactions on Information Forensics and Security 16 (2021) 1480\u20131494.","DOI":"10.1109\/TIFS.2020.3036800"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Huafeng Li Neng Dong Zhengtao Yu Dapeng Tao and Guanqiu Qi. 2022. Triple Adversarial Learning and Multi-view Imaginative Reasoning for Unsupervised Domain Adaptation Person Re-identification. IEEE Transactions on Circuits and Systems for Video Technology 32 5 (2022) 2814\u20132830.","DOI":"10.1109\/TCSVT.2021.3099943"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Huafeng Li Minghui Liu Zhanxuan Hu Feiping Nie and Zhengtao Yu. 2023. Intermediary-guided bidirectional spatial-temporal aggregation network for video-based visible-infrared person reidenti fication. IEEE Transactions on Circuits and Systems for Video Technology 33 9 (2023) 4962\u20134972.","DOI":"10.1109\/TCSVT.2023.3246091"},{"key":"e_1_3_3_1_17_2","unstructured":"Huafeng Li Yanmei Mao Yafei Zhang Guanqiu Qi and Zhengtao Yu. 2023. Domain-adaptive Person Re-identification without Cross-camera Paired Samples. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.06533 (2023)."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Huafeng Li Chen Zhang Zhanxuan Hu Yafei Zhang and Zhengtao Yu. 2024. Interactive attack-defense for generalized person re-identification. Neural Networks 176 (2024) 106349.","DOI":"10.1016\/j.neunet.2024.106349"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02236"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611732"},{"key":"e_1_3_3_1_21_2","unstructured":"Min Lin Qiang Chen and Shuicheng Yan. 2013. Network in network. arXiv preprint arXiv::1312.4400 (2013)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_42"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548147"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.247"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Qing Luo Xiang Gao Bo Jiang Xueting Yan Wanyuan Liu and Junchao Ge. 2023. A review of fine-grained sketch image retrieval based on deep learning. Mathematical Biosciences and Engineering 20 12 (2023) 21186\u201321210.","DOI":"10.3934\/mbe.2023937"},{"key":"e_1_3_3_1_26_2","unstructured":"Wenjie Luo Yujia Li Raquel Urtasun and Richard Zemel. 2016. Understanding the effective receptive field in deep convolutional neural networks. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00836"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00077"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240606"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_46"},{"key":"e_1_3_3_1_32_2","first-page":"1","volume-title":"Proceedings of the 31th British Machine Vision Conference","author":"Sain Aneeshan","year":"2020","unstructured":"Aneeshan Sain, Ayan\u00a0Kumar Bhunia, Yongxin Yang, Tao Xiang, and Yi-Zhe Song. 2020. Cross-modal hierarchical modelling for fine-grained sketch based image retrieval. In Proceedings of the 31th British Machine Vision Conference. 1\u201312."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00840"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Patsorn Sangkloy Nathan Burnell Cusuh Ham and James Hays. 2016. The sketchy database: learning to retrieve badly drawn bunnies. ACM Transactions on Graphics 35 4 (2016) 1\u201312.","DOI":"10.1145\/2897824.2925954"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.45"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.592"},{"key":"e_1_3_3_1_38_2","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9 11 (2008)."},{"key":"e_1_3_3_1_39_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_40_2","unstructured":"Tete Xiao Mannat Singh Eric Mintun Trevor Darrell Piotr Doll\u00e1r and Ross Girshick. 2021. Early convolutions help transformers see better. Advances in neural information processing systems 34 (2021) 30392\u201330400."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Shuanglin Yan Yafei Zhang Minghong Xie Dacheng Zhang and ZhengtaoYu. 2022. Cross-domain person re-identification with pose-invariant feature decomposition and hypergraph structure alignment. Neurocomputing 467 (2022) 229\u2013241.","DOI":"10.1016\/j.neucom.2021.09.054"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_14"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.93"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"crossref","unstructured":"Qian Yu Jifei Song Yi-Zhe Song Tao Xiang and Timothy\u00a0M Hospedales. 2021. Fine-grained instance-level sketch-based image retrieval. International Journal of Computer Vision 129 2 (2021) 484\u2013500.","DOI":"10.1007\/s11263-020-01382-3"},{"key":"e_1_3_3_1_45_2","unstructured":"Qian Yu Yongxin Yang Yi-Zhe Song Tao Xiang and Timothy Hospedales. 2015. Sketch-a-net that beats humans. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1501.07873 (2015)."},{"key":"e_1_3_3_1_46_2","unstructured":"Bowen Yuan Bairu Chen Zhiyi Tan Xi Shao and Bing-Kun Bao. 2022. Unbiased feature enhancement framework for cross-modality person re-identification. Multimedia Systems (2022) 1\u201311."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_19"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548224"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"crossref","unstructured":"Fengyao Zhu Yu Zhu Xiaoben Jiang and Jiongyao Ye. 2022. Cross-domain attention and center loss for sketch re-identification. IEEE Transactions on Information Forensics and Security 17 (2022) 3421\u20133432.","DOI":"10.1109\/TIFS.2022.3208811"}],"event":{"name":"MMAsia '24: ACM Multimedia Asia","location":"Auckland New Zealand","acronym":"MMAsia '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 6th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700200","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696409.3700200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:15Z","timestamp":1750295415000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700200"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":50,"alternative-id":["10.1145\/3696409.3700200","10.1145\/3696409"],"URL":"https:\/\/doi.org\/10.1145\/3696409.3700200","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}