{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T21:12:57Z","timestamp":1780434777567,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":47,"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\/3664647.3680698","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"9175-9183","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Channel-Spatial Support-Query Cross-Attention for Fine-Grained Few-Shot Image Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8125-4370","authenticated-orcid":false,"given":"Shicheng","family":"Yang","sequence":"first","affiliation":[{"name":"Lanzhou University of Technology, Lanzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8833-9401","authenticated-orcid":false,"given":"Xiaoxu","family":"Li","sequence":"additional","affiliation":[{"name":"Lanzhou University of Technology, Lanzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4081-3001","authenticated-orcid":false,"given":"Dongliang","family":"Chang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, 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, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1174-610X","authenticated-orcid":false,"given":"Jing-Hao","family":"Xue","sequence":"additional","affiliation":[{"name":"University College London, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Arman Afrasiyabi Jean-Franccois Lalonde and Christian Gagn\u00e9. 2021. Mixture-Based Feature Space Learning for Few-Shot Image Classification. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00891"},{"key":"e_1_3_2_1_2_1","volume-title":"From Instance to Metric Calibration: A Unified Framework for Open-World Few-Shot Learning","author":"An Yuexuan","year":"2023","unstructured":"Yuexuan An, Hui Xue, Xingyu Zhao, and Jing Wang. 2023. From Instance to Metric Calibration: A Unified Framework for Open-World Few-Shot Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Yu-Chiang Frank Wang, and Jia-Bin Huang","author":"Chen Wei-Yu","year":"2019","unstructured":"Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia-Bin Huang. 2019. A Closer Look at Few-shot Classification. In ICLR."},{"key":"e_1_3_2_1_4_1","volume-title":"CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification. In CVPR.","author":"Chikontwe Philip","year":"2022","unstructured":"Philip Chikontwe, Soopil Kim, and Sang Hyun Park. 2022. CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification. In CVPR."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Jun Fu Jing Liu Haijie Tian Yong Li Yongjun Bao Zhiwei Fang and Hanqing Lu. 2019. Dual Attention Network for Scene Segmentation. In CVPR.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"e_1_3_2_1_6_1","volume-title":"NIPS. Curran Associates","author":"Goyal Ankit","unstructured":"Ankit Goyal, Alexey Bochkovskiy, Jia Deng, and Vladlen Koltun. 2022. Non-deep Networks. In NIPS. Curran Associates, Inc."},{"key":"e_1_3_2_1_7_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_9_1","volume-title":"NIPS. Curran Associates","author":"Hou Ruibing","unstructured":"Ruibing Hou, Hong Chang, Bingpeng MA, Shiguang Shan, and Xilin Chen. 2019. Cross Attention Network for Few-shot Classification. In NIPS. Curran Associates, Inc."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Jie Hu Li Shen and Gang Sun. 2018. Squeeze-and-Excitation Networks. In CVPR.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Dahyun Kang Heeseung Kwon Juhong Min and Minsu Cho. 2021. Relational Embedding for Few-Shot Classification. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00870"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Jonathan Krause Michael Stark Jia Deng and Li Fei-Fei. 2013. 3D object representations for fine-grained categorization. In ICCV.","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_1_13_1","unstructured":"Kwonjoon Lee Subhransu Maji Avinash Ravichandran and Stefano Soatto. 2019. Meta-Learning With Differentiable Convex Optimization. In CVPR."},{"key":"e_1_3_2_1_14_1","unstructured":"SuBeen Lee WonJun Moon and Jae-Pil Heo. 2022. Task Discrepancy Maximization for Fine-Grained Few-Shot Classification. In CVPR."},{"key":"e_1_3_2_1_15_1","unstructured":"Wenbin Li Lei Wang Jinglin Xu Jing Huo Yang Gao and Jiebo Luo. 2019. Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning. In CVPR."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275382"},{"key":"e_1_3_2_1_17_1","volume-title":"BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification","author":"Li Xiaoxu","year":"2021","unstructured":"Xiaoxu Li, Jijie Wu, Zhuo Sun, Zhanyu Ma, Jie Cao, and Jing-Hao Xue. 2021. BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification. IEEE Transactions on Image Processing (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"Deep metric learning for few-shot image classification: A Review of recent developments. Pattern Recognition","author":"Li Xiaoxu","year":"2023","unstructured":"Xiaoxu Li, Xiaochen Yang, Zhanyu Ma, and Jing-Hao Xue. 2023. Deep metric learning for few-shot image classification: A Review of recent developments. Pattern Recognition (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"TransIFC: Invariant Cues-aware Feature Concentration Learning for Efficient Fine-grained Bird Image Classification","author":"Liu Hai","year":"2023","unstructured":"Hai Liu, Cheng Zhang, Yongjian Deng, Bochen Xie, Tingting Liu, Zhaoli Zhang, and You-Fu Li. 2023. TransIFC: Invariant Cues-aware Feature Concentration Learning for Efficient Fine-grained Bird Image Classification. IEEE Transactions on Multimedia (2023), 1--14."},{"key":"e_1_3_2_1_20_1","volume-title":"Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions. ArXiv","author":"Liu Yichao","year":"2021","unstructured":"Yichao Liu, Zongru Shao, and Nico Hoffmann. 2021. Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions. ArXiv, Vol. abs\/2112.05561 (2021)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28208"},{"key":"e_1_3_2_1_22_1","volume-title":"Fine-Grained Visual Classification of Aircraft. ArXiv","author":"Maji Subhransu","year":"2013","unstructured":"Subhransu Maji, Esa Rahtu, Juho Kannala, Matthew B. Blaschko, and Andrea Vedaldi. 2013. Fine-Grained Visual Classification of Aircraft. ArXiv, Vol. abs\/1306.5151 (2013)."},{"key":"e_1_3_2_1_23_1","volume-title":"Ajay Uppili Arasanipalai, and Qibin Hou","author":"Misra Diganta","year":"2021","unstructured":"Diganta Misra, Trikay Nalamada, Ajay Uppili Arasanipalai, and Qibin Hou. 2021. Rotate to Attend: Convolutional Triplet Attention Module. In WACV."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Maria-Elena Nilsback and Andrew Zisserman. 2008. Automated Flower Classification over a Large Number of Classes. In ICCV.","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Xuran Pan Chunjiang Ge Rui Lu Shiji Song Guanfu Chen Zeyi Huang and Gao Huang. 2022. On the Integration of Self-Attention and Convolution. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00089"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Ramprasaath R Selvaraju Michael Cogswell Abhishek Das Ramakrishna Vedantam Devi Parikh and Dhruv Batra. 2017. Grad-CAM: Visual explanations from deep networks via gradient-based localization. In ICCV.","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"e_1_3_2_1_28_1","volume-title":"Advances in Neural Information Processing Systems","author":"Snell Jake","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical Networks for Few-shot Learning. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.). Curran Associates, Inc."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00251"},{"key":"e_1_3_2_1_30_1","volume-title":"Philip HS Torr, and Timothy M Hospedales","author":"Sung Flood","year":"2018","unstructured":"Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip HS Torr, and Timothy M Hospedales. 2018. Learning to compare: Relation network for few-shot learning. In CVPR."},{"key":"e_1_3_2_1_31_1","volume-title":"Learning attention-guided pyramidal features for few-shot fine-grained recognition. Pattern Recognition","author":"Tang Hao","year":"2022","unstructured":"Hao Tang, Chengcheng Yuan, Zechao Li, and Jinhui Tang. 2022. Learning attention-guided pyramidal features for few-shot fine-grained recognition. Pattern Recognition (2022)."},{"key":"e_1_3_2_1_32_1","volume-title":"Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition. ArXiv","author":"Tong Meihan","year":"2021","unstructured":"Meihan Tong, Shuai Wang, Bin Xu, Yixin Cao, Minghui Liu, Lei Hou, and Juanzi Li. 2021. Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition. ArXiv, Vol. abs\/2106.15167 (2021)."},{"key":"e_1_3_2_1_33_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_34_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In NIPS."},{"key":"e_1_3_2_1_35_1","unstructured":"Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The Caltech-UCSD Birds-200--2011 dataset. (2011)."},{"key":"e_1_3_2_1_36_1","volume-title":"Learning Mutually Exclusive Part Representations for Fine-grained Image Classification","author":"Wang Chuanming","year":"2023","unstructured":"Chuanming Wang, Huiyuan Fu, and Huadong Ma. 2023. Learning Mutually Exclusive Part Representations for Fine-grained Image Classification. IEEE Transactions on Multimedia (2023), 1--12."},{"key":"e_1_3_2_1_37_1","volume-title":"Distract Your Attention: Multi-Head Cross Attention Network for Facial Expression Recognition. Biomimetics","author":"Wen Zhengyao","year":"2023","unstructured":"Zhengyao Wen, Wenzhong Lin, Tao Wang, and Ge Xu. 2023. Distract Your Attention: Multi-Head Cross Attention Network for Facial Expression Recognition. Biomimetics (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Davis Wertheimer Luming Tang and Bharath Hariharan. 2021. Few-Shot Classification With Feature Map Reconstruction Networks. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00792"},{"key":"e_1_3_2_1_39_1","volume-title":"CBAM: Convolutional Block Attention Module. In ECCV.","author":"Woo Sanghyun","year":"2018","unstructured":"Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In So Kweon. 2018. CBAM: Convolutional Block Attention Module. In ECCV."},{"key":"e_1_3_2_1_40_1","unstructured":"Jijie Wu Dongliang Chang Aneeshan Sain Xiaoxu Li Zhanyu Ma Jie Cao Jun Guo and Yi-Zhe Song. 2023. Bi-directional feature reconstruction network for fine-grained few-shot image classification. In AAAI."},{"key":"e_1_3_2_1_41_1","unstructured":"Jingyi Xu Hieu Le Mingzhen Huang ShahRukh Athar and Dimitris Samaras. 2021. Variational Feature Disentangling for Fine-Grained Few-Shot Classification. In ICCV."},{"key":"e_1_3_2_1_42_1","unstructured":"Shu-Lin Xu Faen Zhang Xiu-Shen Wei and Jianhua Wang. 2022. Dual attention networks for few-shot fine-grained recognition. In AAAI."},{"key":"e_1_3_2_1_43_1","volume-title":"Improved Spatial-Shift MLP Architecture for Vision. ArXiv","author":"Yu Tan","year":"2021","unstructured":"Tan Yu, Xu Li, Yunfeng Cai, Mingming Sun, and Ping Li. 2021. S(^mbox2)-MLPv2: Improved Spatial-Shift MLP Architecture for Vision. ArXiv, Vol. abs\/2108.01072 (2021)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3236636"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Bo Zhang Jiakang Yuan Baopu Li Tao Chen Jiayuan Fan and Botian Shi. 2022. Learning cross-image object semantic relation in transformer for few-shot fine-grained image classification. In ACM MM.","DOI":"10.1145\/3503161.3547961"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Chi Zhang Yujun Cai Guosheng Lin and Chunhua Shen. 2020. DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers. In CVPR.","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"e_1_3_2_1_47_1","unstructured":"Yaohui Zhu Chenlong Liu and Shuqiang Jiang. 2020. Multi-attention Meta Learning for Few-shot Fine-grained Image Recognition.. In IJCAI."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680698","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680698"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":47,"alternative-id":["10.1145\/3664647.3680698","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680698","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"}}]}}