{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:45Z","timestamp":1750309485187,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T00:00:00Z","timestamp":1726272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,14]]},"DOI":"10.1145\/3697355.3697362","type":"proceedings-article","created":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T04:52:23Z","timestamp":1734065543000},"page":"40-46","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An End-to-End Multi-modal-based Framework for Visual Identity Inspection System"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8453-2525","authenticated-orcid":false,"given":"Jing","family":"Wang","sequence":"first","affiliation":[{"name":"China Communications Information & Technology Group, BeiJing, BeiJing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9467-5520","authenticated-orcid":false,"given":"Zihao","family":"Zeng","sequence":"additional","affiliation":[{"name":"China Communications Information & Technology Group, BeiJing, BeiJing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6997-0231","authenticated-orcid":false,"given":"Haifeng","family":"Jiang","sequence":"additional","affiliation":[{"name":"China Communications Information & Technology Group, BeiJing, BeiJing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1340-292X","authenticated-orcid":false,"given":"Zhijie","family":"Jin","sequence":"additional","affiliation":[{"name":"China Communications Information & Technology Group, BeiJing, BeiJing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5044-7470","authenticated-orcid":false,"given":"Yang","family":"Mo","sequence":"additional","affiliation":[{"name":"China Communications Information & Technology Group, BeiJing, BeiJing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3604-4912","authenticated-orcid":false,"given":"Yexing","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Communications Information & Technology Group, HangZhou, ZheJiang, China"}]}],"member":"320","published-online":{"date-parts":[[2024,12,12]]},"reference":[{"key":"e_1_3_3_1_1_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-35385-7_3"},{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_3_1_4_2","volume-title":"NIPS (pp. 91\u201399).","author":"Ren S.","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real time object detection with region proposal networks. In NIPS (pp. 91\u201399)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_3_1_8_2","unstructured":"Ashish V. Noam S. Niki P. Jakob U. Llion J. Aidan G. \u0141ukasz K. & Illia P.(2017). Attention is all you need. In NeurIPS."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"e_1_3_3_1_10_2","unstructured":"Nicolas C. Francisco M. Gabriel S. Nicolas U. Alexander K. & Sergey Z.(2020). End-to-end object detection with transformers. In ECCV."},{"key":"e_1_3_3_1_11_2","first-page":"23","volume-title":"ACM Transactions on Multimedia Computing, Communications, and ApplicationsVolume 20,Issue","author":"Sujuan Hou","year":"2023","unstructured":"Sujuan Hou, Jiacheng Li, Weiqing Min, Qiang Hou, Yanna Zhao, Yuanjie Zheng, and Shuqiang Jiang, Deep learning for logo detection: A Survey, ACM Transactions on Multimedia Computing, Communications, and ApplicationsVolume 20,Issue 323, October 2023, Article No.: 72pp 1\u201323"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466780"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00066"},{"key":"e_1_3_3_1_14_2","first-page":"4391","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Jin W.","year":"2020","unstructured":"X. Jin, W. Su, R. Zhang, Y. He, and H. Xue, \u201cThe open brands dataset:Unified brand detection and recognition at scale,\u201d in IEEE International Conference on Acoustics, Speech and Signal Processing, 2020, pp.4387\u20134391"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.09941"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"e_1_3_3_1_17_2","first-page":"9365","volume-title":"CVPR","author":"Youngmin Baek","unstructured":"Youngmin Baek, Bado Lee, Dongyoon Han, Sangdoo Yun, and Hwalsuk Lee.(2019).Character Region Awareness for Text Detection, In CVPR, pp. 9365-9374"},{"key":"e_1_3_3_1_18_2","first-page":"9336","volume-title":"CVPR","author":"Wenhai Wang","unstructured":"Wenhai Wang, Enze Xie, Xiang Li, Wenbo Hou, Tong Lu, Gang Yu and Shuai Shao.(2019).Shape Robust Text Detection with Progressive Scale Expansion Network. In CVPR, pp. 9336-9345"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1998.710815"},{"key":"e_1_3_3_1_21_2","volume-title":"J. D., Cromartie, R., Geselowitz, A., Greer, T., ... & Zimmerman, J. B.","author":"Pizer S. M.","year":"1987","unstructured":"Pizer, S. M., Amburn, E. P., Austin, J. D., Cromartie, R., Geselowitz, A., Greer, T., ... & Zimmerman, J. B. (1987). Adaptive histogram equalization and its variations. Computer vision, graphics, and image processing, 39(3), 355-368."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Minghui Liao Zhaoyi Wan Cong Yao Kai Chen and Xiang Bai.(2020). Real-time Scene Text Detection with Differentiable Binarization. In AAAI.","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"e_1_3_3_1_23_2","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee.(2023). Visual Instruction Tuning. In NeurIPS Oral."},{"key":"e_1_3_3_1_24_2","unstructured":"JaidedAI. (n.d.). EasyOCR: Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin Chinese Arabic Devanagari Cyrillic and etc. [Online]. Version 1.7.1. Github Repository. Available: https:\/\/github.com\/JaidedAI\/EasyOCR"},{"key":"e_1_3_3_1_25_2","unstructured":"DayBreak-u \"chineseocr_lite \"GitHub. [Online]. Available:https:\/\/github.com\/DayBreak-u\/chineseocr_lite."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Diego A. Velazquez; Josep M. Gonfaus; Pau Rodr\u00edguez; F. Xavier Roca; Seiichi Ozawa; Jordi Gonz\u00e0lez.(2021).Logo Detection With No Priors. IEEE Access","DOI":"10.1109\/ACCESS.2021.3101297"},{"key":"e_1_3_3_1_28_2","unstructured":"Xiaojun Jia Huanqian Yan Yonglin Wu Xingxing Wei Xiaochun Cao Yong Zhang.(2021).An Effective and Robust Detector for Logo Detection.arXiv:2108.00422"}],"event":{"name":"BDIOT 2024: 2024 8th International Conference on Big Data and Internet of Things","acronym":"BDIOT 2024","location":"Macau China"},"container-title":["Proceedings of the 2024 8th International Conference on Big Data and Internet of Things"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3697355.3697362","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3697355.3697362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:34Z","timestamp":1750295854000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3697355.3697362"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,14]]},"references-count":28,"alternative-id":["10.1145\/3697355.3697362","10.1145\/3697355"],"URL":"https:\/\/doi.org\/10.1145\/3697355.3697362","relation":{},"subject":[],"published":{"date-parts":[[2024,9,14]]},"assertion":[{"value":"2024-12-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}