{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:24:56Z","timestamp":1767324296945,"version":"3.48.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032128393","type":"print"},{"value":"9783032128409","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\/978-3-032-12840-9_13","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:22:05Z","timestamp":1767324125000},"page":"186-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Road Obstacle Video Segmentation"],"prefix":"10.1007","author":[{"given":"Shyam Nandan","family":"Rai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shyamgopal","family":"Karthik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mariana-Iuliana","family":"Georgescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barbara","family":"Caputo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlo","family":"Masone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeynep","family":"Akata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"13_CR1","unstructured":"Ackermann, J., Sakaridis, C., Yu, F.: Maskomaly: zero-shot mask anomaly segmentation. In: British Machine Vision Conference (2023)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Ahn, S., Jo, Y., Lee, K., Park, S.: Videopatchcore: an effective method to memorize normality for video anomaly detection. In: Proceedings of the Asian Conference on Computer Vision (ACCV), pp. 2179\u20132195 (2024)","DOI":"10.1007\/978-981-96-0908-6_18"},{"key":"13_CR3","unstructured":"Bevandi\u0107, P., Kre\u0161o, I., Or\u0161i\u0107, M., \u0160egvi\u0107, S.: Discriminative out-of-distribution detection for semantic segmentation. CoRR abs\/1808.07703 (2018)"},{"issue":"11","key":"13_CR4","doi-asserted-by":"publisher","first-page":"3119","DOI":"10.1007\/s11263-021-01511-6","volume":"129","author":"H Blum","year":"2021","unstructured":"Blum, H., Sarlin, P.E., Nieto, J., Siegwart, R., Cadena, C.: The Fishyscapes benchmark: measuring blind spots in semantic segmentation. Int. J. Comput. Vis. 129(11), 3119\u20133135 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"13_CR5","unstructured":"Chan, R., et al.: SegmentMeIfYouCan: a benchmark for anomaly segmentation. In: Advances in Neural Information Processing Systems (2021)"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: European Conference on Computer Vision, pp. 833\u2013851 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"13_CR7","unstructured":"Cheng, B., Choudhuri, A., Misra, I., Kirillov, A., Girdhar, R., Schwing, A.G.: Mask2former for video instance segmentation. CoRR abs\/2112.10764 (2021). https:\/\/arxiv.org\/abs\/2112.10764"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1280\u20131289 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"13_CR10","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: Advances in Neural Information Processing Systems (2021)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The Cityscapes dataset for semantic urban scene understanding. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Di\u00a0Biase, G., Blum, H., Siegwart, R., Cadena, C.: Pixel-wise anomaly detection in complex driving scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 16913\u201316922 (2021)","DOI":"10.1109\/CVPR46437.2021.01664"},{"key":"13_CR13","unstructured":"Fort, S., Hu, H., Lakshminarayanan, B.: Deep ensembles: a loss landscape perspective. arXiv preprint arXiv:1912.02757 (2019)"},{"key":"13_CR14","unstructured":"Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning (2016)"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Grci\u0107, M., Bevandi\u0107, P., \u0160egvi\u0107, S.: Dense open-set recognition with synthetic outliers generated by real NVP. In: International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (2021)","DOI":"10.5220\/0010260701330143"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Grcic, M., Saric, J., Segvic, S.: On advantages of mask-level recognition for outlier-aware segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 2937\u20132947 (2023)","DOI":"10.1109\/CVPRW59228.2023.00295"},{"key":"13_CR17","doi-asserted-by":"publisher","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18\u201324 June 2022, pp. 15979\u201315988. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01553","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"13_CR18","unstructured":"Hendrycks, D., et al.: Improving and assessing anomaly detectors for large-scale settings (2022)"},{"key":"13_CR19","unstructured":"Hendrycks, D., et al.: Scaling out-of-distribution detection for real-world settings. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesv\u00e1ri, C., Niu, G., Sabato, S. (eds.) International Conference on Machine Learning, ICML 2022, 17\u201323 July 2022, Baltimore, Maryland, USA. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 8759\u20138773. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/hendrycks22a.html"},{"key":"13_CR20","unstructured":"Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: International Conference on Learning Representations (2017)"},{"issue":"10","key":"13_CR21","doi-asserted-by":"publisher","first-page":"2702","DOI":"10.1109\/TPAMI.2019.2926463","volume":"42","author":"X Huang","year":"2020","unstructured":"Huang, X., Wang, P., Cheng, X., Zhou, D., Geng, Q., Yang, R.: The apolloscape open dataset for autonomous driving and its application. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2702\u20132719 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2019.2926463","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Jung, S., Lee, J., Gwak, D., Choi, S., Choo, J.: Standardized max logits: a simple yet effective approach for identifying unexpected road obstacles in urban-scene segmentation. In: International Conference on Computer Vision, pp. 15405\u201315414 (2021)","DOI":"10.1109\/ICCV48922.2021.01514"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5168\u20135177 (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Lis, K., Nakka, K., Fua, P., Salzmann, M.: Detecting the unexpected via image resynthesis. In: International Conference on Computer Vision, pp. 2152\u20132161 (2019)","DOI":"10.1109\/ICCV.2019.00224"},{"key":"13_CR26","unstructured":"Liu, W., Wang, X., Owens, J., Li, Y.: Energy-based out-of-distribution detection. In: Advances in Neural Information Processing Systems (2020)"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"13_CR29","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1007\/978-3-031-26348-4_28","volume-title":"ACCV 2022, Part V","author":"K Maag","year":"2022","unstructured":"Maag, K., Chan, R., Uhlemeyer, S., Kowol, K., Gottschalk, H.: Two video data sets for tracking and retrieval of out of distribution objects. In: Wang, L., Gall, J., Chin, T., Sato, I., Chellappa, R. (eds.) ACCV 2022, Part V. LNCS, vol. 13845, pp. 476\u2013494. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-26348-4_28"},{"key":"13_CR30","doi-asserted-by":"publisher","unstructured":"Miao, J., Wei, Y., Wu, Y., Liang, C., Li, G., Yang, Y.: VSPW: a large-scale dataset for video scene parsing in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, 19\u201325 June 2021, pp. 4133\u20134143. Computer Vision Foundation\/IEEE (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00412. https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/html\/Miao_VSPW_A_Large-scale_Dataset_for_Video_Scene_Parsing_in_the_CVPR_2021_paper.html","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"13_CR31","unstructured":"Mukhoti, J., Gal, Y.: Evaluating Bayesian deep learning methods for semantic segmentation. CoRR abs\/1811.12709 (2018)"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Nayal, N., Yavuz, M., Henriques, J.F., G\u00fcney, F.: RbA: segmenting unknown regions rejected by all. In: International Conference on Computer Vision, pp. 711\u2013722 (2023)","DOI":"10.1109\/ICCV51070.2023.00072"},{"key":"13_CR33","doi-asserted-by":"publisher","unstructured":"Pinggera, P., Ramos, S., Gehrig, S., Franke, U., Rother, C., Mester, R.: Lost and found: detecting small road hazards for self-driving vehicles. In: 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS 2016, Daejeon, South Korea, 9\u201314 October 2016, pp. 1099\u20131106. IEEE (2016). https:\/\/doi.org\/10.1109\/IROS.2016.7759186","DOI":"10.1109\/IROS.2016.7759186"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Rai, S.N., Cermelli, F., Caputo, B., Masone, C.: Mask2anomaly: mask transformer for universal open-set segmentation. T-PAMI (2024)","DOI":"10.1109\/TPAMI.2024.3419055"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Rai, S.N., Cermelli, F., Fontanel, D., Masone, C., Caputo, B.: Unmasking anomalies in road-scene segmentation. In: International Conference on Computer Vision, pp. 4014\u20134023 (2023)","DOI":"10.1109\/ICCV51070.2023.00373"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Ramachandra, B., Jones, M.J.: Street scene: a new dataset and evaluation protocol for video anomaly detection. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 2558\u20132567 (2020)","DOI":"10.1109\/WACV45572.2020.9093457"},{"key":"13_CR37","unstructured":"Ravi, N., et al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024). https:\/\/arxiv.org\/abs\/2408.00714"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Ristea, N.C., Croitoru, F.A., Ionescu, R.T., Popescu, M., Khan, F.S., Shah, M.: Self-distilled masked auto-encoders are efficient video anomaly detectors. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15984\u201315995 (2024)","DOI":"10.1109\/CVPR52733.2024.01513"},{"key":"13_CR39","unstructured":"Ryali, C., et al.: Hiera: a hierarchical vision transformer without the bells-and-whistles. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) International Conference on Machine Learning, ICML 2023, 23\u201329 July 2023, Honolulu, Hawaii, USA. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 29441\u201329454. PMLR (2023). https:\/\/proceedings.mlr.press\/v202\/ryali23a.html"},{"key":"13_CR40","doi-asserted-by":"publisher","unstructured":"Singh, A., Kamireddypalli, A., Gandhi, V., Krishna, K.M.: Lidar guided small obstacle segmentation. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS 2020, Las Vegas, NV, USA, 24 October 2020\u201324 January 2021, pp. 8513\u20138520. IEEE (2020). https:\/\/doi.org\/10.1109\/IROS45743.2020.9341465","DOI":"10.1109\/IROS45743.2020.9341465"},{"key":"13_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Vojir, T., \u0160ipka, T., Aljundi, R., Chumerin, N., Reino, D.O., Matas, J.: Road anomaly detection by partial image reconstruction with segmentation coupling. In: International Conference on Computer Vision, pp. 15631\u201315640 (2021)","DOI":"10.1109\/ICCV48922.2021.01536"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"Xia, Y., Zhang, Y., Liu, F., Shen, W., Yuille, A.: Synthesize then compare: detecting failures and anomalies for semantic segmentation. In: European Conference on Computer Vision, pp. 145\u2013161 (2020)","DOI":"10.1007\/978-3-030-58452-8_9"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, D., Sakmann, K., Beluch, W., Hutmacher, R., Li, Y.: Anomaly-aware semantic segmentation via style-aligned OoD augmentation. In: International Conference on Computer Vision Workshop, pp. 4067\u20134075 (2023)","DOI":"10.1109\/ICCVW60793.2023.00439"},{"key":"13_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, T., et al.: DVIS: decoupled video instance segmentation framework. In: International Conference on Computer Vision, pp. 1282\u20131291 (2023)","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"13_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, X., Peng, C., Xue, X., Sun, J.: ExFuse: enhancing feature fusion for semantic segmentation. In: European Conference on Computer Vision, pp. 273\u2013288 (2018)","DOI":"10.1007\/978-3-030-01249-6_17"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-12840-9_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:22:10Z","timestamp":1767324130000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-12840-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032128393","9783032128409"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-12840-9_13","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":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"DAGM German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Freiburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"47","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dagm-gcpr.de\/year\/2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}