{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T12:09:25Z","timestamp":1779365365326,"version":"3.53.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["L231013, L241056"],"award-info":[{"award-number":["L231013, L241056"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62376271, 62572059, 62365014, U22B2034"],"award-info":[{"award-number":["62376271, 62572059, 62365014, U22B2034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1007\/s00371-026-04486-y","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T10:40:59Z","timestamp":1778755259000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust detection in complex construction sites: HiPA-DETR with weather-aware and cross-domain generalization"],"prefix":"10.1007","volume":"42","author":[{"given":"Zenghuang","family":"Fu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinming","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiliang","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiguang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,14]]},"reference":[{"key":"4486_CR1","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.aei.2018.05.003","volume":"37","author":"W Fang","year":"2018","unstructured":"Fang, W., Ding, L., Zhong, B., Love, P., Luo, H.: Automated detection of workers and heavy equipment on construction sites: a convolutional neural network approach. Adv. Eng. Informatics 37, 139\u2013149 (2018)","journal-title":"Adv. Eng. Informatics"},{"key":"4486_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104499","volume":"142","author":"R Duan","year":"2022","unstructured":"Duan, R., Deng, H., Tian, M., Deng, Y., Lin, J.: Soda: a large-scale open site object detection dataset for deep learning in construction. Autom. Constr. 142, 104499 (2022)","journal-title":"Autom. Constr."},{"key":"4486_CR3","doi-asserted-by":"crossref","unstructured":"Wang, X., El-Gohary, N.: Few-shot object detection and attribute recognition from construction site images for improved field compliance. Autom. Constr. (2024)","DOI":"10.1016\/j.autcon.2024.105539"},{"key":"4486_CR4","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.autcon.2012.12.002","volume":"32","author":"M Memarzadeh","year":"2013","unstructured":"Memarzadeh, M., Golparvar-Fard, M., Carlos Niebles, J.: Automated 2d detection of construction equipment and workers from site video streams using histograms of oriented gradients and colors. Autom. Constr. 32, 24\u201337 (2013)","journal-title":"Autom. Constr."},{"key":"4486_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.103670","volume":"126","author":"H Son","year":"2021","unstructured":"Son, H., Kim, C.: Integrated worker detection and tracking for the safe operation of construction machinery. Autom. Constr. 126, 103670 (2021)","journal-title":"Autom. Constr."},{"key":"4486_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2020.103482","volume":"122","author":"X An","year":"2021","unstructured":"An, X., Zhou, L., Liu, Z., Wang, C., Li, P., Li, Z.: Dataset and benchmark for detecting moving objects in construction sites. Autom. Constr. 122, 103482 (2021)","journal-title":"Autom. Constr."},{"key":"4486_CR7","doi-asserted-by":"crossref","unstructured":"Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., Darrell, T.: Bdd100k: A diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 2636\u20132645 (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"4486_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108796","volume":"130","author":"R Qian","year":"2021","unstructured":"Qian, R., Lai, X., Li, X.: 3d object detection for autonomous driving: a survey. Pattern Recognit. 130, 108796 (2021)","journal-title":"Pattern Recognit."},{"key":"4486_CR9","doi-asserted-by":"publisher","first-page":"1699","DOI":"10.1109\/TIV.2022.3213796","volume":"8","author":"K Wang","year":"2023","unstructured":"Wang, K., Zhou, T., Li, X., Ren, F.: Performance and challenges of 3d object detection methods in complex scenes for autonomous driving. IEEE Trans. Intell. Veh. 8, 1699\u20131716 (2023)","journal-title":"IEEE Trans. Intell. Veh."},{"key":"4486_CR10","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"4486_CR11","unstructured":"Khanam, R., Hussain, M.: Yolov11: An overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725, (2024)"},{"key":"4486_CR12","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European conference on computer vision, pp. 213\u2013229 (2020) Springer","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"4486_CR13","doi-asserted-by":"crossref","unstructured":"Shehzadi, T., Hashmi, K.A., Stricker, D., Afzal, M.Z.: Sparse semi-detr: sparse learnable queries for semi-supervised object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5840\u20135850 (2024)","DOI":"10.1109\/CVPR52733.2024.00558"},{"key":"4486_CR14","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., Chen, J.: Detrs beat yolos on real-time object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"4486_CR15","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L., Shum, H.-Y.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. In: The Eleventh International Conference on Learning Representations, (2023)"},{"key":"4486_CR16","unstructured":"Tian, Y., Ye, Q., Doermann, D.: Yolov12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524, (2025)"},{"key":"4486_CR17","first-page":"523","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 523 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4486_CR18","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767, (2018)"},{"key":"4486_CR19","unstructured":"Bochkovskiy, A., Wang, C.-Y.,\u00a0Mark Liao, H.-Y.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, (2020)"},{"key":"4486_CR20","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Mark Liao, H.-Y.: Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"4486_CR21","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. In: International Conference on Learning Representations, (2021)"},{"key":"4486_CR22","doi-asserted-by":"crossref","unstructured":"Kim, H.-S., Seong, J., Jung, H.-J.: Optimal domain adaptive object detection with self-training and adversarial-based approach for construction site monitoring. Autom. Constr. (2024)","DOI":"10.1016\/j.autcon.2023.105244"},{"key":"4486_CR23","first-page":"6589","volume":"2","author":"A Pravallika","year":"2024","unstructured":"Pravallika, A., Hashmi, M.F., Gupta, A.: Deep learning frontiers in 3d object detection: a comprehensive review for autonomous driving. IEEE Access 2, 6589 (2024)","journal-title":"IEEE Access"},{"key":"4486_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"4486_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"1","key":"4486_CR26","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2020.2984801","volume":"38","author":"M Hnewa","year":"2020","unstructured":"Hnewa, M., Radha, H.: Object detection under rainy conditions for autonomous vehicles: a review of state-of-the-art and emerging techniques. IEEE Signal Process. Mag. 38(1), 53\u201367 (2020)","journal-title":"IEEE Signal Process. Mag."},{"key":"4486_CR27","doi-asserted-by":"crossref","unstructured":"Ul\u00a0Ain Tahir, N., Zhang, Z., Asim, M., Chen, J., ELAffendi, M.: Object detection in autonomous vehicles under adverse weather: a review of traditional and deep learning approaches. Algorithms, 17(3), 103, (2024)","DOI":"10.3390\/a17030103"},{"key":"4486_CR28","doi-asserted-by":"crossref","unstructured":"Choi, S., Jung, S., Yun, H., Kim, J.T., Kim, S., Choo, J.: Robustnet: Improving domain generalization in urban-scene segmentation via instance selective whitening. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11580\u201311590 (2021)","DOI":"10.1109\/CVPR46437.2021.01141"},{"issue":"6","key":"4486_CR29","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1007\/s11633-022-1339-y","volume":"19","author":"D Wu","year":"2022","unstructured":"Wu, D., Liao, M.-W., Zhang, W.-T., Wang, X.-G., Bai, X., Cheng, W.-Q., Liu, W.-Y.: Yolop: you only look once for panoptic driving perception. Mach. Intell. Res. 19(6), 550\u2013562 (2022)","journal-title":"Mach. Intell. Res."},{"key":"4486_CR30","doi-asserted-by":"crossref","unstructured":"Xie, Y., Wei, H., Liu, Z., Wang, X., Ji, X.: Synfog: A photo-realistic synthetic fog dataset based on end-to-end imaging simulation for advancing real-world defogging in autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21763\u201321772 (2024)","DOI":"10.1109\/CVPR52733.2024.02056"},{"key":"4486_CR31","doi-asserted-by":"crossref","unstructured":"Gupta, H., Kotlyar, O., Andreasson, H., Lilienthal, A.J.: Robust object detection in challenging weather conditions. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 7523\u20137532 (2024)","DOI":"10.1109\/WACV57701.2024.00735"},{"key":"4486_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, J., Luo, Z., Zhang, G., Zhang, X., Lu, S.: Da-detr: Domain adaptive detection transformer with information fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23787\u201323798 (2023)","DOI":"10.1109\/CVPR52729.2023.02278"},{"key":"4486_CR33","doi-asserted-by":"crossref","unstructured":"He, L., Wang, W., Chen, A., Sun, M., Kuo, C.-H., Todorovic, S.: Bidirectional alignment for domain adaptive detection with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18775\u201318785 (2023)","DOI":"10.1109\/ICCV51070.2023.01721"},{"key":"4486_CR34","doi-asserted-by":"crossref","unstructured":"Ogino, Y., Shoji, Y., Toizumi, T., Ito, A.: Erup-yolo: Enhancing object detection robustness for adverse weather condition by unified image-adaptive processing. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 8597\u20138605. IEEE, (2025)","DOI":"10.1109\/WACV61041.2025.00833"},{"key":"4486_CR35","unstructured":"Kenk, M.A., Hassaballah, M.: Dawn: vehicle detection in adverse weather nature dataset. arXiv preprint arXiv:2008.05402, (2020)"},{"key":"4486_CR36","doi-asserted-by":"crossref","unstructured":"Sakaridis, C., Dai, D., Van Gool, L.: Acdc: The adverse conditions dataset with correspondences for semantic driving scene understanding. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10765\u201310775 (2021)","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"4486_CR37","unstructured":"Chu, C., Zhmoginov, A., Sandler, M.: Cyclegan, a master of steganography. NIPS 2017 Workshop Machine Deception. arXiv preprint arXiv:1712.02950, (2017)"},{"key":"4486_CR38","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.-Y., et al.: Segment anything. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"4486_CR39","unstructured":"Meng, W., Luo, Y., Li, X., Jiang, D., Zhang, Z.: Polaformer: Polarity-aware linear attention for vision transformers. In: The Thirteenth International Conference on Learning Representations, (2025)"},{"key":"4486_CR40","doi-asserted-by":"crossref","unstructured":"Feng, Y., Huang, J., Du, S., Ying, S., Yong, J.-H., Li, Y., Ding, G., Ji, R., Gao, Y.: Hyper-yolo: When visual object detection meets hypergraph computation. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)","DOI":"10.1109\/TPAMI.2024.3524377"},{"key":"4486_CR41","doi-asserted-by":"crossref","unstructured":"Ma, X., Dai, X., Bai, Y., Wang, Y., Fu, Y.: Rewrite the stars. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5694\u20135703 (2024)","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"4486_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, B., Yu, S., Ma, W., Yu, M., Mei, S., Wang, A.,\u00a0He, J., Yuille, A., Kortylewski, A.: Ood-cv: A benchmark for robustness to out-of-distribution shifts of individual nuisances in natural images. In: European conference on computer vision, pp. 163\u2013180. Springer (2022)","DOI":"10.1007\/978-3-031-20074-8_10"},{"key":"4486_CR43","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in neural information processing systems, vol. 30, (2017)"},{"key":"4486_CR44","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778, (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4486_CR45","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K.,\u00a0Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp. 248\u2013255. Ieee, (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"4486_CR46","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Yeh, I.-H., Mark\u00a0Liao, H.-Y.: Yolov9: Learning what you want to learn using programmable gradient information. In: European conference on computer vision, pp. 1\u201321. Springer, (2024)","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"4486_CR47","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"4486_CR48","unstructured":"Peng, Y., Li, H., Wu, P., Zhang, Y., Sun, X., Wu, F.: D-fine: redefine regression task in detrs as fine-grained distribution refinement. arXiv preprint arXiv:2410.13842, (2024)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04486-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-026-04486-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04486-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T11:42:59Z","timestamp":1779363779000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-026-04486-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":48,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["4486"],"URL":"https:\/\/doi.org\/10.1007\/s00371-026-04486-y","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"27 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"295"}}