{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T05:59:56Z","timestamp":1775887196105,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Innovation and Technology Commission of the Hong Kong Special Administrative Region, China","award":["B\/E030\/18"],"award-info":[{"award-number":["B\/E030\/18"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413952","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:26:18Z","timestamp":1602505578000},"page":"83-91","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph"],"prefix":"10.1145","author":[{"given":"Jingkang","family":"Yang","sequence":"first","affiliation":[{"name":"Sensetime Research & Rice University, Shenzhen, China"}]},{"given":"Weirong","family":"Chen","sequence":"additional","affiliation":[{"name":"SenseTime Research & The Chinese University of Hong Kong, Hong Kong, China"}]},{"given":"Litong","family":"Feng","sequence":"additional","affiliation":[{"name":"Sensetime Research, Hong Kong, China"}]},{"given":"Xiaopeng","family":"Yan","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shenzhen, China"}]},{"given":"Huabin","family":"Zheng","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shenzhen, China"}]},{"given":"Wayne","family":"Zhang","sequence":"additional","affiliation":[{"name":"SenseTime Research & Shanghai Jiao Tong University, Hong Kong, China"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"G\u00f6rkem Algan and Ilkay Ulusoy. 2019. Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey. arXiv preprint arXiv:1912.05170 (2019).  G\u00f6rkem Algan and Ilkay Ulusoy. 2019. Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey. arXiv preprint arXiv:1912.05170 (2019)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.57"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(87)90114-1"},{"key":"e_1_3_2_2_4_1","volume-title":"Neil: Extracting visual knowledge from web data. In ICCV. 1409--1416.","author":"Chen Xinlei","year":"2013"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Zhao-Min Chen Xiu-Shen Wei Peng Wang and Yanwen Guo. 2019. Multi-label image recognition with graph convolutional networks. In CVPR. 5177--5186.  Zhao-Min Chen Xiu-Shen Wei Peng Wang and Yanwen Guo. 2019. Multi-label image recognition with graph convolutional networks. In CVPR. 5177--5186.","DOI":"10.1109\/CVPR.2019.00532"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Tat-Seng Chua Jinhui Tang Richang Hong Haojie Li Zhiping Luo and Yantao Zheng. 2009. NUS-WIDE: a real-world web image database from National University of Singapore. In ACM CIVR. 1--9.  Tat-Seng Chua Jinhui Tang Richang Hong Haojie Li Zhiping Luo and Yantao Zheng. 2009. NUS-WIDE: a real-world web image database from National University of Singapore. In ACM CIVR. 1--9.","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_2_7_1","unstructured":"Micha\u00ebl Defferrard Xavier Bresson and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In NIPS. 3844--3852.  Micha\u00ebl Defferrard Xavier Bresson and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In NIPS. 3844--3852."},{"key":"e_1_3_2_2_8_1","volume-title":"Imagenet: A large-scale hierarchical image database","author":"Deng Jia","year":"2009"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1976.5408784"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2013.2262232"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Aritra Ghosh Himanshu Kumar and PS Sastry. 2017. Robust loss functions under label noise for deep neural networks. In AAAI.  Aritra Ghosh Himanshu Kumar and PS Sastry. 2017. Robust loss functions under label noise for deep neural networks. In AAAI.","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"e_1_3_2_2_12_1","volume-title":"Curriculumnet: Weakly supervised learning from large-scale web images. In ECCV. 135--150.","author":"Guo Sheng","year":"2018"},{"key":"e_1_3_2_2_13_1","volume-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels. In NIPS. 8527--8537.","author":"Han Bo","year":"2018"},{"key":"e_1_3_2_2_14_1","unstructured":"Jiangfan Han Ping Luo and Xiaogang Wang. 2019. Deep self-learning from noisy labels. In ICCV. 5138--5147.  Jiangfan Han Ping Luo and Xiaogang Wang. 2019. Deep self-learning from noisy labels. In ICCV. 5138--5147."},{"key":"e_1_3_2_2_15_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.  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_2_16_1","doi-asserted-by":"crossref","unstructured":"Ahmet Iscen Giorgos Tolias Yannis Avrithis and Ondrej Chum. 2019. Label propagation for deep semi-supervised learning. In CVPR. 5070--5079.  Ahmet Iscen Giorgos Tolias Yannis Avrithis and Ondrej Chum. 2019. Label propagation for deep semi-supervised learning. In CVPR. 5070--5079.","DOI":"10.1109\/CVPR.2019.00521"},{"key":"e_1_3_2_2_17_1","volume-title":"Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In ICML. 2304--2313.","author":"Jiang Lu","year":"2018"},{"key":"e_1_3_2_2_18_1","unstructured":"Thomas N Kipf and Max Welling. 2017a. Semi-supervised classification with graph convolutional networks. In ICLR.  Thomas N Kipf and Max Welling. 2017a. Semi-supervised classification with graph convolutional networks. In ICLR."},{"key":"e_1_3_2_2_19_1","unstructured":"Thomas N. Kipf and Max Welling. 2017b. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR.  Thomas N. Kipf and Max Welling. 2017b. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR."},{"key":"e_1_3_2_2_20_1","volume-title":"Openimages: A public dataset for large-scale multi-label and multi-class image classification. Dataset available from https:\/\/github. com\/openimages","author":"Krasin Ivan","year":"2017"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_22_1","unstructured":"Alina Kuznetsova Hassan Rom Neil Alldrin Jasper Uijlings Ivan Krasin Jordi Pont-Tuset Shahab Kamali Stefan Popov Matteo Malloci Tom Duerig etal 2018. The open images dataset v4: Unified image classification object detection and visual relationship detection at scale. arXiv preprint arXiv:1811.00982 (2018).  Alina Kuznetsova Hassan Rom Neil Alldrin Jasper Uijlings Ivan Krasin Jordi Pont-Tuset Shahab Kamali Stefan Popov Matteo Malloci Tom Duerig et al. 2018. The open images dataset v4: Unified image classification object detection and visual relationship detection at scale. arXiv preprint arXiv:1811.00982 (2018)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Yann LeCun Yoshua Bengio and Geoffrey Hinton. 2015. Deep learning. nature Vol. 521 7553 (2015) 436--444.  Yann LeCun Yoshua Bengio and Geoffrey Hinton. 2015. Deep learning. nature Vol. 521 7553 (2015) 436--444.","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_2_24_1","volume-title":"Cleannet: Transfer learning for scalable image classifier training with label noise. In CVPR. 5447--5456.","author":"Lee Kuang-Huei","year":"2018"},{"key":"e_1_3_2_2_25_1","unstructured":"Wen Li Limin Wang Wei Li Eirikur Agustsson and Luc Van Gool. 2017. Webvision database: Visual learning and understanding from web data. arXiv preprint arXiv:1708.02862 (2017).  Wen Li Limin Wang Wei Li Eirikur Agustsson and Luc Van Gool. 2017. Webvision database: Visual learning and understanding from web data. arXiv preprint arXiv:1708.02862 (2017)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477035"},{"key":"e_1_3_2_2_27_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019"},{"key":"e_1_3_2_2_28_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In NeurIPS. 13--23.","author":"Lu Jiasen","year":"2019"},{"key":"e_1_3_2_2_29_1","volume-title":"JMLR","volume":"9","author":"van der Maaten Laurens","year":"2008"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Dhruv Mahajan Ross Girshick Vignesh Ramanathan Kaiming He Manohar Paluri Yixuan Li Ashwin Bharambe and Laurens van der Maaten. 2018. Exploring the limits of weakly supervised pretraining. In ECCV. 181--196.  Dhruv Mahajan Ross Girshick Vignesh Ramanathan Kaiming He Manohar Paluri Yixuan Li Ashwin Bharambe and Laurens van der Maaten. 2018. Exploring the limits of weakly supervised pretraining. In ECCV. 181--196.","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2223460"},{"key":"e_1_3_2_2_32_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In NIPS. 3111--3119.  Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In NIPS. 3111--3119."},{"key":"e_1_3_2_2_33_1","unstructured":"George A Miller. 1998. WordNet: An electronic lexical database .MIT press.  George A Miller. 1998. WordNet: An electronic lexical database .MIT press."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"e_1_3_2_2_35_1","volume-title":"Ocgan: One-class novelty detection using gans with constrained latent representations. In CVPR. 2898--2906.","author":"Perera Pramuditha","year":"2019"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Manan Shah Krishnamurthy Viswanathan Chun-Ta Lu Ariel Fuxman Zhen Li Aleksei Timofeev Chao Jia and Chen Sun. 2019. Inferring Context from Pixels for Multimodal Image Classification. In ACM CIKM. ACM 189--198.  Manan Shah Krishnamurthy Viswanathan Chun-Ta Lu Ariel Fuxman Zhen Li Aleksei Timofeev Chao Jia and Chen Sun. 2019. Inferring Context from Pixels for Multimodal Image Classification. In ACM CIKM. ACM 189--198.","DOI":"10.1145\/3357384.3357987"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Piyush Sharma Nan Ding Sebastian Goodman and Radu Soricut. 2018. Conceptual captions: A cleaned hypernymed image alt-text dataset for automatic image captioning. In ACL. 2556--2565.  Piyush Sharma Nan Ding Sebastian Goodman and Radu Soricut. 2018. Conceptual captions: A cleaned hypernymed image alt-text dataset for automatic image captioning. In ACL. 2556--2565.","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_2_38_1","unstructured":"Weijie Su Xizhou Zhu Yue Cao Bin Li Lewei Lu Furu Wei and Jifeng Dai. 2020. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. In ICLR.  Weijie Su Xizhou Zhu Yue Cao Bin Li Lewei Lu Furu Wei and Jifeng Dai. 2020. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. In ICLR."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Chen Sun Chuang Gan and Ram Nevatia. 2015. Automatic concept discovery from parallel text and visual corpora. In ICCV. 2596--2604.  Chen Sun Chuang Gan and Ram Nevatia. 2015. Automatic concept discovery from parallel text and visual corpora. In ICCV. 2596--2604.","DOI":"10.1109\/ICCV.2015.298"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Daiki Tanaka Daiki Ikami Toshihiko Yamasaki and Kiyoharu Aizawa. 2018. Joint optimization framework for learning with noisy labels. In CVPR. 5552--5560.  Daiki Tanaka Daiki Ikami Toshihiko Yamasaki and Kiyoharu Aizawa. 2018. Joint optimization framework for learning with noisy labels. In CVPR. 5552--5560.","DOI":"10.1109\/CVPR.2018.00582"},{"key":"e_1_3_2_2_41_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NIPS. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NIPS. 5998--6008."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1821594116"},{"key":"e_1_3_2_2_43_1","volume-title":"Cnn-rnn: A unified framework for multi-label image classification. In CVPR. 2285--2294.","author":"Wang Jiang","year":"2016"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.10.023"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2956775"},{"key":"e_1_3_2_2_46_1","unstructured":"Felix Wu Amauri Souza Tianyi Zhang Christopher Fifty Tao Yu and Kilian Weinberger. 2019 b. Simplifying Graph Convolutional Networks. In ICML. PMLR 6861--6871.  Felix Wu Amauri Souza Tianyi Zhang Christopher Fifty Tao Yu and Kilian Weinberger. 2019 b. Simplifying Graph Convolutional Networks. In ICML. PMLR 6861--6871."},{"key":"e_1_3_2_2_47_1","unstructured":"Zonghan Wu Shirui Pan Fengwen Chen Guodong Long Chengqi Zhang and S Yu Philip. 2020. A comprehensive survey on graph neural networks. TNNLS (2020).  Zonghan Wu Shirui Pan Fengwen Chen Guodong Long Chengqi Zhang and S Yu Philip. 2020. A comprehensive survey on graph neural networks. TNNLS (2020)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","unstructured":"Tong Xiao Tian Xia Yi Yang Chang Huang and Xiaogang Wang. 2015. Learning from massive noisy labeled data for image classification. In CVPR. 2691--2699.  Tong Xiao Tian Xia Yi Yang Chang Huang and Xiaogang Wang. 2015. Learning from massive noisy labeled data for image classification. In CVPR. 2691--2699.","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"e_1_3_2_2_49_1","unstructured":"I Zeki Yalniz Herv\u00e9 J\u00e9gou Kan Chen Manohar Paluri and Dhruv Mahajan. 2019. Billion-scale semi-supervised learning for image classification. arXiv preprint arXiv:1905.00546 (2019).  I Zeki Yalniz Herv\u00e9 J\u00e9gou Kan Chen Manohar Paluri and Dhruv Mahajan. 2019. Billion-scale semi-supervised learning for image classification. arXiv preprint arXiv:1905.00546 (2019)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"crossref","unstructured":"J. Yang L. Feng W. Chen X. Yan H. Zheng P. Luo and W. Zhang. 2020. Webly Supervised Image Classification with Self-Contained Confidence. In ECCV.  J. Yang L. Feng W. Chen X. Yan H. Zheng P. Luo and W. Zhang. 2020. Webly Supervised Image Classification with Self-Contained Confidence. In ECCV.","DOI":"10.1007\/978-3-030-58598-3_46"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Lei Yang Xiaohang Zhan Dapeng Chen Junjie Yan Chen Change Loy and Dahua Lin. 2019 b. Learning to cluster faces on an affinity graph. In CVPR. 2298--2306.  Lei Yang Xiaohang Zhan Dapeng Chen Junjie Yan Chen Change Loy and Dahua Lin. 2019 b. Learning to cluster faces on an affinity graph. In CVPR. 2298--2306.","DOI":"10.1109\/CVPR.2019.00240"},{"key":"e_1_3_2_2_52_1","unstructured":"Zhilin Yang Zihang Dai Yiming Yang Jaime Carbonell Russ R Salakhutdinov and Quoc V Le. 2019 a. Xlnet: Generalized autoregressive pretraining for language understanding. In NeurIPS. 5753--5763.  Zhilin Yang Zihang Dai Yiming Yang Jaime Carbonell Russ R Salakhutdinov and Quoc V Le. 2019 a. Xlnet: Generalized autoregressive pretraining for language understanding. In NeurIPS. 5753--5763."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"crossref","unstructured":"Ryota Yoshihashi Wen Shao Rei Kawakami Shaodi You Makoto Iida and Takeshi Naemura. 2019. Classification-reconstruction learning for open-set recognition. In CVPR. 4016--4025.  Ryota Yoshihashi Wen Shao Rei Kawakami Shaodi You Makoto Iida and Takeshi Naemura. 2019. Classification-reconstruction learning for open-set recognition. In CVPR. 4016--4025.","DOI":"10.1109\/CVPR.2019.00414"},{"key":"e_1_3_2_2_54_1","volume-title":"Mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412","author":"Zhang Hongyi","year":"2017"},{"key":"e_1_3_2_2_55_1","volume-title":"Conceptlearner: Discovering visual concepts from weakly labeled image collections. In CVPR. 1492--1500.","author":"Zhou Bolei","year":"2015"},{"key":"e_1_3_2_2_56_1","unstructured":"Jie Zhou Ganqu Cui Zhengyan Zhang Cheng Yang Zhiyuan Liu Lifeng Wang Changcheng Li and Maosong Sun. 2018. Graph neural networks: A review of methods and applications. arXiv preprint arXiv:1812.08434 (2018).  Jie Zhou Ganqu Cui Zhengyan Zhang Cheng Yang Zhiyuan Liu Lifeng Wang Changcheng Li and Maosong Sun. 2018. Graph neural networks: A review of methods and applications. arXiv preprint arXiv:1812.08434 (2018)."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Feng Zhu Hongsheng Li Wanli Ouyang Nenghai Yu and Xiaogang Wang. 2017. Learning spatial regularization with image-level supervisions for multi-label image classification. In CVPR. 5513--5522.  Feng Zhu Hongsheng Li Wanli Ouyang Nenghai Yu and Xiaogang Wang. 2017. Learning spatial regularization with image-level supervisions for multi-label image classification. In CVPR. 5513--5522.","DOI":"10.1109\/CVPR.2017.219"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413952","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:32:07Z","timestamp":1750195927000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413952"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":57,"alternative-id":["10.1145\/3394171.3413952","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413952","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}