{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:09:19Z","timestamp":1784131759984,"version":"3.55.0"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729850","type":"print"},{"value":"9783031729867","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72986-7_2","type":"book-chapter","created":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T05:04:16Z","timestamp":1730437456000},"page":"19-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["SKYSCENES: A Synthetic Dataset for\u00a0Aerial Scene Understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2194-3115","authenticated-orcid":false,"given":"Sahil","family":"Khose","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7850-5936","authenticated-orcid":false,"given":"Anisha","family":"Pal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3933-3893","authenticated-orcid":false,"given":"Aayushi","family":"Agarwal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5210-0722","authenticated-orcid":false,"family":"Deepanshi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1971-1606","authenticated-orcid":false,"given":"Judy","family":"Hoffman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7555-3644","authenticated-orcid":false,"given":"Prithvijit","family":"Chattopadhyay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,2]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Cai, W., Jin, K., Hou, J., Guo, C., Wu, L., Yang, W.: Vdd: varied drone dataset for semantic segmentation (2023)","DOI":"10.2139\/ssrn.4902735"},{"key":"2_CR2","doi-asserted-by":"publisher","unstructured":"Chauhan, A., et al.: Chapter 10 - earth observation applications for urban mapping and monitoring: research prospects, opportunities and challenges. In: Kumar, A., Srivastava, P.K., Saikia, P., Mall, R.K. (eds.) Earth Observation in Urban Monitoring, pp. 197\u2013229. Earth Observation, Elsevier (2024). https:\/\/doi.org\/10.1016\/B978-0-323-99164-3.00007-0. https:\/\/www.sciencedirect.com\/science\/article\/pii\/B9780323991643000070","DOI":"10.1016\/B978-0-323-99164-3.00007-0"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs (2017)","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"2_CR4","doi-asserted-by":"publisher","unstructured":"Chen, L., Liu, F., Zhao, Y., Wang, W., Yuan, X., Zhu, J.: Valid: a comprehensive virtual aerial image dataset. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 2009\u20132016 (2020). https:\/\/doi.org\/10.1109\/ICRA40945.2020.9197186","DOI":"10.1109\/ICRA40945.2020.9197186"},{"key":"2_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/978-3-030-03398-9_30","volume-title":"Pattern Recognition and Computer Vision","author":"Yu Chen","year":"2018","unstructured":"Chen, Yu., Wang, Y., Lu, P., Chen, Y., Wang, G.: Large-scale structure from motion with semantic constraints of aerial images. In: Lai, J.H., et al. (eds.) PRCV 2018. LNCS, vol. 11256, pp. 347\u2013359. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-03398-9_30"},{"key":"2_CR6","doi-asserted-by":"publisher","first-page":"144064","DOI":"10.1109\/ACCESS.2020.3012417","volume":"8","author":"CY Chiang","year":"2020","unstructured":"Chiang, C.Y., Barnes, C., Angelov, P., Jiang, R.: Deep learning-based automated forest health diagnosis from aerial images. IEEE Access 8, 144064\u2013144076 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3012417","journal-title":"IEEE Access"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Demir, I., et\u00a0al.: Deepglobe 2018: a challenge to parse the earth through satellite images. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 172\u2013172 (2018)","DOI":"10.1109\/CVPRW.2018.00031"},{"key":"2_CR9","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: Carla: an open urban driving simulator. In: Conference on Robot Learning, pp. 1\u201316. PMLR (2017)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Du, D., et al.: The unmanned aerial vehicle benchmark: object detection and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 370\u2013386 (2018)","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Fonder, M., Droogenbroeck, M.V.: Mid-air: a multi-modal dataset for extremely low altitude drone flights. In: Conference on Computer Vision and Pattern Recognition Workshop (CVPRW) (2019)","DOI":"10.1109\/CVPRW.2019.00081"},{"key":"2_CR12","doi-asserted-by":"publisher","unstructured":"Frueh, C., Sammon, R., Zakhor, A.: Automated texture mapping of 3d city models with oblique aerial imagery. In: Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004, pp. 396\u2013403 (2004). https:\/\/doi.org\/10.1109\/TDPVT.2004.1335266","DOI":"10.1109\/TDPVT.2004.1335266"},{"key":"2_CR13","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":"2_CR14","doi-asserted-by":"crossref","unstructured":"Hoyer, L., Dai, D., Gool, L.V.: Daformer: improving network architectures and training strategies for domain-adaptive semantic segmentation (2022)","DOI":"10.1109\/CVPR52688.2022.00969"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Hoyer, L., Dai, D., Gool, L.V.: Hrda: context-aware high-resolution domain-adaptive semantic segmentation (2022)","DOI":"10.1007\/978-3-031-20056-4_22"},{"key":"2_CR16","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models (2021)"},{"key":"2_CR17","unstructured":"Institute of Computer Graphics and Vision, Graz University of Technology: Semantic drone dataset. http:\/\/dronedataset.icg.tugraz.at"},{"key":"2_CR18","doi-asserted-by":"publisher","unstructured":"Kedys, J., Tchappi, I., Najjar, A.: Uavs for disaster management - an exploratory review. Procedia Comput. Sci. 231, 129\u2013136 (2024). https:\/\/doi.org\/10.1016\/j.procs.2023.12.184. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050923021968","DOI":"10.1016\/j.procs.2023.12.184"},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"Lin, L., Liu, Y., Hu, Y., Yan, X., Xie, K., Huang, H.: Capturing, reconstructing, and simulating: the urbanscene3d dataset. In: ECCV 2022, pp. 93\u2013109. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20074-8_6","DOI":"10.1007\/978-3-031-20074-8_6"},{"key":"2_CR20","doi-asserted-by":"publisher","unstructured":"Liu, T., Yang, X.: Monitoring land changes in an urban area using satellite imagery, gis and landscape metrics. Appl. Geogr. 56, 42\u201354 (2015). https:\/\/doi.org\/10.1016\/j.apgeog.2014.10.002. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0143622814002306","DOI":"10.1016\/j.apgeog.2014.10.002"},{"issue":"4","key":"2_CR21","doi-asserted-by":"publisher","first-page":"7981","DOI":"10.1109\/LRA.2021.3101879","volume":"6","author":"R Lopez-Campos","year":"2021","unstructured":"Lopez-Campos, R., Martinez-Carranza, J.: Espada: extended synthetic and photogrammetric aerial-image dataset. IEEE Rob. Autom. Lett. 6(4), 7981\u20137988 (2021). https:\/\/doi.org\/10.1109\/LRA.2021.3101879","journal-title":"IEEE Rob. Autom. Lett."},{"key":"2_CR22","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.isprsjprs.2020.05.009","volume":"165","author":"Y Lyu","year":"2020","unstructured":"Lyu, Y., Vosselman, G., Xia, G.S., Yilmaz, A., Yang, M.Y.: Uavid: a semantic segmentation dataset for UAV imagery. ISPRS J. Photogramm. Remote. Sens. 165, 108\u2013119 (2020)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Maheshwari, H., Liu, Y.C., Kira, Z.: Missing modality robustness in semi-supervised multi-modal semantic segmentation (2023)","DOI":"10.1109\/WACV57701.2024.00106"},{"key":"2_CR24","doi-asserted-by":"publisher","unstructured":"Morgan, G.R., Wang, C., Li, Z., Schill, S.R., Morgan, D.R.: Deep learning of high-resolution aerial imagery for coastal marsh change detection: a comparative study. ISPRS Int. J. Geo-Inf. 11(2) (2022). https:\/\/doi.org\/10.3390\/ijgi11020100. https:\/\/www.mdpi.com\/2220-9964\/11\/2\/100","DOI":"10.3390\/ijgi11020100"},{"key":"2_CR25","doi-asserted-by":"publisher","unstructured":"Munawar, H.S., Ullah, F., Qayyum, S., Khan, S.I., Mojtahedi, M.: Uavs in disaster management: application of integrated aerial imagery and convolutional neural network for flood detection. Sustainability 13(14) (2021). https:\/\/doi.org\/10.3390\/su13147547. https:\/\/www.mdpi.com\/2071-1050\/13\/14\/7547","DOI":"10.3390\/su13147547"},{"key":"2_CR26","doi-asserted-by":"publisher","unstructured":"Neuhold, G., Ollmann, T., Bul\u00f2, S.R., Kontschieder, P.: The mapillary vistas dataset for semantic understanding of street scenes. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5000\u20135009 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.534","DOI":"10.1109\/ICCV.2017.534"},{"key":"2_CR27","unstructured":"Nguyen, K., et al.: The state of aerial surveillance: a survey (2022)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Nigam, I., Huang, C., Ramanan, D.: Ensemble knowledge transfer for semantic segmentation. In: Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision, pp. 916\u2013924. IEEE (2018)","DOI":"10.1109\/WACV.2018.00168"},{"key":"2_CR29","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision (2024)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Otal, H.T., Zavar, E., Binder, S.B., Greer, A., Canbaz, M.A.: Harnessing deep learning and satellite imagery for post-buyout land cover mapping (2024)","DOI":"10.1109\/CAI59869.2024.00130"},{"key":"2_CR31","unstructured":"Peng, X., et al.: Visda: the visual domain adaptation challenge. In: IEEE International Conference on Computer Vision, pp. 1685\u20131692 (2017)"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Prokaj, J., Medioni, G.: Persistent tracking for wide area aerial surveillance. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.155"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Rahnemoonfar, M., Chowdhury, T., Sarkar, A., Varshney, D., Yari, M., Murphy, R.: Floodnet: a high resolution aerial imagery dataset for post flood scene understanding (2020)","DOI":"10.1109\/ACCESS.2021.3090981"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Rizzoli, G., Barbato, F., Caligiuri, M., Zanuttigh, P.: Syndrone\u2013multi-modal uav dataset for urban scenarios. arXiv preprint arXiv:2308.10491 (2023)","DOI":"10.1109\/ICCVW60793.2023.00235"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.M.: The synthia dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3234\u20133243 (2016)","DOI":"10.1109\/CVPR.2016.352"},{"key":"2_CR36","doi-asserted-by":"publisher","unstructured":"Rottensteiner, F., et al.: The isprs benchmark on urban object classification and 3d building reconstruction. ISPRS Ann. Photogram. Remote Sens. Spatial Inf. Sci. I-3 (2012).https:\/\/doi.org\/10.5194\/isprsannals-I-3-293-2012","DOI":"10.5194\/isprsannals-I-3-293-2012"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Sakaridis, C., Dai, D., Van\u00a0Gool, L.: Guided curriculum model adaptation and uncertainty-aware evaluation for semantic nighttime image segmentation. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00747"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Sankaranarayanan, S., Balaji, Y., Castillo, C.D., Chellappa, R.: Generate to adapt: aligning domains using generative adversarial networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00887"},{"key":"2_CR39","unstructured":"Scanlon, M.: Semantic Annotation of Aerial Images using Deep Learning, Transfer Learning, and Synthetic Training Data. Ph.D. thesis, University of Galway (09 2018)"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Shah, S., Dey, D., Lovett, C., Kapoor, A.: Airsim: high-fidelity visual and physical simulation for autonomous vehicles. In: Field and Service Robotics (2017). https:\/\/arxiv.org\/abs\/1705.05065","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Sun, T., et al.: Shift: a synthetic driving dataset for continuous multi-task domain adaptation (2022)","DOI":"10.1109\/CVPR52688.2022.02068"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Testolina, P., Barbato, F., Michieli, U., Giordani, M., Zanuttigh, P., Zorzi, M.: Selma: semantic large-scale multimodal acquisitions in variable weather, daytime and viewpoints (2022)","DOI":"10.1109\/TITS.2023.3257086"},{"key":"2_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2019.111322","volume":"237","author":"XY Tong","year":"2020","unstructured":"Tong, X.Y., et al.: Land-cover classification with high-resolution remote sensing images using transferable deep models. Remote Sens. Environ. 237, 111322 (2020)","journal-title":"Remote Sens. Environ."},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Tartanair: a dataset to push the limits of visual slam (2020). https:\/\/arxiv.org\/abs\/2003.14338","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Wei, Z., et al.: Stronger, fewer, & superior: harnessing vision foundation models for domain generalized semantic segmentation (2024)","DOI":"10.1109\/CVPR52733.2024.02704"},{"key":"2_CR46","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: 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":"2_CR48","doi-asserted-by":"publisher","unstructured":"Zhu, P., et al.: Detection and tracking meet drones challenge. IEEE Trans. Pattern Anal. Mach. Intell. (2021). https:\/\/doi.org\/10.1109\/TPAMI.2021.3119563","DOI":"10.1109\/TPAMI.2021.3119563"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72986-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T05:04:43Z","timestamp":1730437483000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72986-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,2]]},"ISBN":["9783031729850","9783031729867"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72986-7_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,2]]},"assertion":[{"value":"2 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}