{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T21:51:41Z","timestamp":1791496301574,"version":"4.3.4"},"reference-count":65,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2018,10,10]],"date-time":"2018-10-10T00:00:00Z","timestamp":1539129600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Zhejiang Province Nature Science Foundation of China","award":["LR17F030006"],"award-info":[{"award-number":["LR17F030006"]}]},{"DOI":"10.13039\/501100013314","name":"111 Project","doi-asserted-by":"crossref","award":["D17019"],"award-info":[{"award-number":["D17019"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Cooperative Research Centres Programme"},{"DOI":"10.13039\/501100011818","name":"Data to Decisions CRC","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100011818","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61671196, 61525206 and 61701149"],"award-info":[{"award-number":["61671196, 61525206 and 61701149"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2017YFC0820600"],"award-info":[{"award-number":["2017YFC0820600"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2018,11,30]]},"abstract":"<jats:p>The superiority of deeply learned pedestrian representations has been reported in very recent literature of person re-identification (re-ID). In this article, we consider the more pragmatic issue of learning a deep feature with no or only a few labels. We propose a progressive unsupervised learning (PUL) method to transfer pretrained deep representations to unseen domains. Our method is easy to implement and can be viewed as an effective baseline for unsupervised re-ID feature learning. Specifically, PUL iterates between (1) pedestrian clustering and (2) fine-tuning of the convolutional neural network (CNN) to improve the initialization model trained on the irrelevant labeled dataset. Since the clustering results can be very noisy, we add a selection operation between the clustering and fine-tuning. At the beginning, when the model is weak, CNN is fine-tuned on a small amount of reliable examples that locate near to cluster centroids in the feature space. As the model becomes stronger, in subsequent iterations, more images are being adaptively selected as CNN training samples. Progressively, pedestrian clustering and the CNN model are improved simultaneously until algorithm convergence. This process is naturally formulated as self-paced learning. We then point out promising directions that may lead to further improvement. Extensive experiments on three large-scale re-ID datasets demonstrate that PUL outputs discriminative features that improve the re-ID accuracy. Our code has been released at https:\/\/github.com\/hehefan\/Unsupervised-Person-Re-identification-Clustering-and-Fine-tuning.<\/jats:p>","DOI":"10.1145\/3243316","type":"journal-article","created":{"date-parts":[[2018,10,10]],"date-time":"2018-10-10T09:30:46Z","timestamp":1539163846000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":557,"title":["Unsupervised Person Re-identification"],"prefix":"10.1145","volume":"14","author":[{"given":"Hehe","family":"Fan","sequence":"first","affiliation":[{"name":"Institute of Information and Control, Hangzhou Dianzi University and Center for Artificial Intelligence, University of Technology Sydney, Ultimo, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zheng","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence, University of Technology Sydney, Ultimo, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenggang","family":"Yan","sequence":"additional","affiliation":[{"name":"Institute of Information and Control, Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence, University of Technology Sydney, Ultimo, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,10,10]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA\u201907)","author":"Arthur David","year":"2007","unstructured":"David Arthur and Sergei Vassilvitskii . 2007 . k-means++: The advantages of careful seeding . In Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA\u201907) . 1027--1035. David Arthur and Sergei Vassilvitskii. 2007. k-means++: The advantages of careful seeding. In Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA\u201907). 1027--1035."},{"key":"e_1_2_1_2_1","volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201909)","author":"Babenko Boris","unstructured":"Boris Babenko , Ming-Hsuan Yang , and Serge J. Belongie . 2009. Visual tracking with online multiple instance learning . In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201909) . 983--990. Retrieved from Boris Babenko, Ming-Hsuan Yang, and Serge J. Belongie. 2009. Visual tracking with online multiple instance learning. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201909). 983--990. Retrieved from"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.358"},{"key":"e_1_2_1_4_1","doi-asserted-by":"crossref","unstructured":"S. Bai X. Bai Q. Tian and L. J. Latecki. 2018. Regularized diffusion process on bidirectional context for object retrieval. IEEE Trans. Pattern Anal. Mach. Intell. (2018). Retrieved from  S. Bai X. Bai Q. Tian and L. J. Latecki. 2018. Regularized diffusion process on bidirectional context for object retrieval. IEEE Trans. Pattern Anal. Mach. Intell. (2018). Retrieved from","DOI":"10.1109\/TPAMI.2018.2828815"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.90"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.142"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.145"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.149"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821921"},{"key":"e_1_2_1_11_1","volume-title":"Few-example object detection with model communication","author":"Dong Xuanyi","year":"2018","unstructured":"Xuanyi Dong , Liang Zheng , Fan Ma , Yi Yang , and Deyu Meng . 2018. Few-example object detection with model communication . IEEE Trans. Pattern Anal. Mach. Intell. ( 2018 ). Retrieved from Xuanyi Dong, Liang Zheng, Fan Ma, Yi Yang, and Deyu Meng. 2018. Few-example object detection with model communication. IEEE Trans. Pattern Anal. Mach. Intell. (2018). Retrieved from"},{"key":"e_1_2_1_12_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV\u201917)","author":"Fan Hehe","unstructured":"Hehe Fan , Xiaojun Chang , De Cheng , Yi Yang , Dong Xu , and Alexander G. Hauptmann . 2017. Complex event detection by identifying reliable shots from untrimmed videos . In Proceedings of the IEEE International Conference on Computer Vision (ICCV\u201917) . 736--744. Retrieved from Hehe Fan, Xiaojun Chang, De Cheng, Yi Yang, Dong Xu, and Alexander G. Hauptmann. 2017. Complex event detection by identifying reliable shots from untrimmed videos. In Proceedings of the IEEE International Conference on Computer Vision (ICCV\u201917). 736--744. Retrieved from"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539926"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"e_1_2_1_15_1","unstructured":"Mengyue Geng Yaowei Wang Tao Xiang and Yonghong Tian. 2016. Deep transfer learning for person re-identification. arXiv abs\/1611.05244.  Mengyue Geng Yaowei Wang Tao Xiang and Yonghong Tian. 2016. Deep transfer learning for person re-identification. arXiv abs\/1611.05244."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_21"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_18_1","unstructured":"Alexander Hermans Lucas Beyer and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. arXiv abs\/1703.07737.  Alexander Hermans Lucas Beyer and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. arXiv abs\/1703.07737."},{"key":"e_1_2_1_19_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems. 2078--2086","author":"Jiang Lu","unstructured":"Lu Jiang , Deyu Meng , Shoou- I Yu , Zhen-Zhong Lan , Shiguang Shan , and Alexander G. Hauptmann . 2014. Self-paced learning with diversity . In Proceedings of the Annual Conference on Neural Information Processing Systems. 2078--2086 . Lu Jiang, Deyu Meng, Shoou-I Yu, Zhen-Zhong Lan, Shiguang Shan, and Alexander G. Hauptmann. 2014. Self-paced learning with diversity. In Proceedings of the Annual Conference on Neural Information Processing Systems. 2078--2086."},{"key":"e_1_2_1_20_1","volume-title":"Proceedings of the 14th European Conference on Computer Vision (ECCV\u201916)","author":"Kodirov Elyor","year":"2016","unstructured":"Elyor Kodirov , Tao Xiang , Zhen-Yong Fu , and Shaogang Gong . 2016 . Person re-identification by unsupervised l<sub>1<\/sub> graph learning . In Proceedings of the 14th European Conference on Computer Vision (ECCV\u201916) . 178--195. Retrieved from Elyor Kodirov, Tao Xiang, Zhen-Yong Fu, and Shaogang Gong. 2016. Person re-identification by unsupervised l<sub>1<\/sub> graph learning. In Proceedings of the 14th European Conference on Computer Vision (ECCV\u201916). 178--195. Retrieved from"},{"key":"e_1_2_1_21_1","volume-title":"Proceedings of the 26th Annual Conference on Neural Information Processing Systems. 1106--1114","author":"Krizhevsky Alex","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E. Hinton . 2012. ImageNet classification with deep convolutional neural networks . In Proceedings of the 26th Annual Conference on Neural Information Processing Systems. 1106--1114 . Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In Proceedings of the 26th Annual Conference on Neural Information Processing Systems. 1106--1114."},{"key":"e_1_2_1_22_1","volume-title":"Proceedings of the 24th Annual Conference on Neural Information Processing Systems. 1189--1197","author":"Kumar M. Pawan","year":"2010","unstructured":"M. Pawan Kumar , Benjamin Packer , and Daphne Koller . 2010 . Self-paced learning for latent variable models . In Proceedings of the 24th Annual Conference on Neural Information Processing Systems. 1189--1197 . M. Pawan Kumar, Benjamin Packer, and Daphne Koller. 2010. Self-paced learning for latent variable models. In Proceedings of the 24th Annual Conference on Neural Information Processing Systems. 1189--1197."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.27"},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201915)","author":"Liao Shengcai","unstructured":"Shengcai Liao , Yang Hu , Xiangyu Zhu , and Stan Z. Li . 2015. Person re-identification by local maximal occurrence representation and metric learning . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201915) . 2197--2206. Retrieved from Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z. Li. 2015. Person re-identification by local maximal occurrence representation and metric learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201915). 2197--2206. Retrieved from"},{"key":"e_1_2_1_25_1","unstructured":"Yutian Lin Liang Zheng Zhedong Zheng Yu Wu and Yi Yang. 2017. Improving person re-identification by attribute and identity learning. arXiv abs\/1703.07220.  Yutian Lin Liang Zheng Zhedong Zheng Yu Wu and Yi Yang. 2017. Improving person re-identification by attribute and identity learning. arXiv abs\/1703.07220."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.62"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2700762"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967209"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751966"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3305916"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.11.018"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2659221"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.146"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_1"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.410"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_48"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_25"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_45"},{"key":"e_1_2_1_42_1","unstructured":"Longhui Wei Shiliang Zhang Wen Gao and Qi Tian. 2017. Person transfer GAN to bridge domain gap for person re-identification. arXiv abs\/1711.08565.  Longhui Wei Shiliang Zhang Wen Gao and Qi Tian. 2017. Person transfer GAN to bridge domain gap for person re-identification. arXiv abs\/1711.08565."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00543"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.140"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.360"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2749977"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2749965"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3089249"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2237023"},{"key":"e_1_2_1_50_1","volume-title":"Proceedings of the 21st AAAI Conference on Artificial Intelligence. 4306--4312","author":"Yang Yang","unstructured":"Yang Yang , Longyin Wen , Siwei Lyu , and Stan Z. Li . 2017. Unsupervised learning of multi-level descriptors for person re-identification . In Proceedings of the 21st AAAI Conference on Artificial Intelligence. 4306--4312 . Yang Yang, Longyin Wen, Siwei Lyu, and Stan Z. Li. 2017. Unsupervised learning of multi-level descriptors for person re-identification. In Proceedings of the 21st AAAI Conference on Artificial Intelligence. 4306--4312."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2605058"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.16"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.139"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.143"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.314"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.460"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.26"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_52"},{"key":"e_1_2_1_59_1","volume-title":"Pose invariant embedding for deep person re-identification. arXiv abs\/1701.07732","author":"Zheng Liang","year":"2017","unstructured":"Liang Zheng , Yujia Huang , Huchuan Lu , and Yi Yang . 2017. Pose invariant embedding for deep person re-identification. arXiv abs\/1701.07732 ( 2017 ). Liang Zheng, Yujia Huang, Huchuan Lu, and Yi Yang. 2017. Pose invariant embedding for deep person re-identification. arXiv abs\/1701.07732 (2017)."},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.5555\/2919332.2919877"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298783"},{"key":"e_1_2_1_62_1","volume-title":"Hauptmann","author":"Zheng Liang","year":"2016","unstructured":"Liang Zheng , Yi Yang , and Alexander G . Hauptmann . 2016 . Person re-identification: Past , present and future. arXiv abs\/1610.02984 (2016). Liang Zheng, Yi Yang, and Alexander G. Hauptmann. 2016. Person re-identification: Past, present and future. arXiv abs\/1610.02984 (2016)."},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2709749"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.405"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.389"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3243316","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3243316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:57:31Z","timestamp":1750193851000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3243316"}},"subtitle":["Clustering and Fine-tuning"],"short-title":[],"issued":{"date-parts":[[2018,10,10]]},"references-count":65,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,11,30]]}},"alternative-id":["10.1145\/3243316"],"URL":"https:\/\/doi.org\/10.1145\/3243316","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,10]]},"assertion":[{"value":"2018-02-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}