{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T17:31:00Z","timestamp":1767375060012,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":41,"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":[{"name":"Natural Science Foundation of Tianjin Municipality","award":["23JCZDJC00280"],"award-info":[{"award-number":["23JCZDJC00280"]}]},{"name":"R&D Program of Beijing Municipal Education Commission","award":["KZ202210005007"],"award-info":[{"award-number":["KZ202210005007"]}]},{"name":"Shandong Project towards the Integration of Education and Industry","award":["2022JBZ01-03"],"award-info":[{"award-number":["2022JBZ01-03"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372325"],"award-info":[{"award-number":["62372325"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shandong Province National Talents Supporting Program","award":["2023GJJLJRC-070"],"award-info":[{"award-number":["2023GJJLJRC-070"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681383","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"2700-2708","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A Coarse to Fine Detection Method for Prohibited Object in X-ray Images Based on Progressive Transformer Decoder"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6348-671X","authenticated-orcid":false,"given":"Chunjie","family":"Ma","sequence":"first","affiliation":[{"name":"Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3619-6757","authenticated-orcid":false,"given":"Lina","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong Jianzhu University, Jinan, Shandong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2182-5741","authenticated-orcid":false,"given":"Zan","family":"Gao","sequence":"additional","affiliation":[{"name":"Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9937-2669","authenticated-orcid":false,"given":"Li","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Beijing University Of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"volume-title":"IEEE\/CVF International Conference on Computer Vision. IEEE","author":"Bodla Navaneeth","key":"e_1_3_2_1_1_1","unstructured":"Navaneeth Bodla, Bharat Singh, Rama Chellappa, and Larry S. Davis. 0022\/2017- 10--29. Soft-NMS -- Improving Object Detection with One Line of Code. In IEEE\/CVF International Conference on Computer Vision. IEEE, Los Alamitos, CA, USA, 5561--5569."},{"key":"e_1_3_2_1_2_1","volume-title":"Endto- End Object Detection with Transformers. In European Conference on Computer Vision (ECCV)","author":"Carion Nicolas","year":"2020","unstructured":"Nicolas Carion, F MASSA, N Usunier, and G SYNNAEVE. 2020,August 23--28. Endto- End Object Detection with Transformers. In European Conference on Computer Vision (ECCV). Glasgow, UK, 213--229."},{"key":"e_1_3_2_1_3_1","volume-title":"Atomic Number Prior Guided Network for Prohibited Items Detection from Heavily Cluttered X-ray Imagery. Frontiers in Physics 10 (Jan","author":"Chen Jinwen","year":"2023","unstructured":"Jinwen Chen, Jiaxu Leng, Xinbo Gao, Mengjingcheng Mo, and Shibo Guan. 2023. Atomic Number Prior Guided Network for Prohibited Items Detection from Heavily Cluttered X-ray Imagery. Frontiers in Physics 10 (Jan. 2023), 1117261."},{"key":"e_1_3_2_1_4_1","volume-title":"YOLOX: Exceeding YOLO Series in","author":"Ge Zheng","year":"2021","unstructured":"Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, and Jian Sun. 2021. YOLOX: Exceeding YOLO Series in 2021. arXiv:2107.08430 [cs]"},{"key":"e_1_3_2_1_5_1","volume-title":"Mask R-CNN. In IEEE\/CVF International Conference on Computer Vision","author":"He Kaiming","year":"2017","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, and Ross Girshick. 2017. Mask R-CNN. In IEEE\/CVF International Conference on Computer Vision. Honolulu, HI, USA, 2961--2969."},{"volume-title":"Multi- View Vision Transformers for Object Detection. In International Conference on Pattern Recognition (ICPR). IEEE, Montreal, QC, Canada, 4678--4684","author":"Isaac-Medina Brian K. S.","key":"e_1_3_2_1_6_1","unstructured":"Brian K. S. Isaac-Medina, Chris G. Willcocks, and Toby P. Breckon. 2022. Multi- View Vision Transformers for Object Detection. In International Conference on Pattern Recognition (ICPR). IEEE, Montreal, QC, Canada, 4678--4684."},{"key":"e_1_3_2_1_7_1","volume-title":"DETRs with Hybrid Matching. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Vancouver Canada","author":"Jia Ding","year":"2023","unstructured":"Ding Jia, Yuhui Yuan, Haodi He, Xiaopei Wu, Haojun Yu, Weihong Lin, Lei Sun, Chao Zhang, and Han Hu. 2023-06--20\/0022. DETRs with Hybrid Matching. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Vancouver Canada, 19702--19712. arXiv:2207.13080 [cs]"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612563"},{"key":"e_1_3_2_1_9_1","unstructured":"Glenn Jocher Alex Stoken Jirka Borovec NanoCode012 ChristopherSTAN Liu Changyu Laughing tkianai yxNONG Adam Hogan lorenzomammana AlexWang1900 Ayush Chaurasia Laurentiu Diaconu Marc wanghaoyang0106 ml5ah Doug Durgesh Francisco Ingham Frederik Guilhen Adrien Colmagro Hu Ye Jacobsolawetz Jake Poznanski Jiacong Fang Junghoon Kim Khiem Doan and Lijun Yu. 2021. Ultralytics\/YOLOv5: V4.0 - Nn.SiLU() Activations Weights & Biases Logging PyTorch Hub Integration. Zenodo."},{"key":"e_1_3_2_1_10_1","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE","author":"Li Feng","year":"2022","unstructured":"Feng Li, Hao Zhang, Shilong Liu, Jian Guo, Lionel M. Ni, and Lei Zhang. 2022. DNDETR: Accelerate DETR Training by Introducing Query DeNoising. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, New Orleans, LA, USA, 13609--13617."},{"key":"e_1_3_2_1_11_1","volume-title":"DAB-DETR: Dynamic Anchor Boxes Are Better Queries for DETR. In International Conference on Learning Representations. Virtual, 1--19","author":"Liu Shilong","year":"2022","unstructured":"Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, and Lei Zhang. 2022. DAB-DETR: Dynamic Anchor Boxes Are Better Queries for DETR. In International Conference on Learning Representations. Virtual, 1--19."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12560"},{"key":"e_1_3_2_1_13_1","volume-title":"SSD: Single Shot Multibox Detector. In European Conference on Computer Vision","author":"Liu Wei","year":"2016","unstructured":"Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng Yang Fu, and Alexander C. Berg. 2016. SSD: Single Shot Multibox Detector. In European Conference on Computer Vision (Amsterdam, Netherlands, 2016--10- . Springer, 21--37."},{"volume-title":"Grid R-CNN. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE","author":"Lu Xin","key":"e_1_3_2_1_14_1","unstructured":"Xin Lu, Buyu Li, Yuxin Yue, Quanquan Li, and Junjie Yan. 0016\/2019-06--20. Grid R-CNN. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Long Beach, CA, USA, 7355--7364."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12514"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023"},{"key":"e_1_3_2_1_17_1","volume-title":"Occluded Prohibited Object Detection in X-Ray Images with Global Context-Aware Multi- Scale Feature Aggregation. Neurocomputing 519 (Jan","author":"Ma Chunjie","year":"2023","unstructured":"Chunjie Ma, Li Zhuo, Jiafeng Li, Yutong Zhang, and Jing Zhang. 2023. Occluded Prohibited Object Detection in X-Ray Images with Global Context-Aware Multi- Scale Feature Aggregation. Neurocomputing 519 (Jan. 2023), 1--16."},{"key":"e_1_3_2_1_18_1","volume-title":"Conditional DETR for Fast Training Convergence. In IEEE\/CVF International Conference on Computer Vision. IEEE, Montreal, QC, Canada, 3631--3640","author":"Meng Depu","year":"2021","unstructured":"Depu Meng, Xiaokang Chen, Zejia Fan, Gang Zeng, Houqiang Li, Yuhui Yuan, Lei Sun, and JingdongWang. 2021. Conditional DETR for Fast Training Convergence. In IEEE\/CVF International Conference on Computer Vision. IEEE, Montreal, QC, Canada, 3631--3640."},{"volume-title":"Efficient Non-Maximum Suppression. In International Conference on Pattern Recognition","author":"Neubeck A.","key":"e_1_3_2_1_19_1","unstructured":"A. Neubeck and L. Van Gool. 2006. Efficient Non-Maximum Suppression. In International Conference on Pattern Recognition. Hong Kong, China, 850--855."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/mi13040565"},{"volume-title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE","author":"Qiao Siyuan","key":"e_1_3_2_1_21_1","unstructured":"Siyuan Qiao, Liang-Chieh Chen, and Alan Yuille. 0019\/2021-06--25. DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Virtual, Online, USA, 10208--10219."},{"key":"e_1_3_2_1_22_1","volume-title":"Real-Time Object Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Redmon Joseph","year":"2016","unstructured":"Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (Las Vegas, NV, USA, 2016-06--27). IEEE, 779--788."},{"key":"e_1_3_2_1_23_1","first-page":"1137","article-title":"Faster R-CNN","volume":"39","author":"Ren Shaoqing","year":"2017","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2017. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. 39, 6 (2017), 1137--1149.","journal-title":"Towards Real-Time Object Detection with Region Proposal Networks."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"volume-title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE","author":"Sun Peize","key":"e_1_3_2_1_25_1","unstructured":"Peize Sun, Rufeng Zhang, Yi Jiang, Tao Kong, Chenfeng Xu,Wei Zhan, Masayoshi Tomizuka, Lei Li, Zehuan Yuan, Changhu Wang, and Ping Luo. 0019\/2021-06- 25. Sparse R-CNN: End-to-End Object Detection with Learnable Proposals. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Virtual, Online, USA, 14449--14458."},{"volume-title":"Advances in Neural Information Processing Systems (NeurIPS). Curran Associates","author":"Vaswani Ashish","key":"e_1_3_2_1_26_1","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017--12-04\/2017--12-09. Attention Is All You Need. In Advances in Neural Information Processing Systems (NeurIPS). Curran Associates, Inc., Long Beach, CA, USA, 1--15."},{"key":"e_1_3_2_1_27_1","volume-title":"Transformers for Imbalanced Baggage Threat Recognition. In IEEE International Symposium on Robotic and Sensors Environments. IEEE, Abu Dhabi, United Arab Emirates, 1--7.","author":"Velayudhan Divya","year":"2022","unstructured":"Divya Velayudhan, Abdelfatah Hassan Ahmed, Taimur Hassan, Mohammed Bennamoun, Ernesto Damiani, and Naoufel Werghi. 2022. Transformers for Imbalanced Baggage Threat Recognition. In IEEE International Symposium on Robotic and Sensors Environments. IEEE, Abu Dhabi, United Arab Emirates, 1--7."},{"key":"e_1_3_2_1_28_1","volume-title":"Material- Aware Cross-channel Interaction Attention (MCIA) for Occluded Prohibited Item Detection. The Visual Computer (May","author":"Du Huiqian","year":"2022","unstructured":"ManWang, Huiqian Du,Wenbo Mei, ShauiWang, and Dasen Yuan. 2022. Material- Aware Cross-channel Interaction Attention (MCIA) for Occluded Prohibited Item Detection. The Visual Computer (May 2022), 1--13."},{"key":"e_1_3_2_1_29_1","first-page":"22","article-title":"YOLO-T: Multitarget Intelligent Recognition Method for X-ray Images Based on the YOLO and Transformer Models","volume":"12","author":"Wang Mingxun","year":"2022","unstructured":"Mingxun Wang, Baolu Yang, Xin Wang, Cheng Yang, Jie Xu, Baozhong Mu, Kai Xiong, and Yanyi Li. 2022. YOLO-T: Multitarget Intelligent Recognition Method for X-ray Images Based on the YOLO and Transformer Models. Applied Sciences 12, 22 (Nov. 2022), 11848.","journal-title":"Applied Sciences"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2400\/1\/012041"},{"key":"e_1_3_2_1_31_1","volume-title":"X-Ray Small Target Security Inspection Based on TB-YOLOv5. Security and Communication Networks 2022 (Aug","author":"Wang Muchen","year":"2022","unstructured":"Muchen Wang, Yueming Zhu, Yongkang Liu, and Huiping Deng. 2022. X-Ray Small Target Security Inspection Based on TB-YOLOv5. Security and Communication Networks 2022 (Aug. 2022), 1--16."},{"key":"e_1_3_2_1_32_1","volume-title":"IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI). IEEE","author":"Zhang Hongyi","year":"2022","unstructured":"ZuoshuaiWang, Hongyi Zhang, Zhibin Lin, Xiangqiong Tan, and Ben Zhou. 2022. Prohibited Items Detection in Baggage Security Based on Improved YOLOv5. In IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI). IEEE, Xiamen, China, 20--25."},{"volume-title":"Operationalizing Convolutional Neural Network Architectures for Prohibited Object Detection in X-ray Imagery. In IEEE International Conference on Machine Learning and Applications. IEEE","author":"Webb W.","key":"e_1_3_2_1_33_1","unstructured":"ThomasW.Webb, Neelanjan Bhowmik, Yona Falinie A. Gaus, and Toby P. Breckon. 2021. Operationalizing Convolutional Neural Network Architectures for Prohibited Object Detection in X-ray Imagery. In IEEE International Conference on Machine Learning and Applications. IEEE, Pasadena, CA, USA, 610--615."},{"volume-title":"Rethinking Classification and Localization for Object Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE","author":"Wu Yue","key":"e_1_3_2_1_34_1","unstructured":"Yue Wu, Yinpeng Chen, Lu Yuan, Zicheng Liu, Lijuan Wang, Hongzhi Li, and Yun Fu. 0014\/2020-06--19. Rethinking Classification and Localization for Object Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Seattle, WA, USA, 10183--10192."},{"key":"e_1_3_2_1_35_1","volume-title":"Dynamic R-CNN: Towards High Quality Object Detection Via Dynamic Training. In European Conference on Computer Vision (Lecture Notes in Computer Science). Springer","author":"Zhang Hongkai","year":"2020","unstructured":"Hongkai Zhang, Hong Chang, Bingpeng Ma, Naiyan Wang, and Xilin Chen. 23--28, August, 2020. Dynamic R-CNN: Towards High Quality Object Detection Via Dynamic Training. In European Conference on Computer Vision (Lecture Notes in Computer Science). Springer, Glasgow, UK, 260--275."},{"key":"e_1_3_2_1_36_1","volume-title":"X-Ray Image Recognition Based on Improved Mask R-CNN Algorithm. Mathematical Problems in Engineering 2021 (Sept","author":"Zhang Jicun","year":"2021","unstructured":"Jicun Zhang, Xueping Song, Jiawei Feng, and Jiyou Fei. 2021. X-Ray Image Recognition Based on Improved Mask R-CNN Algorithm. Mathematical Problems in Engineering 2021 (Sept. 2021), 14."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611788"},{"key":"e_1_3_2_1_38_1","volume-title":"Progressive End-to-End Object Detection in Crowded Scenes. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE","author":"Zheng Anlin","year":"2022","unstructured":"Anlin Zheng, Yuang Zhang, Xiangyu Zhang, Xiaojuan Qi, and Jian Sun. 2022. Progressive End-to-End Object Detection in Crowded Scenes. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, New Orleans, Louisiana, USA, 857--866."},{"key":"e_1_3_2_1_39_1","volume-title":"Less Is More: Focus Attention for Efficient DETR. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE","author":"Zheng Dehua","year":"2023","unstructured":"Dehua Zheng, Wenhui Dong, Hailin Hu, Xinghao Chen, and Yunhe Wang. 2023. Less Is More: Focus Attention for Efficient DETR. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE, Paris, France, 6651--6660."},{"volume-title":"Deformable DETR: Deformable Transformers for Endto-End Object Detection. In International Conference on Learning Representations. ICLR, Virtual Conference, 1--16","author":"Zhu Xizhou","key":"e_1_3_2_1_40_1","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. Apr 26th through May 1st,2020. Deformable DETR: Deformable Transformers for Endto-End Object Detection. In International Conference on Learning Representations. ICLR, Virtual Conference, 1--16."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108076"}],"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\/3664647.3681383","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681383","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\/3664647.3681383"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":41,"alternative-id":["10.1145\/3664647.3681383","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681383","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"}}]}}