{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T14:04:34Z","timestamp":1772719474904,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":54,"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"}],"funder":[{"name":"The Major Program of the National Natural Science Foundation of China","award":["61991411"],"award-info":[{"award-number":["61991411"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202272, 62172256, 62202278"],"award-info":[{"award-number":["62202272, 62172256, 62202278"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2019ZD06, ZR2020QF036, ZR2021ZD15"],"award-info":[{"award-number":["ZR2019ZD06, ZR2020QF036, ZR2021ZD15"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680593","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"8277-8286","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Bi-directional Task-Guided Network for Few-Shot Fine-Grained Image Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4697-5033","authenticated-orcid":false,"given":"Zhen-Xiang","family":"Ma","sequence":"first","affiliation":[{"name":"Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3481-4892","authenticated-orcid":false,"given":"Zhen-Duo","family":"Chen","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6400-6014","authenticated-orcid":false,"given":"Li-Jun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1365-4401","authenticated-orcid":false,"given":"Zi-Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9934-647X","authenticated-orcid":false,"given":"Tai","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6901-5476","authenticated-orcid":false,"given":"Xin","family":"Luo","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9972-7370","authenticated-orcid":false,"given":"Xin-Shun","family":"Xu","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder and Melanie Subbiah et al. 2020. Language Models are Few-Shot Learners. In NeurIPS. 1877--1901."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Chun-Fu (Richard) Chen Quanfu Fan and Rameswar Panda. 2021. CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification. In ICCV. 347--356.","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2910052"},{"key":"e_1_3_2_1_4_1","volume-title":"Lanqing Guo, and Bihan Wen.","author":"Cheng Hao","year":"2023","unstructured":"Hao Cheng, Siyuan Yang, Joey Tianyi Zhou, Lanqing Guo, and Bihan Wen. 2023. Frequency Guidance Matters in Few-Shot Learning. In ICCV. 11814--11824."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3143692"},{"key":"e_1_3_2_1_6_1","unstructured":"Carl Doersch Ankush Gupta and Andrew Zisserman. 2020. CrossTransformers: spatially-aware few-shot transfer. In NeurIPS. 21981--21993."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Chuanqi Dong Wenbin Li Jing Huo Zheng Gu and Yang Gao. 2020. Learning Task-aware Local Representations for Few-shot Learning. In IJCAI. 716--722.","DOI":"10.24963\/ijcai.2020\/100"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Lintao Dong Wei Zhai and Zheng-Jun Zha. 2023. Exploring Tuning Characteristics of Ventral Stream's Neurons for Few-Shot Image Classification. In AAAI. 534--542.","DOI":"10.1609\/aaai.v37i1.25128"},{"key":"e_1_3_2_1_9_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Fei Du Peng Yang Qi Jia Fengtao Nan Xiaoting Chen and Yun Yang. 2023. Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions. In CVPR. 15814--15823.","DOI":"10.1109\/CVPR52729.2023.01518"},{"key":"e_1_3_2_1_11_1","volume-title":"Jiyang Xie, Zhanyu Ma, Yi-Zhe Song, and Jun Guo.","author":"Du Ruoyi","year":"2020","unstructured":"Ruoyi Du, Dongliang Chang, Ayan Kumar Bhunia, Jiyang Xie, Zhanyu Ma, Yi-Zhe Song, and Jun Guo. 2020. Fine-Grained Visual Classification via Progressive Multi-granularity Training of Jigsaw Patches. In ECCV. 153--168."},{"key":"e_1_3_2_1_12_1","unstructured":"Chelsea Finn Pieter Abbeel and Sergey Levine. 2017. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. In ICML. 1126--1135."},{"key":"e_1_3_2_1_13_1","volume-title":"Girshick","author":"Hariharan Bharath","year":"2017","unstructured":"Bharath Hariharan and Ross B. Girshick. 2017. Low-Shot Visual Recognition by Shrinking and Hallucinating Features. In ICCV. 3037--3046."},{"key":"e_1_3_2_1_14_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_15_1","volume-title":"Yang Song, Yin Cui, Chen Sun, Alexander Shepard, Hartwig Adam, Pietro Perona, and Serge J. Belongie.","author":"Horn Grant Van","year":"2018","unstructured":"Grant Van Horn, Oisin Mac Aodha, Yang Song, Yin Cui, Chen Sun, Alexander Shepard, Hartwig Adam, Pietro Perona, and Serge J. Belongie. 2018. The INaturalist Species Classification and Detection Dataset. In CVPR. 8769--8778."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3065693"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001510"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Menglin Jia Luming Tang Bor-Chun Chen Claire Cardie Serge J. Belongie Bharath Hariharan and Ser-Nam Lim. 2022. Visual Prompt Tuning. In ECCV. 709--727.","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_19_1","volume-title":"Novel Dataset for Fine-Grained Image Categorization. In CVPR Workshop. 806--813","author":"Khosla Aditya","year":"2011","unstructured":"Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao, and Li Fei-Fei. 2011. Novel Dataset for Fine-Grained Image Categorization. In CVPR Workshop. 806--813."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Jinxiang Lai Siqian Yang Junhong Zhou Wenlong Wu Xiaochen Chen Jun Liu Bin-Bin Gao and Chengjie Wang. 2023. Clustered-patch Element Connection for Few-shot Learning. In IJCAI. 991--998.","DOI":"10.24963\/ijcai.2023\/110"},{"key":"e_1_3_2_1_22_1","unstructured":"Kwonjoon Lee Subhransu Maji Avinash Ravichandran and Stefano Soatto. 2019. Meta-Learning With Differentiable Convex Optimization. In CVPR. 10657--10665."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Su Been Lee WonJun Moon and Jae-Pil Heo. 2022. Task Discrepancy Maximization for Fine-grained Few-Shot Classification. In CVPR. 5321--5330.","DOI":"10.1109\/CVPR52688.2022.00526"},{"key":"e_1_3_2_1_24_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. 7260--7268."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275382"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3043128"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Bin Liu Yue Cao Yutong Lin Qi Li Zheng Zhang Mingsheng Long and Han Hu. 2020. Negative Margin Matters: Understanding Margin in Few-Shot Classification. In ECCV. 438--455.","DOI":"10.1007\/978-3-030-58548-8_26"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Yang Liu Weifeng Zhang Chao Xiang Tu Zheng Deng Cai and Xiaofei He. 2022. Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification. In CVPR. 14391--14400.","DOI":"10.1109\/CVPR52688.2022.01401"},{"key":"e_1_3_2_1_29_1","unstructured":"Tsendsuren Munkhdalai Xingdi Yuan Soroush Mehri and Adam Trischler. 2018. Rapid Adaptation with Conditionally Shifted Neurons. In ICML. 3661--3670."},{"key":"e_1_3_2_1_30_1","unstructured":"Andrei A. Rusu Dushyant Rao Jakub Sygnowski Oriol Vinyals Razvan Pascanu Simon Osindero and Raia Hadsell. 2019. Meta-Learning with Latent Embedding Optimization. In ICLR."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Zhiqiang Shen Zechun Liu Jie Qin Marios Savvides and Kwang-Ting Cheng. 2021. Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning. In AAAI. 9594--9602.","DOI":"10.1609\/aaai.v35i11.17155"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Christian Simon Piotr Koniusz Richard Nock and Mehrtash Harandi. 2020. Adaptive Subspaces for Few-Shot Learning. In CVPR. 4135--4144.","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"e_1_3_2_1_33_1","volume-title":"Zemel","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard S. Zemel. 2017. Prototypical Networks for Few-shot Learning. In NeurIPS. 4077--4087."},{"key":"e_1_3_2_1_34_1","volume-title":"Hospedales","author":"Sung Flood","year":"2018","unstructured":"Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H. S. Torr, and Timothy M. Hospedales. 2018. Learning to Compare: Relation Network for Few-Shot Learning. In CVPR. 1199--1208."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Hao Tang Zechao Li Zhimao Peng and Jinhui Tang. 2020. BlockMix: Meta Regularization and Self-Calibrated Inference for Metric-Based Meta-Learning. In ACM MM. 610--618.","DOI":"10.1145\/3394171.3413884"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108792"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Luming Tang Davis Wertheimer and Bharath Hariharan. 2020. Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition. In CVPR. 14340--14349.","DOI":"10.1109\/CVPR42600.2020.01436"},{"key":"e_1_3_2_1_38_1","unstructured":"Oriol Vinyals Charles Blundell Tim Lillicrap Koray Kavukcuoglu and Daan Wierstra. 2016. Matching Networks for One Shot Learning. In NeurIPS. 3630--3638."},{"key":"e_1_3_2_1_39_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_40_1","doi-asserted-by":"crossref","unstructured":"Chuanming Wang Huiyuan Fu and Huadong Ma. 2022. PaCL: Part-level Contrastive Learning for Fine-grained Few-shot Image Classification. In ACM MM. 6416--6424.","DOI":"10.1145\/3503161.3547997"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2924811"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Davis Wertheimer and Bharath Hariharan. 2019. Few-Shot Learning With Localization in Realistic Settings. In CVPR. 6558--6567.","DOI":"10.1109\/CVPR.2019.00672"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Davis Wertheimer Luming Tang and Bharath Hariharan. 2021. Few-Shot Classification With Feature Map Reconstruction Networks. In CVPR. 8012--8021.","DOI":"10.1109\/CVPR46437.2021.00792"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","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. 2821--2829.","DOI":"10.1609\/aaai.v37i3.25383"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Yike Wu Bo Zhang Gang Yu Weixi Zhang Bin Wang Tao Chen and Jiayuan Fan. 2021. Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification. In ACM MM. 107--115.","DOI":"10.1145\/3474085.3475532"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Shulin Xu Faen Zhang Xiushen Wei and Jianhua Wang. 2022. Dual Attention Networks for Few-Shot Fine-Grained Recognition. In AAAI. 2911--2919.","DOI":"10.1609\/aaai.v36i3.20196"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3061147"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Han-Jia Ye Hexiang Hu De-Chuan Zhan and Fei Sha. 2020. Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions. In CVPR. 8805--8814.","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3236636"},{"key":"e_1_3_2_1_50_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. 2135--2144.","DOI":"10.1145\/3503161.3547961"},{"key":"e_1_3_2_1_51_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. 12200--12210.","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"e_1_3_2_1_52_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Jingkang Yang, Chen Change Loy, and Ziwei Liu. 2022. Conditional Prompt Learning for Vision-Language Models. In CVPR. 16795--16804."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Yaohui Zhu Chenlong Liu and Shuqiang Jiang. 2020. Multi-attention Meta Learning for Few-shot Fine-grained Image Recognition. In IJCAI. 1090--1096.","DOI":"10.24963\/ijcai.2020\/152"}],"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\/3664647.3680593","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680593"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":54,"alternative-id":["10.1145\/3664647.3680593","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680593","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"}}]}}