{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T16:49:44Z","timestamp":1783961384488,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T00:00:00Z","timestamp":1684454400000},"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":[[2023,5,19]]},"DOI":"10.1145\/3604078.3604108","type":"proceedings-article","created":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T16:46:07Z","timestamp":1698338767000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["ML-VehicleDet: A Unified Multi-label Vehicle Detection Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4013-2107","authenticated-orcid":false,"given":"Runwei","family":"Guan","sequence":"first","affiliation":[{"name":"Department of Computing, Xi'an Jiaotong-Liverpool University, China and \rSchool of EEE, University of Liverpool, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7596-3598","authenticated-orcid":false,"given":"Shanliang","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Computing, Xi'an Jiaotong-Liverpool University, China and \rSchool of Engineering, University of Liverpool, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1024-5442","authenticated-orcid":false,"given":"Xiaohui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computing, Xi'an Jiaotong-Liverpool University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0212-2365","authenticated-orcid":false,"given":"Jeremy","family":"Smith","sequence":"additional","affiliation":[{"name":"School of EEE, University of Liverpool, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5787-4716","authenticated-orcid":false,"given":"Ka Lok","family":"Man","sequence":"additional","affiliation":[{"name":"Department of Computing, Xi'an Jiaotong-Liverpool University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4532-0924","authenticated-orcid":false,"given":"Yutao","family":"Yue","sequence":"additional","affiliation":[{"name":"Institute of Deep Perception Technology, JITRI, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking.\u00a0Computer Vision and Image Understanding,\u00a0193, 102907","author":"Wen L.","year":"2020","unstructured":"Wen , L. , Du , D. , Cai , Z. , Lei , Z. , Chang , M. C. , Qi , H. , ... & Lyu , S. ( 2020 ). UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking.\u00a0Computer Vision and Image Understanding,\u00a0193, 102907 . Wen, L., Du, D., Cai, Z., Lei, Z., Chang, M. C., Qi, H., ... & Lyu, S. (2020). UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking.\u00a0Computer Vision and Image Understanding,\u00a0193, 102907."},{"key":"e_1_3_2_1_2_1","unstructured":"Jocher G.: YOLOv5. https:\/\/github.com\/ultralytics\/yolov5 (2021)  Jocher G.: YOLOv5. https:\/\/github.com\/ultralytics\/yolov5 (2021)"},{"key":"e_1_3_2_1_3_1","volume-title":"Yolox: Exceeding yolo series","author":"Ge Z.","year":"2021","unstructured":"Ge , Z. , Liu , S. , Wang , F. , Li , Z. , & Sun , J. ( 2021 ). Yolox: Exceeding yolo series in 2021.\u00a0arXiv preprint arXiv:2107.08430. Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021). Yolox: Exceeding yolo series in 2021.\u00a0arXiv preprint arXiv:2107.08430."},{"key":"e_1_3_2_1_4_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks.\u00a0Advances in neural information processing systems,\u00a028","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.\u00a0Advances in neural information processing systems,\u00a028 . Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks.\u00a0Advances in neural information processing systems,\u00a028."},{"key":"e_1_3_2_1_5_1","volume-title":"Yolov3: An incremental improvement.\u00a0arXiv preprint arXiv:1804.02767","author":"Redmon J.","year":"2018","unstructured":"Redmon , J. , & Farhadi , A. ( 2018 ). Yolov3: An incremental improvement.\u00a0arXiv preprint arXiv:1804.02767 . Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement.\u00a0arXiv preprint arXiv:1804.02767."},{"key":"e_1_3_2_1_6_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale.\u00a0arXiv preprint arXiv:2010.11929","author":"Dosovitskiy A.","year":"2020","unstructured":"Dosovitskiy , A. , Beyer , L. , Kolesnikov , A. , Weissenborn , D. , Zhai , X. , Unterthiner , T. , ... & Houlsby , N. ( 2020 ). An image is worth 16x16 words: Transformers for image recognition at scale.\u00a0arXiv preprint arXiv:2010.11929 . Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., ... & Houlsby, N. (2020). An image is worth 16x16 words: Transformers for image recognition at scale.\u00a0arXiv preprint arXiv:2010.11929."},{"key":"e_1_3_2_1_7_1","first-page":"2071","volume-title":"In\u00a0Proceedings of the AAAI Conference on Artificial Intelligence\u00a0(Vol. 36","author":"Paul S.","year":"2022","unstructured":"Paul , S. , & Chen , P. Y. ( 2022 , June). Vision transformers are robust learners . In\u00a0Proceedings of the AAAI Conference on Artificial Intelligence\u00a0(Vol. 36 , No. 2, pp. 2071 - 2081 ). Paul, S., & Chen, P. Y. (2022, June). Vision transformers are robust learners. In\u00a0Proceedings of the AAAI Conference on Artificial Intelligence\u00a0(Vol. 36, No. 2, pp. 2071-2081)."},{"key":"e_1_3_2_1_8_1","volume-title":"SGM: sequence generation model for multi-label classification.\u00a0arXiv preprint arXiv:1806.04822","author":"Yang P.","year":"2018","unstructured":"Yang , P. , Sun , X. , Li , W. , Ma , S. , Wu , W. , & Wang , H. ( 2018 ). SGM: sequence generation model for multi-label classification.\u00a0arXiv preprint arXiv:1806.04822 . Yang, P., Sun, X., Li, W., Ma, S., Wu, W., & Wang, H. (2018). SGM: sequence generation model for multi-label classification.\u00a0arXiv preprint arXiv:1806.04822."},{"key":"e_1_3_2_1_9_1","volume-title":"In\u00a0Asian Conference on Machine Learning\u00a0(pp. 125-140)","author":"Yang Y. Y.","year":"2019","unstructured":"Yang , Y. Y. , Lin , Y. A. , Chu , H. M. , & Lin , H. T. ( 2019 , October). Deep learning with a rethinking structure for multi-label classification . In\u00a0Asian Conference on Machine Learning\u00a0(pp. 125-140) . PMLR. Yang, Y. Y., Lin, Y. A., Chu, H. M., & Lin, H. T. (2019, October). Deep learning with a rethinking structure for multi-label classification. In\u00a0Asian Conference on Machine Learning\u00a0(pp. 125-140). PMLR."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00025"},{"key":"e_1_3_2_1_12_1","volume-title":"Hierarchical multi-label object detection framework for remote sensing images.\u00a0Remote Sensing,\u00a012(17), 2734","author":"Shin S. J.","year":"2020","unstructured":"Shin , S. J. , Kim , S. , Kim , Y. , & Kim , S. ( 2020 ). Hierarchical multi-label object detection framework for remote sensing images.\u00a0Remote Sensing,\u00a012(17), 2734 . Shin, S. J., Kim, S., Kim, Y., & Kim, S. (2020). Hierarchical multi-label object detection framework for remote sensing images.\u00a0Remote Sensing,\u00a012(17), 2734."},{"key":"e_1_3_2_1_13_1","volume-title":"GRAN: graph recurrent attention network for pedestrian orientation classification.\u00a0Complex & Intelligent Systems, 1-18","author":"Li X.","year":"2022","unstructured":"Li , X. , Ma , S. , Shan , L. , Liu , S. , & Chai , S. ( 2022 ). GRAN: graph recurrent attention network for pedestrian orientation classification.\u00a0Complex & Intelligent Systems, 1-18 . Li, X., Ma, S., Shan, L., Liu, S., & Chai, S. (2022). GRAN: graph recurrent attention network for pedestrian orientation classification.\u00a0Complex & Intelligent Systems, 1-18."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"e_1_3_2_1_16_1","volume-title":"The pascal visual object classes (voc) challenge.\u00a0International journal of computer vision,\u00a088(2), 303-338","author":"Everingham M.","year":"2010","unstructured":"Everingham , M. , Van Gool , L. , Williams , C. K. , Winn , J. , & Zisserman , A. ( 2010 ). The pascal visual object classes (voc) challenge.\u00a0International journal of computer vision,\u00a088(2), 303-338 . Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge.\u00a0International journal of computer vision,\u00a088(2), 303-338."},{"key":"e_1_3_2_1_17_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection.\u00a0arXiv preprint arXiv:2010.04159","author":"Zhu X.","year":"2020","unstructured":"Zhu , X. , Su , W. , Lu , L. , Li , B. , Wang , X. , & Dai , J. ( 2020 ). Deformable detr: Deformable transformers for end-to-end object detection.\u00a0arXiv preprint arXiv:2010.04159 . Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable detr: Deformable transformers for end-to-end object detection.\u00a0arXiv preprint arXiv:2010.04159."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"}],"event":{"name":"ICDIP 2023: The 15th International Conference on Digital Image Processing","location":"Nanjing China","acronym":"ICDIP 2023"},"container-title":["Proceedings of the 15th International Conference on Digital Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604078.3604108","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604078.3604108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:16Z","timestamp":1750178176000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604078.3604108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,19]]},"references-count":18,"alternative-id":["10.1145\/3604078.3604108","10.1145\/3604078"],"URL":"https:\/\/doi.org\/10.1145\/3604078.3604108","relation":{},"subject":[],"published":{"date-parts":[[2023,5,19]]},"assertion":[{"value":"2023-10-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}