{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:57:48Z","timestamp":1781539068681,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100004932","name":"Texas Department of Transportation","doi-asserted-by":"publisher","award":["0-7150"],"award-info":[{"award-number":["0-7150"]}],"id":[{"id":"10.13039\/100004932","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation","award":["2213694"],"award-info":[{"award-number":["2213694"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810611","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"2448-2456","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Data-Centric Multimodal Pavement Distress Detection Using Intensity\u2013Range Imagery"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5809-9379","authenticated-orcid":false,"given":"Wenhan","family":"Tao","sequence":"first","affiliation":[{"name":"Texas State University, San Marcos, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2762-8709","authenticated-orcid":false,"given":"Yongsheng","family":"Bai","sequence":"additional","affiliation":[{"name":"Texas State University, San Marcos, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1528-9711","authenticated-orcid":false,"given":"Feng","family":"Wang","sequence":"additional","affiliation":[{"name":"Texas State University, San Marcos, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9972-9760","authenticated-orcid":false,"given":"Jelena","family":"Te\u0161i\u0107","sequence":"additional","affiliation":[{"name":"Texas State University, San Marcos, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Tadas Baltru\u0161aitis Chaitanya Ahuja and Louis-Philippe Morency. 2019. Multimodal Machine Learning: A Survey and Taxonomy. IEEE TPAMI 41 2 (2019) 423\u2013443. doi:10.1109\/TPAMI.2018.2798607","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Debojyoti Biswas Andrew Scouten Haitao Gong Feng Wang and Jelena Te\u0161i\u0107. 2026. MoPac+: Multimodal Modeling of the Pavement Cracks Using Hard-Example Mining and Context-Aware Feature Aggregation. Measurement 272 (2026) 120896. doi:10.1016\/j.measurement.2026.120896","DOI":"10.1016\/j.measurement.2026.120896"},{"key":"e_1_3_3_1_4_2","unstructured":"Alexey Bochkovskiy Chien-Yao Wang and Hong-Yuan\u00a0Mark Liao. 2020. YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv:2004.10934."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Alexander Buslaev Vladimir\u00a0I. Iglovikov Eugene Khvedchenya Alex Parinov Mikhail Druzhinin and Alexandr\u00a0A. Kalinin. 2020. Albumentations: Fast and Flexible Image Augmentations. Information 11 2 (2020) 125. doi:10.3390\/info11020125","DOI":"10.3390\/info11020125"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Sa\u00fal Cano-Ortiz Lara\u00a0Lloret Iglesias Pablo\u00a0Martinez Ruiz\u00a0del \u00c1rbol and Daniel Castro-Fresno. 2023. Improving detection of asphalt distresses with deep learning-based diffusion model for intelligent road maintenance. Developments in the Built Environment 17 (2023) 100315. doi:10.1016\/j.dibe.2023.100315","DOI":"10.1016\/j.dibe.2023.100315"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463615"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548399"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475661"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"e_1_3_3_1_13_2","unstructured":"Terrance DeVries and Graham\u00a0W. Taylor. 2017. Improved Regularization of Convolutional Neural Networks with Cutout. arXiv:1708.04552."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Yuchuan Du Ning Pan Zihao Xu Fuwen Deng Yu Shen and Hua Kang. 2021. Pavement distress detection and classification based on YOLO network. International Journal of Pavement Engineering 22 13 (2021) 1659\u20131672. doi:10.1080\/10298436.2020.1714047","DOI":"10.1080\/10298436.2020.1714047"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463650"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Zheng Ge Songtao Liu Feng Wang Zeming Li and Jian Sun. 2021. YOLOX: Exceeding YOLO Series in 2021. arXiv:2107.08430.","DOI":"10.1155\/2021\/9818014"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Zhibin Han Yutong Cai Anqi Liu Yiran Zhao and Ciyun Lin. 2024. MS-YOLOv8-Based Object Detection Method for Pavement Disease Recognition. Sensors 24 14 (2024) 4569. doi:10.3390\/s24144569","DOI":"10.3390\/s24144569"},{"key":"e_1_3_3_1_20_2","series-title":"Lecture Notes in Computer Science (LNCS)","first-page":"213","volume-title":"ACCV","author":"Hazirbas Caner","year":"2016","unstructured":"Caner Hazirbas, Lingni Ma, Csaba Domokos, and Daniel Cremers. 2016. FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-Based CNN Architecture. In ACCV(Lecture Notes in Computer Science (LNCS), Vol.\u00a010111). Springer, Cham, Switzerland, 213\u2013228."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Jiayv Jing Ling Ding Xu Yang Hang Cheng Yazhen Qiu Hainian Wang and Rauno Heikkil\u00e4. 2025. A hierarchical framework for three-dimensional pavement crack detection on point clouds with multi-scale abnormal region filtering and multimodal interaction fusion. Computer-Aided Civil and Infrastructure Engineering 40 31 (2025) 6577\u20136596. doi:10.1111\/mice.70167","DOI":"10.1111\/mice.70167"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Hong Lang Jinsong Qian Ye Yuan Jiang Chen Yingying Xing and Aidi Wang. 2024. Automatic Pixel-Level Segmentation of Multiple Pavement Distresses and Surface Design Features with PDSNet II. Journal of Computing in Civil Engineering 38 6 (2024) 04024028. doi:10.1061\/JCCEE5.CPENG-5894","DOI":"10.1061\/JCCEE5.CPENG-5894"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_3_1_25_2","volume-title":"Automated Pavement Distress Survey: 2D\/3D Laser Images","author":"Center MBRT","year":"2011","unstructured":"MBRT Center. 2011. Automated Pavement Distress Survey: 2D\/3D Laser Images. Technical Report. Mack-Blackwell Transportation Center."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Natalia Neverova Christian Wolf Graham\u00a0W. Taylor and Florian Nebout. 2016. ModDrop: Adaptive Multi-Modal Gesture Recognition. IEEE TPAMI 38 8 (2016) 1692\u20131706. doi:10.1109\/TPAMI.2015.2461544","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548018"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_3_1_29_2","unstructured":"Joseph Redmon and Ali Farhadi. 2018. YOLOv3: An Incremental Improvement. arXiv:1804.02767."},{"key":"e_1_3_3_1_30_2","first-page":"91","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems (NeurIPS). Curran Associates, Inc., Red Hook, NY, USA, 91\u201399."},{"key":"e_1_3_3_1_31_2","first-page":"568","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-Stream Convolutional Networks for Action Recognition in Videos. In Advances in Neural Information Processing Systems (NeurIPS). Curran Associates, Inc., Red Hook, NY, USA, 568\u2013576."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Weidong Song Zaiyan Zhang Bing Zhang Guohui Jia Hongbo Zhu and Jinhe Zhang. 2023. ISTD-PDS7: A Benchmark Dataset for Multi-Type Pavement Distress Segmentation from CCD Images in Complex Scenarios. Remote Sensing 15 7 (2023) 1750. doi:10.3390\/rs15071750","DOI":"10.3390\/rs15071750"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Yi Tan Ting Deng Jingyu Zhou and Zhixiang Zhou. 2024. LiDAR-Based Automatic Pavement Distress Detection and Management Using Deep Learning and BIM. Journal of Construction Engineering and Management 150 7 (2024) 04024069. doi:10.1061\/JCEMD4.COENG-14358","DOI":"10.1061\/JCEMD4.COENG-14358"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"e_1_3_3_1_36_2","unstructured":"Chien-Yao Wang Alexey Bochkovskiy and Hong-Yuan\u00a0Mark Liao. 2022. YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. arXiv:2207.02696."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Sicheng Wang Benxin Cai Weidong Wang Zheng Li Wenbo Hu Bin Yan and Xianhua Liu. 2024. Automated detection of pavement distress based on enhanced YOLOv8 and synthetic data with textured background modeling. Transportation Geotechnics 48 (2024) 101304. doi:10.1016\/j.trgeo.2024.101304","DOI":"10.1016\/j.trgeo.2024.101304"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Tian Wen Shuo Ding Hong Lang Jian\u00a0John Lu Ye Yuan Yichuan Peng Jiang Chen and Aidi Wang. 2023. Automated pavement distress segmentation on asphalt surfaces using a deep learning network. International Journal of Pavement Engineering 24 2 (2023) 2027414. doi:10.1080\/10298436.2022.2027414","DOI":"10.1080\/10298436.2022.2027414"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Zhengchao Xu Zhe Dai Zhaoyun Sun Chen Zuo Huansheng Song and Changwei Yuan. 2023. Enhancing Pavement Distress Detection Using a Morphological Constraints-Based Data Augmentation Method. Coatings 13 4 (2023) 764. doi:10.3390\/coatings13040764","DOI":"10.3390\/coatings13040764"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Allen Zhang Kelvin C.\u00a0P. Wang Yue Fei Yang Liu Cheng Chen Guangwei Yang Joshua\u00a0Qiang Li Enhui Yang and Shi Qiu. 2019. Automated Pixel-Level Pavement Crack Detection on 3D Asphalt Surfaces with a Recurrent Neural Network. Computer-Aided Civil and Infrastructure Engineering 34 3 (2019) 213\u2013229. doi:10.1111\/mice.12409","DOI":"10.1111\/mice.12409"},{"key":"e_1_3_3_1_42_2","unstructured":"Hongyi Zhang Moustapha Ciss\u00e9 Yann\u00a0N. Dauphin and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Tianjie Zhang Donglei Wang and Yang Lu. 2024. A data-centric strategy to improve performance of automatic pavement defects detection. Automation in Construction 160 (2024) 105334. doi:10.1016\/j.autcon.2024.105334","DOI":"10.1016\/j.autcon.2024.105334"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3805622.3810611","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:45:10Z","timestamp":1781538310000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810611"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":42,"alternative-id":["10.1145\/3805622.3810611","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810611","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}