{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:44:27Z","timestamp":1780443867835,"version":"3.54.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032050595","type":"print"},{"value":"9783032050601","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"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\/978-3-032-05060-1_17","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T07:58:06Z","timestamp":1758009486000},"page":"195-206","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging Vision-Language Models for Improving Detection of Obstacles on Railway Tracks"],"prefix":"10.1007","author":[{"given":"Vincenzo","family":"Carletti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Greco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessia","family":"Saggese","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Camilla","family":"Spingola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruno","family":"Vento","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Carletti, V., et al.: Combining deep networks with model-based scene segmentation for reliably detecting rocks on railway tracks. In: 2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI), pp. 524\u2013529. IEEE (2024)","DOI":"10.1109\/RTSI61910.2024.10761174"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Carletti, V., et al.: Onboard vision based system for automatic rock detection on rail tracks. In: International Conference on Pattern Recognition, pp. 263\u2013274. Springer (2024)","DOI":"10.1007\/978-3-031-88223-4_19"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Carletti, V., Greco, A., Saggese, A., Vento, B.: Enhancing safety by obstacle detection at railway level crossings. In: 2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI), pp. 482\u2013487. IEEE (2024)","DOI":"10.1109\/RTSI61910.2024.10761238"},{"key":"17_CR4","doi-asserted-by":"publisher","DOI":"10.1145\/3721291","volume-title":"Video fire recognition using zero-shot vision-language models guided by a task-aware object detector","author":"D Gragnaniello","year":"2025","unstructured":"Gragnaniello, D., Greco, A., Sansone, C., Vento, B.: Video fire recognition using zero-shot vision-language models guided by a task-aware object detector. ACM Trans. Multimedia Comput., Communications and Applications (2025)"},{"key":"17_CR5","unstructured":"Harb, J., et al.: FRSign: A large-scale traffic light dataset for autonomous trains. arXiv preprint arXiv:2002.05665 (2020)"},{"key":"17_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2022.111277","volume":"196","author":"D He","year":"2022","unstructured":"He, D.: Urban rail transit obstacle detection based on improved R-CNN. Measurement 196, 111277 (2022)","journal-title":"Measurement"},{"issue":"6","key":"17_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3295748","volume":"51","author":"MZ Hossain","year":"2019","unstructured":"Hossain, M.Z., Sohel, F., Shiratuddin, M.F., Laga, H.: A comprehensive survey of deep learning for image captioning. ACM Comput. Surv. (CsUR) 51(6), 1\u201336 (2019)","journal-title":"ACM Comput. Surv. (CsUR)"},{"key":"17_CR8","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: International conference on machine learning, pp. 19730\u201319742. PMLR (2023)"},{"issue":"8","key":"17_CR9","doi-asserted-by":"publisher","first-page":"5705","DOI":"10.1007\/s10462-020-09832-7","volume":"53","author":"S Manmadhan","year":"2020","unstructured":"Manmadhan, S., Kovoor, B.C.: Visual question answering: a state-of-the-art review. Artif. Intell. Rev. 53(8), 5705\u20135745 (2020). https:\/\/doi.org\/10.1007\/s10462-020-09832-7","journal-title":"Artif. Intell. Rev."},{"issue":"6","key":"17_CR10","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR11","doi-asserted-by":"publisher","unstructured":"Risti\u0107-Durrant, D., et al.: Artificial intelligence for obstacle detection in railways: project SMART and beyond. In: Bernardi, S., et al. (eds.) EDCC 2020. CCIS, vol. 1279, pp. 44\u201355. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58462-7_4","DOI":"10.1007\/978-3-030-58462-7_4"},{"key":"17_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-assisted Intervention \u2014 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"17_CR13","doi-asserted-by":"publisher","first-page":"77656","DOI":"10.1109\/ACCESS.2018.2883704","volume":"6","author":"Z Wang","year":"2018","unstructured":"Wang, Z., Wu, X., Yu, G., Li, M.: Efficient rail area detection using convolutional neural network. IEEE Access 6, 77656\u201377664 (2018)","journal-title":"IEEE Access"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Xu, Y., Gao, C., Yuan, L., Tang, S., Wei, G.: Real-time obstacle detection over rails using deep convolutional neural network. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp. 1007\u20131012. IEEE (2019)","DOI":"10.1109\/ITSC.2019.8917091"},{"issue":"6","key":"17_CR15","doi-asserted-by":"publisher","first-page":"1916","DOI":"10.3390\/s18061916","volume":"18","author":"T Ye","year":"2018","unstructured":"Ye, T., Wang, B., Song, P., Li, J.: Automatic railway traffic object detection system using feature fusion refine neural network under shunting mode. Sensors 18(6), 1916 (2018)","journal-title":"Sensors"},{"key":"17_CR16","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","volume":"129","author":"C Yu","year":"2021","unstructured":"Yu, C., et al.: BiSeNet V2: bilateral network with guided aggregation for real-time semantic segmentation. Int. J. Comput. Vision 129, 3051\u20133068 (2021)","journal-title":"Int. J. Comput. Vision"},{"issue":"6","key":"17_CR17","doi-asserted-by":"publisher","first-page":"1747","DOI":"10.1016\/j.cja.2020.02.024","volume":"33","author":"L Yundong","year":"2020","unstructured":"Yundong, L.: Multi-block SSD based on small object detection for UAV railway scene surveillance. Chin. J. Aeronaut. 33(6), 1747\u20131755 (2020)","journal-title":"Chin. J. Aeronaut."},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Zendel, O., et al.: RailSem19: a dataset for semantic rail scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00161"},{"issue":"1","key":"17_CR19","doi-asserted-by":"publisher","first-page":"662","DOI":"10.3390\/app13010662","volume":"13","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Li, K., Zhang, G., Zhu, Z., Wang, P.: DFA-UNet: efficient railroad image segmentation. Appl. Sci. 13(1), 662 (2023)","journal-title":"Appl. Sci."},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: Vision language models in autonomous driving: a survey and outlook. IEEE Trans. Intell. Veh. (2024)","DOI":"10.1109\/TIV.2024.3402136"}],"container-title":["Lecture Notes in Computer Science","Computer Analysis of Images and Patterns"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05060-1_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T07:58:11Z","timestamp":1758009491000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05060-1_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"ISBN":["9783032050595","9783032050601"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05060-1_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"17 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Analysis of Images and Patterns","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Las Palmas de Gran Canaria","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"22 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/caip2025.com","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}