{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T22:43:02Z","timestamp":1774219382095,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guoqiang Institute Tsinghua University and the Natural Science Foundation of Hunan Province China","award":["No. 2020JJ2050"],"award-info":[{"award-number":["No. 2020JJ2050"]}]},{"name":"National Natural Science Foundation of China","award":["No. 62122095 62072472 and U19A2067"],"award-info":[{"award-number":["No. 62122095 62072472 and U19A2067"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548274","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:46Z","timestamp":1665416566000},"page":"3628-3636","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["FastPR: One-stage Semantic Person Retrieval via Self-supervised Learning"],"prefix":"10.1145","author":[{"given":"Meng","family":"Sun","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Ju","family":"Ren","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Yaoxue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093640"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00940"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.06.015"},{"key":"e_1_3_2_2_4_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"e_1_3_2_2_6_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Duan Xuguang","year":"2018","unstructured":"Xuguang Duan , Wenbing Huang , Chuang Gan , Jingdong Wang , Wenwu Zhu , and Junzhou Huang . 2018 . Weakly supervised dense event captioning in videos . Advances in Neural Information Processing Systems , Vol. 31 (2018). Xuguang Duan, Wenbing Huang, Chuang Gan, Jingdong Wang, Wenwu Zhu, and Junzhou Huang. 2018. Weakly supervised dense event captioning in videos. Advances in Neural Information Processing Systems, Vol. 31 (2018)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682632"},{"key":"e_1_3_2_2_8_1","volume-title":"Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728","author":"Gidaris Spyros","year":"2018","unstructured":"Spyros Gidaris , Praveer Singh , and Nikos Komodakis . 2018. Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728 ( 2018 ). Spyros Gidaris, Praveer Singh, and Nikos Komodakis. 2018. Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728 (2018)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.770"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_11_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00202"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"e_1_3_2_2_14_1","volume-title":"Self-supervised learning: Generative or contrastive","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu , Fanjin Zhang , Zhenyu Hou , Li Mian , Zhaoyu Wang , Jing Zhang , and Jie Tang . 2021. Self-supervised learning: Generative or contrastive . IEEE Transactions on Knowledge and Data Engineering ( 2021 ). Xiao Liu, Fanjin Zhang, Zhenyu Hou, Li Mian, Zhaoyu Wang, Jing Zhang, and Jie Tang. 2021. Self-supervised learning: Generative or contrastive. IEEE Transactions on Knowledge and Data Engineering (2021)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240712"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein etal 2015. Imagenet large scale visual recognition challenge. International journal of computer vision Vol. 115 3 (2015) 211--252.  Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision Vol. 115 3 (2015) 211--252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW52041.2021.00009"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"e_1_3_2_2_25_1","volume-title":"Self-supervised dialogue learning. arXiv preprint arXiv:1907.00448","author":"Wu Jiawei","year":"2019","unstructured":"Jiawei Wu , Xin Wang , and William Yang Wang . 2019. Self-supervised dialogue learning. arXiv preprint arXiv:1907.00448 ( 2019 ). Jiawei Wu, Xin Wang, and William Yang Wang. 2019. Self-supervised dialogue learning. arXiv preprint arXiv:1907.00448 (2019)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"e_1_3_2_2_27_1","volume-title":"Transfer Learning Based Approach for Semantic Person Retrieval. In 15th IEEE International Conference on Advanced Video and Signal-based Surveillance: AVSS 2018 (30\/11\/18)","author":"Yaguchi Takuya","unstructured":"Takuya Yaguchi and Mark S. Nixon . 2018 . Transfer Learning Based Approach for Semantic Person Retrieval. In 15th IEEE International Conference on Advanced Video and Signal-based Surveillance: AVSS 2018 (30\/11\/18) . Takuya Yaguchi and Mark S. Nixon. 2018. Transfer Learning Based Approach for Semantic Person Retrieval. In 15th IEEE International Conference on Advanced Video and Signal-based Surveillance: AVSS 2018 (30\/11\/18)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462924"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.10"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548274","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:42Z","timestamp":1750186842000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548274"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":34,"alternative-id":["10.1145\/3503161.3548274","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548274","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}