{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T13:20:04Z","timestamp":1769001604509,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202499,62062021"],"award-info":[{"award-number":["62202499,62062021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hunan Provincial Natural Science Foundation of China","award":["2022JJ40632"],"award-info":[{"award-number":["2022JJ40632"]}]},{"name":"National Key R&D Program of China","award":["2021YFE0110500"],"award-info":[{"award-number":["2021YFE0110500"]}]},{"name":"Guiyang scientific plan project contract","award":["[2023] 48-11"],"award-info":[{"award-number":["[2023] 48-11"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611719","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"655-665","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["POAR: Towards Open Vocabulary Pedestrian Attribute Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0179-1396","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"first","affiliation":[{"name":"Henan Normal University, Xinxiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4086-0713","authenticated-orcid":false,"given":"Suchen","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0097-6196","authenticated-orcid":false,"given":"Shichao","family":"Kan","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7857-8687","authenticated-orcid":false,"given":"Zhenyu","family":"Weng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6255-9422","authenticated-orcid":false,"given":"Yigang","family":"Cen","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0645-9109","authenticated-orcid":false,"given":"Yap-peng","family":"Tan","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00451"},{"key":"e_1_3_2_2_2_1","volume-title":"A comprehensive survey of scene graphs: Generation and application","author":"Chang Xiaojun","year":"2021","unstructured":"Xiaojun Chang, Pengzhen Ren, Pengfei Xu, Zhihui Li, Xiaojiang Chen, and Alexander G Hauptmann. 2021. A comprehensive survey of scene graphs: Generation and application. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178144"},{"key":"e_1_3_2_2_4_1","volume-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Dan Yuhao","unstructured":"Yuhao Dan, Jie Zhou, Qin Chen, Qingchun Bai, and Liang He. 2022. Enhancing Class Understanding Via Prompt-Tuning For Zero-Shot Text Classification. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 4303--4307."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654966"},{"key":"e_1_3_2_2_6_1","volume-title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification. CoRR","author":"Ding Zefeng","year":"2021","unstructured":"Zefeng Ding, Changxing Ding, Zhiyin Shao, and Dacheng Tao. 2021. Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification. CoRR, Vol. abs\/2107.12666 (2021). [arXiv]2107.12666 https:\/\/arxiv.org\/abs\/2107.12666"},{"key":"e_1_3_2_2_7_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the AAAI conference on artificial intelligence.","author":"Esmaeilpour Sepideh","year":"2022","unstructured":"Sepideh Esmaeilpour, Bing Liu, Eric Robertson, and Lei Shu. 2022. Zero-Shot Out-of-Distribution Detection Based on the Pretrained Model CLIP. In Proceedings of the AAAI conference on artificial intelligence."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3045286"},{"key":"e_1_3_2_2_11_1","volume-title":"Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921","author":"Gu Xiuye","year":"2021","unstructured":"Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo, and Yin Cui. 2021. Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01591-y"},{"key":"e_1_3_2_2_13_1","volume-title":"Hand and Rama Chellappa","author":"Emily","year":"2017","unstructured":"Emily M. Hand and Rama Chellappa. 2017. Attributes for Improved Attributes: A Multi-Task Network Utilizing Implicit and Explicit Relationships for Facial Attribute Classification. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, USA, Satinder Singh and Shaul Markovitch (Eds.). AAAI Press, 4068--4074."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123424"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00100"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19991"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.450"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486476"},{"key":"e_1_3_2_2_20_1","volume-title":"Article arXiv:2207.08677 (July","author":"Li Wanhua","year":"2022","unstructured":"Wanhua Li, Zhexuan Cao, Jianjiang Feng, Jie Zhou, and Jiwen Lu. 2022. Label2Label: A Language Modeling Framework for Multi-Attribute Learning. arXiv e-prints, Article arXiv:2207.08677 (July 2022), Xiv:2207.08677 pages.arxiv: 2207.08677 [cs.CV]"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018690"},{"key":"e_1_3_2_2_22_1","volume-title":"Localization Guided Learning for Pedestrian Attribute Recognition. In British Machine Vision Conference 2018, BMVC 2019.","author":"Liu Pengze","year":"2018","unstructured":"Pengze Liu, Xihui Liu, Junjie Yan, and Jing Shao. 2018. Localization Guided Learning for Pedestrian Attribute Recognition. In British Machine Vision Conference 2018, BMVC 2019."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.46"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.10.003"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3259686"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00241"},{"key":"e_1_3_2_2_28_1","volume-title":"International Conference on Machine Learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6868"},{"key":"e_1_3_2_2_30_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV).","author":"Sarafianos Nikolaos","unstructured":"Nikolaos Sarafianos, Xiang Xu, and Ioannis A. Kakadiaris. 2018. Deep Imbalanced Attribute Classification using Visual Attention Aggregation. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_2_31_1","volume-title":"Multi-attribute Open Set Recognition. In DAGM German Conference on Pattern Recognition. Springer, 101--115","author":"Saranrittichai Piyapat","year":"2022","unstructured":"Piyapat Saranrittichai, Chaithanya Kumar Mummadi, Claudia Blaiotta, Mauricio Munoz, and Volker Fischer. 2022. Multi-attribute Open Set Recognition. In DAGM German Conference on Pattern Recognition. Springer, 101--115."},{"key":"e_1_3_2_2_32_1","volume-title":"British Machine Vision Conference 2017, BMVC 2017","author":"Sarfraz M. Saquib","year":"2017","unstructured":"M. Saquib Sarfraz, Arne Schumann, Yan Wang, and Rainer Stiefelhagen. 2017. Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model. In British Machine Vision Conference 2017, BMVC 2017, London, UK, September 4-7, 2017. BMVA Press."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6883"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00510"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.05.028"},{"key":"e_1_3_2_2_37_1","volume-title":"International Conference on Learning Representations.","author":"Vaze Sagar","year":"2022","unstructured":"Sagar Vaze, Kai Han, Andrea Vedaldi, and Andrew Zisserman. 2022. Open-Set Recognition: a Good Closed-Set Classifier is All You Need?. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108220"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.02.019"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01307"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01499-z"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2020.2999445"},{"key":"e_1_3_2_2_44_1","volume-title":"Local Correlation Ensemble with GCN based on Attention Features for Cross-domain Person Re-ID. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)","author":"Zhang Yue","year":"2022","unstructured":"Yue Zhang, Fanghui Zhang, Yi Jin, Yigang Cen, Viacheslav Voronin, and Shaohua Wan. 2022. Local Correlation Ensemble with GCN based on Attention Features for Cross-domain Person Re-ID. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) (2022)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/441"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019275"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_11"},{"key":"e_1_3_2_2_48_1","volume-title":"2015 International Conference on Biometrics (ICB). 535--540","author":"Zhu Jianqing","unstructured":"Jianqing Zhu, Shengcai Liao, Dong Yi, Zhen Lei, and Stan Z. Li. 2015. Multi-label CNN based pedestrian attribute learning for soft biometrics. In 2015 International Conference on Biometrics (ICB). 535--540."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611719","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:07:39Z","timestamp":1755821259000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611719"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":48,"alternative-id":["10.1145\/3581783.3611719","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611719","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}