{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T07:23:40Z","timestamp":1760081020894,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172256, 62202278, 62202272"],"award-info":[{"award-number":["62172256, 62202278, 62202272"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2019ZD06, ZR2020QF036"],"award-info":[{"award-number":["ZR2019ZD06, ZR2020QF036"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681350","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"8750-8758","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Hierarchical Multi-label Learning for Incremental Multilingual Text Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2187-8598","authenticated-orcid":false,"given":"Xiao-Qian","family":"Liu","sequence":"first","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7242-5452","authenticated-orcid":false,"given":"Ming-Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3481-4892","authenticated-orcid":false,"given":"Zhen-Duo","family":"Chen","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6901-5476","authenticated-orcid":false,"given":"Xin","family":"Luo","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9972-7370","authenticated-orcid":false,"given":"Xin-Shun","family":"Xu","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01984"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00481"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01467"},{"key":"e_1_3_2_1_4_1","volume-title":"Proc. Asia. Conf. Comput. Vis. Workshops","volume":"11367","author":"Busta Michal","year":"2018","unstructured":"Michal Busta, Yash Patel, and Jiri Matas. 2018. E2E-MLT - An Unconstrained End-to-End Method for Multi-language Scene Text. In Proc. Asia. Conf. Comput. Vis. Workshops, Vol. 11367. 127--143."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_15"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/124"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19971"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6735"},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. Eur. Conf. Comput. Vis. Workshops (4)","volume":"13804","author":"Huang Jing","year":"2022","unstructured":"Jing Huang, Kevin J. Liang, Rama Kovvuri, and Tal Hassner. 2022. Task Grouping for Multilingual Text Recognition. In Proc. Eur. Conf. Comput. Vis. Workshops (4), Vol. 13804. 297--313."},{"key":"e_1_3_2_1_13_1","volume-title":"Multilingual OCR. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 4547--4557","author":"Huang Jing","year":"2021","unstructured":"Jing Huang, Guan Pang, Rama Kovvuri, Mandy Toh, Kevin J. Liang, Praveen Krishnan, Xi Yin, and Tal Hassner. 2021. A Multiplexed Network for End-to-End, Multilingual OCR. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 4547--4557."},{"key":"e_1_3_2_1_14_1","volume-title":"Overcoming catastrophic forgetting in neural networks. CoRR","author":"Kirkpatrick James","year":"2016","unstructured":"James Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, and Raia Hadsell. 2016. Overcoming catastrophic forgetting in neural networks. CoRR, Vol. abs\/1612.00796 (2016)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_37"},{"volume-title":"Proc. IEEE Int. Conf. Pattern Recognit. 2262--2268","author":"Liu Xialei","key":"e_1_3_2_1_16_1","unstructured":"Xialei Liu, Marc Masana, Luis Herranz, Joost van de Weijer, Antonio M. L\u00f3pez, and Andrew D. Bagdanov. 2018. Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting. In Proc. IEEE Int. Conf. Pattern Recognit. 2262--2268."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26070"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107980"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475238"},{"volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 5533--5542","author":"Rebuffi Sylvestre-Alvise","key":"e_1_3_2_1_22_1","unstructured":"Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H. Lampert. 2017. iCaRL: Incremental Classifier and Representation Learning. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 5533--5542."},{"key":"e_1_3_2_1_23_1","volume-title":"Proc. Neural Inf. Process. Syst. 348--358","author":"Rolnick David","year":"2019","unstructured":"David Rolnick, Arun Ahuja, Jonathan Schwarz, Timothy P. Lillicrap, and Gregory Wayne. 2019. Experience Replay for Continual Learning. In Proc. Neural Inf. Process. Syst. 348--358."},{"key":"e_1_3_2_1_24_1","volume-title":"Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, and Raia Hadsell.","author":"Rusu Andrei A.","year":"2016","unstructured":"Andrei A. Rusu, Neil C. Rabinowitz andGuillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, and Raia Hadsell. 2016. Progressive Neural Networks. CoRR, Vol. abs\/1606.04671 (2016)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. Int. Conf. Document Anal. Recog. 1329--1337","author":"Triki Amal Rannen","year":"2017","unstructured":"Amal Rannen Triki, Rahaf Aljundi, Matthew B. Blaschko, and Tinne Tuytelaars. 2017. Encoder Based Lifelong Learning. In Proc. Int. Conf. Document Anal. Recog. 1329--1337."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611769"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612062"},{"key":"e_1_3_2_1_32_1","volume-title":"Proc. Neural Inf. Process. Syst. 907--916","author":"Xu Ju","year":"2018","unstructured":"Ju Xu and Zhanxing Zhu. 2018. Reinforced Continual Learning. In Proc. Neural Inf. Process. Syst. 907--916."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00035"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"e_1_3_2_1_35_1","volume-title":"Augmented Transformers with Adaptive n-grams Embedding for Multilingual Scene Text Recognition. CoRR","author":"Yan Xueming","year":"2023","unstructured":"Xueming Yan, Zhihang Fang, and Yaochu Jin. 2023. Augmented Transformers with Adaptive n-grams Embedding for Multilingual Scene Text Recognition. CoRR, Vol. abs\/2302.14261 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547784"},{"key":"e_1_3_2_1_37_1","volume-title":"Proc. Int. Conf. Learn. Represent. (Poster).","author":"Yoon Jaehong","year":"2018","unstructured":"Jaehong Yoon, Eunho Yang, Jeongtae Lee, and Sung Ju Hwang. 2018. Lifelong Learning with Dynamically Expandable Networks. In Proc. Int. Conf. Learn. Represent. (Poster)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/189"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612247"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01322"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01139"},{"key":"e_1_3_2_1_42_1","volume-title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model. CoRR","author":"Zhao Shuai","year":"2023","unstructured":"Shuai Zhao, Xiaohan Wang, Linchao Zhu, and Yi Yang. 2023. CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model. CoRR, Vol. abs\/2305.14014 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/197"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01709"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681350","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:44Z","timestamp":1750295864000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681350"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":44,"alternative-id":["10.1145\/3664647.3681350","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681350","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}