{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T15:33:28Z","timestamp":1779291208797,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC","award":["62071127,U1909207"],"award-info":[{"award-number":["62071127,U1909207"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475532","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T06:35:51Z","timestamp":1634538951000},"page":"107-115","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification"],"prefix":"10.1145","author":[{"given":"Yike","family":"Wu","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayuan","family":"Fan","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01450"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.128"},{"key":"e_1_3_2_1_3_1","volume-title":"Learning to Compare Relation: Semantic Alignment for Few-Shot Learning. arXiv preprint arXiv:2003.00210","author":"Cao Congqi","year":"2020","unstructured":"Congqi Cao and Yanning Zhang . 2020. Learning to Compare Relation: Semantic Alignment for Few-Shot Learning. arXiv preprint arXiv:2003.00210 ( 2020 ). Congqi Cao and Yanning Zhang. 2020. Learning to Compare Relation: Semantic Alignment for Few-Shot Learning. arXiv preprint arXiv:2003.00210 (2020)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.47"},{"key":"e_1_3_2_1_5_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. arXiv preprint arXiv:1904.04232 (2019). Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia- Bin Huang. 2019. A closer look at few-shot classification. arXiv preprint arXiv:1904.04232 (2019)."},{"key":"e_1_3_2_1_6_1","volume-title":"A new meta-baseline for few-shot learning. arXiv preprint arXiv:2003.04390","author":"Chen Yinbo","year":"2020","unstructured":"Yinbo Chen , Xiaolong Wang , Zhuang Liu , Huijuan Xu , and Trevor Darrell . 2020. A new meta-baseline for few-shot learning. arXiv preprint arXiv:2003.04390 ( 2020 ). Yinbo Chen, Xiaolong Wang, Zhuang Liu, Huijuan Xu, and Trevor Darrell. 2020. A new meta-baseline for few-shot learning. arXiv preprint arXiv:2003.04390 (2020)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.325"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/100"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_45"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305498"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"e_1_3_2_1_14_1","volume-title":"Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043","author":"Garcia Victor","year":"2017","unstructured":"Victor Garcia and Joan Bruna . 2017. Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043 ( 2017 ). Victor Garcia and Joan Bruna. 2017. Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043 (2017)."},{"key":"e_1_3_2_1_15_1","unstructured":"Fusheng Hao Fengxiang He Jun Cheng Lei Wang Jianzhong Cao and Dacheng Tao. 2019. Collect and select: Semantic alignment metric learning for few-shot learning. In ICCV. 8460--8469.  Fusheng Hao Fengxiang He Jun Cheng Lei Wang Jianzhong Cao and Dacheng Tao. 2019. Collect and select: Semantic alignment metric learning for few-shot learning. In ICCV. 8460--8469."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001510"},{"key":"e_1_3_2_1_17_1","volume-title":"Acmm: Aligned cross-modal memory for few-shot image and sentence matching. In ICCV. 5774--5783.","author":"Huang Yan","year":"2019","unstructured":"Yan Huang and Liang Wang . 2019 . Acmm: Aligned cross-modal memory for few-shot image and sentence matching. In ICCV. 5774--5783. Yan Huang and Liang Wang. 2019. Acmm: Aligned cross-modal memory for few-shot image and sentence matching. In ICCV. 5774--5783."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969465"},{"key":"e_1_3_2_1_19_1","volume-title":"Proc. CVPR Workshop on Fine-Grained Visual Categorization (FGVC)","volume":"2","author":"Khosla Aditya","year":"2011","unstructured":"Aditya Khosla , Nityananda Jayadevaprakash , Bangpeng Yao , and Fei-Fei Li . 2011 . Novel dataset for fine-grained image categorization: Stanford dogs . In Proc. CVPR Workshop on Fine-Grained Visual Categorization (FGVC) , Vol. 2 . Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao, and Fei-Fei Li. 2011. Novel dataset for fine-grained image categorization: Stanford dogs. In Proc. CVPR Workshop on Fine-Grained Visual Categorization (FGVC), Vol. 2."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.743"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_24_1","volume-title":"SFNet: Learning Object-Aware Semantic Correspondence. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Lee Junghyup","year":"2019","unstructured":"Junghyup Lee , Dohyung Kim , Jean Ponce , and Bumsub Ham . 2019 . SFNet: Learning Object-Aware Semantic Correspondence. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019 , Long Beach, CA, USA , June 16-20, 2019. Computer Vision Foundation \/ IEEE, 2278--2287. https:\/\/doi.org\/10.1109\/CVPR. 2019.00238 10.1109\/CVPR Junghyup Lee, Dohyung Kim, Jean Ponce, and Bumsub Ham. 2019. SFNet: Learning Object-Aware Semantic Correspondence. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019. Computer Vision Foundation \/ IEEE, 2278--2287. https:\/\/doi.org\/10.1109\/CVPR. 2019.00238"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00743"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018642"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073683"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_31"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298775"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_26"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3327010"},{"key":"e_1_3_2_1_34_1","unstructured":"Andrei A Rusu Dushyant Rao Jakub Sygnowski Oriol Vinyals Razvan Pascanu Simon Osindero and Raia Hadsell. 2018. Meta-learning with latent embedding optimization. ICLR.  Andrei A Rusu Dushyant Rao Jakub Sygnowski Oriol Vinyals Razvan Pascanu Simon Osindero and Raia Hadsell. 2018. Meta-learning with latent embedding optimization. ICLR."},{"key":"e_1_3_2_1_35_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and AndrewZisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and AndrewZisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). 805--821","author":"Sun Ming","year":"2018","unstructured":"Ming Sun , Yuchen Yuan , Feng Zhou , and Errui Ding . 2018 . Multi-attention multiclass constraint for fine-grained image recognition . In Proceedings of the European Conference on Computer Vision (ECCV). 805--821 . Ming Sun, Yuchen Yuan, Feng Zhou, and Errui Ding. 2018. Multi-attention multiclass constraint for fine-grained image recognition. In Proceedings of the European Conference on Computer Vision (ECCV). 805--821."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01436"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454562"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157504"},{"key":"e_1_3_2_1_43_1","unstructured":"Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200--2011 dataset. (2011).  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_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01285"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Zhuhui Wang Shijie Wang Haojie Li Zhi Dou and Jianjun Li. 2020. Graph- Propagation Based Correlation Learning for Weakly Supervised Fine-Grained Image Classification.. In AAAI. 12289--12296.  Zhuhui Wang Shijie Wang Haojie Li Zhi Dou and Jianjun Li. 2020. Graph- Propagation Based Correlation Learning for Weakly Supervised Fine-Grained Image Classification.. In AAAI. 12289--12296.","DOI":"10.1609\/aaai.v34i07.6912"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2924811"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/2586117.2587186"},{"key":"e_1_3_2_1_48_1","volume-title":"Learning embedding adaptation for few-shot learning. arXiv preprint arXiv:1812.03664 7","author":"Ye Han-Jia","year":"2018","unstructured":"Han-Jia Ye , Hexiang Hu , De-Chuan Zhan , and Fei Sha . 2018. Learning embedding adaptation for few-shot learning. arXiv preprint arXiv:1812.03664 7 ( 2018 ). Han-Jia Ye, Hexiang Hu, De-Chuan Zhan, and Fei Sha. 2018. Learning embedding adaptation for few-shot learning. arXiv preprint arXiv:1812.03664 7 (2018)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/152"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475532","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:10Z","timestamp":1750193350000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":53,"alternative-id":["10.1145\/3474085.3475532","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475532","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}