{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T02:11:42Z","timestamp":1768615902704,"version":"3.49.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032144942","type":"print"},{"value":"9783032144959","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-14495-9_33","type":"book-chapter","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T15:22:35Z","timestamp":1768576955000},"page":"429-440","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Infrastructure Monitoring with\u00a0Calibrated Vision Language Model Ensembles: A Graffiti Detection Case Study"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2560-9401","authenticated-orcid":false,"given":"Gaetano","family":"Evangelista","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5993-0196","authenticated-orcid":false,"given":"Houston","family":"Lucas","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7609-8645","authenticated-orcid":false,"given":"Richard","family":"Kelley","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,17]]},"reference":[{"key":"33_CR1","unstructured":"American Public Transportation Association: 2023 public transportation fact book. Technical report, APTA (2023). https:\/\/www.apta.com\/wp-content\/uploads\/APTA-2023-Public-Transportation-Fact-Book.pdf"},{"key":"33_CR2","series-title":"Lecture Notes in Business Information Processing","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/978-3-030-15154-6_7","volume-title":"Information Technology for Management: Emerging Research and Applications","author":"V Carchiolo","year":"2019","unstructured":"Carchiolo, V., Loria, M.P., Malgeri, M., Modica, P.W., Toja, M.: An adaptive algorithm for geofencing. In: Ziemba, E. (ed.) AITM\/ISM -2018. LNBIP, vol. 346, pp. 115\u2013135. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-15154-6_7"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, T., Song, L., Ge, Y., Liu, W., Wang, X., Huang, W.: YOLO-world: real-time open-vocabulary object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16901\u201316911 (2024)","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"33_CR4","unstructured":"DeepSeek-AI: DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"33_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Douglas, D.H., Peucker, T.K.: Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica: Int. J. Geographic Inf. Geovisualization 10(2), 112\u2013122 (1973)","DOI":"10.3138\/FM57-6770-U75U-7727"},{"issue":"5","key":"33_CR7","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1177\/0018720817690639","volume":"59","author":"J Engstr\u00f6m","year":"2017","unstructured":"Engstr\u00f6m, J., Markkula, G., Victor, T., Merat, N.: Effects of cognitive load on driving performance: the cognitive control hypothesis. Hum. Factors 59(5), 734\u2013764 (2017). https:\/\/doi.org\/10.1177\/0018720817690639","journal-title":"Hum. Factors"},{"key":"33_CR8","doi-asserted-by":"publisher","unstructured":"Garc\u00eda-Mendoza, C.V., Gambino, O.J., Villarreal-Cervantes, M.G., Calvo, H.: Evolutionary optimization of ensemble learning to determine sentiment polarity in an unbalanced multiclass corpus. Entropy 22(9), 1020 (2020). https:\/\/doi.org\/10.3390\/e22091020","DOI":"10.3390\/e22091020"},{"key":"33_CR9","unstructured":"Gemma Team, Mesnard, T., et\u00a0al.: Gemma: open models based on Gemini research and technology. arXiv preprint arXiv:2403.08295 (2024)"},{"key":"33_CR10","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"33_CR11","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"issue":"2","key":"33_CR12","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.aei.2015.01.008","volume":"29","author":"C Koch","year":"2015","unstructured":"Koch, C., Georgieva, K., Kasireddy, V., Akinci, B., Fieguth, P.: A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure. Adv. Eng. Inform. 29(2), 196\u2013210 (2015). https:\/\/doi.org\/10.1016\/j.aei.2015.01.008","journal-title":"Adv. Eng. Inform."},{"key":"33_CR13","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023). https:\/\/arxiv.org\/abs\/2304.08485"},{"key":"33_CR14","doi-asserted-by":"publisher","unstructured":"Niculescu-Mizil, A., Caruana, R.: Predicting good probabilities with supervised learning. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 625\u2013632 (2005). https:\/\/doi.org\/10.1145\/1102351.1102430","DOI":"10.1145\/1102351.1102430"},{"issue":"4","key":"33_CR15","doi-asserted-by":"publisher","first-page":"207","DOI":"10.3390\/digital2040017","volume":"2","author":"J Nikolenko","year":"2022","unstructured":"Nikolenko, J., Kent, C., Rueckert, D., Dylov, D.V.: Synthetic image data and its use in computer vision. Digital 2(4), 207\u2013233 (2022). https:\/\/doi.org\/10.3390\/digital2040017","journal-title":"Digital"},{"key":"33_CR16","doi-asserted-by":"publisher","unstructured":"Rwigema, J., Choi, H., Kim, T.: A differential evolution approach to optimize weights of dynamic time warping for multi-sensor based gesture recognition. Sensors 19(5), 1007 (2019). https:\/\/doi.org\/10.3390\/s19051007","DOI":"10.3390\/s19051007"},{"issue":"4","key":"33_CR17","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1023\/A:1008202821328","volume":"11","author":"R Storn","year":"1997","unstructured":"Storn, R., Price, K.: Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim. 11(4), 341\u2013359 (1997). https:\/\/doi.org\/10.1023\/A:1008202821328","journal-title":"J. Global Optim."},{"key":"33_CR18","doi-asserted-by":"publisher","unstructured":"Taherizadeh, S., Jones, A., Taylor, I., Zhao, Z., Stankovski, V.: Monitoring self-adaptive applications within edge computing frameworks: a state-of-the-art review. J. Syst. Softw. 136, 19\u201338 (2018). https:\/\/doi.org\/10.1016\/j.jss.2017.10.033","DOI":"10.1016\/j.jss.2017.10.033"},{"key":"33_CR19","unstructured":"Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks (2020). https:\/\/arxiv.org\/abs\/1905.11946"},{"key":"33_CR20","unstructured":"Tu, W., Deng, W., Campbell, D., Gould, S., Gedeon, T.: An empirical study into what matters for calibrating vision-language models (2024). https:\/\/arxiv.org\/abs\/2402.07417"},{"key":"33_CR21","unstructured":"Ultralytics: YOLO documentation (2023). https:\/\/docs.ultralytics.com\/"},{"key":"33_CR22","unstructured":"Viso.ai: Vision language models (VLMs): Exploring multimodal AI (2025). https:\/\/viso.ai\/deep-learning\/vision-language-models\/"},{"issue":"10","key":"33_CR23","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1111\/mice.12297","volume":"32","author":"A Zhang","year":"2017","unstructured":"Zhang, A., et al.: Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network. Comput.-Aided Civil Infrastruct. Eng. 32(10), 805\u2013819 (2017). https:\/\/doi.org\/10.1111\/mice.12297","journal-title":"Comput.-Aided Civil Infrastruct. Eng."},{"issue":"1","key":"33_CR24","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1007\/s00521-016-2342-4","volume":"28","author":"Y Zhang","year":"2016","unstructured":"Zhang, Y., Liu, B., Cai, J., Zhang, S.: Ensemble weighted extreme learning machine for imbalanced data classification based on differential evolution. Neural Comput. Appl. 28(1), 259\u2013267 (2016). https:\/\/doi.org\/10.1007\/s00521-016-2342-4","journal-title":"Neural Comput. Appl."}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-14495-9_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T15:22:39Z","timestamp":1768576959000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-14495-9_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032144942","9783032144959"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-14495-9_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"17 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Las Vegas, NV","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isvc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isvc.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}