{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T12:18:07Z","timestamp":1771935487850,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"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":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658091","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"414-422","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A Lightweight Surface Defect Segmentation Network with External Semantics and High-frequency Information"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3979-1025","authenticated-orcid":false,"given":"Tianpeng","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences) & Shandong Engineering Research Center of Big Data Applied Technology, Faculty of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9339-8745","authenticated-orcid":false,"given":"Xuesong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences) & Shandong Engineering Research Center of Big Data Applied Technology, Faculty of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Michael Abebe Berwo Yong Fang Jabar Mahmood and Ephrem Afele Retta. 2021. Automotive Engine Cylinder Head Crack Detection: Canny Edge Detection With Morphological Dilation. In 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). 1519--1527."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/drones7030189"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_2_1_4_1","volume-title":"Head-free lightweight semantic segmentation with linear transformer. arXiv preprint arXiv:2301.04648","author":"Dong Bo","year":"2023","unstructured":"Bo Dong, Pichao Wang, and Fan Wang. 2023. Head-free lightweight semantic segmentation with linear transformer. arXiv preprint arXiv:2301.04648 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2958826"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3060461"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2023.3280117"},{"key":"e_1_3_2_1_8_1","first-page":"5436","article-title":"Beyond self-attention: External attention using two linear layers for visual tasks","volume":"45","author":"Guo Meng-Hao","year":"2022","unstructured":"Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu, and Shi-Min Hu. 2022. Beyond self-attention: External attention using two linear layers for visual tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 5 (2022), 5436--5447.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20071974"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-018-1588-5"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAECCT.2016.7942558"},{"key":"e_1_3_2_1_13_1","volume-title":"Sfnet: Faster and accurate semantic segmentation via semantic flow. International Journal of Computer Vision","author":"Li Xiangtai","year":"2023","unstructured":"Xiangtai Li, Jiangning Zhang, Yibo Yang, Guangliang Cheng, Kuiyuan Yang, Yunhai Tong, and Dacheng Tao. 2023. Sfnet: Faster and accurate semantic segmentation via semantic flow. International Journal of Computer Vision (2023), 1--24."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3138428"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2017.2755918"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00061"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00941"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3228042"},{"key":"e_1_3_2_1_20_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention--MICCAI 2015: 18th International Conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention--MICCAI 2015: 18th International Conference, Munich, Germany, October 5--9, 2015, Proceedings, Part III 18. Springer, 234--241."},{"key":"e_1_3_2_1_21_1","volume-title":"Steel defect detection, kaggle challange","year":"2019","unstructured":"Severstal. 2019. Steel defect detection, kaggle challange 2019. https:\/\/www.kaggle.com\/c\/severstal-steel-defect-detection."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3002277"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlaseng.2019.106000"},{"key":"e_1_3_2_1_25_1","volume-title":"Mobilevitv3: Mobile-friendly vision transformer with simple and effective fusion of local, global and input features. arXiv preprint arXiv:2209.15159","author":"Wadekar Shakti N","year":"2022","unstructured":"Shakti N Wadekar and Abhishek Chaurasia. 2022. Mobilevitv3: Mobile-friendly vision transformer with simple and effective fusion of local, global and input features. arXiv preprint arXiv:2209.15159 (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3250302"},{"key":"e_1_3_2_1_27_1","volume-title":"2023 a. Seaformer: Squeeze-enhanced axial transformer for mobile semantic segmentation. arXiv preprint arXiv:2301.13156","author":"Wan Qiang","year":"2023","unstructured":"Qiang Wan, Zilong Huang, Jiachen Lu, Gang Yu, and Li Zhang. 2023 a. Seaformer: Squeeze-enhanced axial transformer for mobile semantic segmentation. arXiv preprint arXiv:2301.13156 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Jingdong Wang Ke Sun Tianheng Cheng Borui Jiang Chaorui Deng Yang Zhao Dong Liu Yadong Mu Mingkui Tan Xinggang Wang et al. 2020a. Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence Vol. 43 10 (2020) 3349--3364.","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-31723-2_4"},{"key":"e_1_3_2_1_32_1","volume-title":"CBAM: Convolutional Block Attention Module. In Computer Vision -- ECCV","author":"Woo Sanghyun","year":"2018","unstructured":"Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In So Kweon. 2018. CBAM: Convolutional Block Attention Module. In Computer Vision -- ECCV 2018, Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer International Publishing, Cham, 3--19."},{"key":"e_1_3_2_1_33_1","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems , Vol. 34 (2021), 12077--12090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01871"},{"key":"e_1_3_2_1_35_1","volume-title":"Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects. arXiv preprint arXiv:2309.12641","author":"Yan Feng","year":"2023","unstructured":"Feng Yan, Xiaoheng Jiang, Yang Lu, Lisha Cui, Shupan Li, Jiale Cao, Mingliang Xu, and Dacheng Tao. 2023. Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects. arXiv preprint arXiv:2309.12641 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"e_1_3_2_1_37_1","first-page":"1","article-title":"MCnet: Multiple context information segmentation network of no-service rail surface defects","volume":"70","author":"Zhang Defu","year":"2020","unstructured":"Defu Zhang, Kechen Song, Jing Xu, Yu He, Menghui Niu, and Yunhui Yan. 2020. MCnet: Multiple context information segmentation network of no-service rail surface defects. IEEE Transactions on Instrumentation and Measurement , Vol. 70 (2020), 1--9.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747311"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533052"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106011"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3323004"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658091","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:45:51Z","timestamp":1755765951000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658091"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":42,"alternative-id":["10.1145\/3652583.3658091","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658091","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}