{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:10:05Z","timestamp":1778080205016,"version":"3.51.4"},"publisher-location":"Cham","reference-count":89,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198175","type":"print"},{"value":"9783031198182","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19818-2_4","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T16:21:10Z","timestamp":1666369270000},"page":"53-72","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["Waymo Open Dataset: Panoramic Video Panoptic Segmentation"],"prefix":"10.1007","author":[{"given":"Jieru","family":"Mei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex Zihao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinchen","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang-Chieh","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henrik","family":"Kretzschmar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Baqu\u00e9, P., Fleuret, F., Fua, P.: Deep occlusion reasoning for multi-camera multi-target detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.38"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Behley, J., et al.: Semantickitti: a dataset for semantic scene understanding of lidar sequences. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00939"},{"issue":"9","key":"4_CR3","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TPAMI.2011.21","volume":"33","author":"J Berclaz","year":"2011","unstructured":"Berclaz, J., Fleuret, F., Turetken, E., Fua, P.: Multiple object tracking using k-shortest paths optimization. PAMI 33(9), 1806\u20131819 (2011)","journal-title":"PAMI"},{"issue":"2","key":"4_CR4","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"GJ Brostow","year":"2009","unstructured":"Brostow, G.J., Fauqueur, J., Cipolla, R.: Semantic object classes in video: a high-definition ground truth database. Pattern Recogn. Lett. 30(2), 88\u201397 (2009)","journal-title":"Pattern Recogn. Lett."},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Chang, M.F., et al.: Argoverse: 3D tracking and forecasting with rich maps. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00895"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Chavdarova, T., et al.: Wildtrack: a multi-camera HD dataset for dense unscripted pedestrian detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00528"},{"key":"4_CR8","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: ICLR (2015)"},{"issue":"4","key":"4_CR9","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","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. TPAMI 40(4), 834\u2013848 (2017)","journal-title":"TPAMI"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Geosim: realistic video simulation via geometry-aware composition for self-driving. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00715"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, B., et al.: Panoptic-deeplab: a simple, strong, and fast baseline for bottom-up panoptic segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Dehghan, A., Modiri Assari, S., Shah, M.: GMMCP tracker: globally optimal generalized maximum multi clique problem for multiple object tracking. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299036"},{"issue":"4","key":"4_CR14","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s11263-020-01393-0","volume":"129","author":"P Dendorfer","year":"2020","unstructured":"Dendorfer, P., et al.: MOTChallenge: a benchmark for single-camera multiple target tracking. IJCV 129(4), 845\u2013888 (2020)","journal-title":"IJCV"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Eshel, R., Moses, Y.: Homography based multiple camera detection and tracking of people in a dense crowd. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587539"},{"issue":"2","key":"4_CR16","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"issue":"2","key":"4_CR17","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59(2), 167\u2013181 (2004)","journal-title":"IJCV"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Ferryman, J., Shahrokni, A.: Pets 2009: dataset and challenge. In: 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, pp. 1\u20136. IEEE (2009)","DOI":"10.1109\/PETS-WINTER.2009.5399556"},{"issue":"2","key":"4_CR19","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1109\/TPAMI.2007.1174","volume":"30","author":"F Fleuret","year":"2007","unstructured":"Fleuret, F., Berclaz, J., Lengagne, R., Fua, P.: Multicamera people tracking with a probabilistic occupancy map. PAMI 30(2), 267\u2013282 (2007)","journal-title":"PAMI"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Gao, N., et al.: SSAP: single-shot instance segmentation with affinity pyramid. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00073"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"4_CR22","unstructured":"Geyer, J., et al.: A2d2: Audi autonomous driving dataset. arXiv preprint arXiv:2004.06320 (2020)"},{"key":"4_CR23","unstructured":"Han, X., et al.: MMPTRACK: large-scale densely annotated multi-camera multiple people tracking benchmark (2021)"},{"key":"4_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/978-3-319-10584-0_20","volume-title":"Computer Vision \u2013 ECCV 2014","author":"B Hariharan","year":"2014","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 297\u2013312. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_20"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR26","unstructured":"He, X., Zemel, R.S., Carreira-Perpi\u00f1\u00e1n, M.\u00c1.: Multiscale conditional random fields for image labeling. In: CVPR (2004)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Hofmann, M., Wolf, D., Rigoll, G.: Hypergraphs for joint multi-view reconstruction and multi-object tracking. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.468"},{"issue":"10","key":"4_CR28","doi-asserted-by":"publisher","first-page":"2702","DOI":"10.1109\/TPAMI.2019.2926463","volume":"42","author":"X Huang","year":"2019","unstructured":"Huang, X., Wang, P., Cheng, X., Zhou, D., Geng, Q., Yang, R.: The apolloscape open dataset for autonomous driving and its application. TPAMI 42(10), 2702\u20132719 (2019)","journal-title":"TPAMI"},{"issue":"10","key":"4_CR29","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. PAMI 42(10), 2702\u20132719 (2020)","journal-title":"PAMI"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Jaus, A., Yang, K., Stiefelhagen, R.: Panoramic panoptic segmentation: towards complete surrounding understanding via unsupervised contrastive learning. In: 2021 IEEE Intelligent Vehicles Symposium (IV), pp. 1421\u20131427. IEEE (2021)","DOI":"10.1109\/IV48863.2021.9575904"},{"key":"4_CR31","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: CVPR (2018)"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Kim, D., Woo, S., Lee, J.Y., Kweon, I.S.: Video Panoptic Segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00988"},{"key":"4_CR33","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"4_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/978-3-642-15549-9_28","volume-title":"Computer Vision \u2013 ECCV 2010","author":"C-H Kuo","year":"2010","unstructured":"Kuo, C.-H., Huang, C., Nevatia, R.: Inter-camera association of multi-target tracks by on-line learned appearance affinity models. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 383\u2013396. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15549-9_28"},{"key":"4_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1007\/978-3-642-15561-1_31","volume-title":"Computer Vision \u2013 ECCV 2010","author":"\u013d Ladick\u00fd","year":"2010","unstructured":"Ladick\u00fd, \u013d, Sturgess, P., Alahari, K., Russell, C., Torr, P.H.S.: What, where and how many? Combining object detectors and CRFs. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 424\u2013437. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_31"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Attention-guided unified network for panoptic segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00719"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Liang, J., Homayounfar, N., Ma, W.C., Xiong, Y., Hu, R., Urtasun, R.: Polytransform: deep polygon transformer for instance segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00915"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Liao, Y., Xie, J., Geiger, A.: Kitti-360: a novel dataset and benchmarks for urban scene understanding in 2D and 3D. arXiv:2109.13410 (2021)","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"4_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"4_CR42","unstructured":"Ling, H., Acuna, D., Kreis, K., Kim, S.W., Fidler, S.: Variational amodal object completion. In: NeurIPS (2020)"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Liu1, H., et al.: An end-to-end network for panoptic segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00633"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Luiten, J., et al.: HOTA: a higher order metric for evaluating multi-object tracking. In: IJCV (2020)","DOI":"10.1007\/s11263-020-01375-2"},{"key":"4_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/978-3-030-58598-3_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Mallya","year":"2020","unstructured":"Mallya, A., Wang, T.-C., Sapra, K., Liu, M.-Y.: World-consistent video-to-video synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 359\u2013378. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_22"},{"key":"4_CR47","doi-asserted-by":"crossref","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: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Narioka, K., Nishimura, H., Itamochi, T., Inomata, T.: Understanding 3D semantic structure around the vehicle with monocular cameras. In: IEEE Intelligent Vehicles Symposium (IV), pp. 132\u2013137. IEEE (2018)","DOI":"10.1109\/IVS.2018.8500397"},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Neuhold, G., Ollmann, T., Bul\u00f2, S.R., Kontschieder, P.: The mapillary vistas dataset for semantic understanding of street scenes. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.534"},{"key":"4_CR50","doi-asserted-by":"crossref","unstructured":"Petrovai, A., Nedevschi, S.: Semantic cameras for 360-degree environment perception in automated urban driving. IEEE Trans. Intell. Transp. Syst. (2022)","DOI":"10.1109\/TITS.2022.3156794"},{"key":"4_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-58568-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Philion","year":"2020","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12"},{"key":"4_CR52","doi-asserted-by":"crossref","unstructured":"Porzi, L., Bul\u00f2, S.R., Colovic, A., Kontschieder, P.: Seamless scene segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00847"},{"key":"4_CR53","doi-asserted-by":"crossref","unstructured":"Qi, C.R., et al.: Offboard 3D object detection from point cloud sequences. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00607"},{"key":"4_CR54","doi-asserted-by":"crossref","unstructured":"Qiao, S., Zhu, Y., Adam, H., Yuille, A., Chen, L.C.: ViP-DeepLab: learning visual perception with depth-aware video panoptic segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00399"},{"key":"4_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-319-48881-3_2","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"E Ristani","year":"2016","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for\u00a0multi-target, multi-camera tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17\u201335. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_2"},{"key":"4_CR56","doi-asserted-by":"crossref","unstructured":"Ristani, E., Tomasi, C.: Features for multi-target multi-camera tracking and re-identification. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00632"},{"key":"4_CR57","doi-asserted-by":"crossref","unstructured":"Roddick, T., Cipolla, R.: Predicting semantic map representations from images using pyramid occupancy networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"4_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/978-3-642-33709-3_25","volume-title":"Computer Vision \u2013 ECCV 2012","author":"A Roshan Zamir","year":"2012","unstructured":"Roshan Zamir, A., Dehghan, A., Shah, M.: GMCP-tracker: global multi-object tracking using generalized minimum clique graphs. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7573, pp. 343\u2013356. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33709-3_25"},{"issue":"3","key":"4_CR59","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vision"},{"key":"4_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/978-3-319-46487-9_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"JL Sch\u00f6nberger","year":"2016","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Frahm, J.-M., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 501\u2013518. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_31"},{"issue":"8","key":"4_CR61","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi, J., Malik, J.: Normalized cuts and image segmentation. PAMI 22(8), 888\u2013905 (2000)","journal-title":"PAMI"},{"key":"4_CR62","doi-asserted-by":"crossref","unstructured":"Song, S., Zeng, A., Chang, A.X., Savva, M., Savarese, S., Funkhouser, T.: Im2Pano3D: extrapolating 360 structure and semantics beyond the field of view. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00405"},{"key":"4_CR63","doi-asserted-by":"crossref","unstructured":"Su, Y.C., Grauman, K.: Making 360 video watchable in 2D: learning videography for click free viewing. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.150"},{"key":"4_CR64","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"4_CR65","doi-asserted-by":"crossref","unstructured":"Tang, Z., et al.: Cityflow: a city-scale benchmark for multi-target multi-camera vehicle tracking and re-identification. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00900"},{"key":"4_CR66","doi-asserted-by":"crossref","unstructured":"Tateno, K., Navab, N., Tombari, F.: Distortion-aware convolutional filters for dense prediction in panoramic images. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01270-0_43"},{"issue":"5\u20136","key":"4_CR67","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1177\/0278364906065387","volume":"25","author":"S Thrun","year":"2006","unstructured":"Thrun, S., Montemerlo, M.: The graph slam algorithm with applications to large-scale mapping of urban structures. Int. J. Robot. Res. 25(5\u20136), 403\u2013429 (2006)","journal-title":"Int. J. Robot. Res."},{"issue":"2","key":"4_CR68","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s11263-005-6642-x","volume":"63","author":"Z Tu","year":"2005","unstructured":"Tu, Z., Chen, X., Yuille, A.L., Zhu, S.C.: Image parsing: unifying segmentation, detection, and recognition. IJCV 63(2), 113\u2013140 (2005)","journal-title":"IJCV"},{"key":"4_CR69","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., et al.: MOTS: multi-object tracking and segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00813"},{"key":"4_CR70","doi-asserted-by":"crossref","unstructured":"Wang, H., Luo, R., Maire, M., Shakhnarovich, G.: Pixel consensus voting for panoptic segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00948"},{"key":"4_CR71","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-58548-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., Chen, L.-C.: Axial-DeepLab: stand-alone axial-attention for panoptic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 108\u2013126. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_7"},{"key":"4_CR72","doi-asserted-by":"crossref","unstructured":"Weber, M., Luiten, J., Leibe, B.: Single-shot panoptic segmentation. In: IROS (2020)","DOI":"10.1109\/IROS45743.2020.9341546"},{"key":"4_CR73","unstructured":"Weber, M., et al.: DeepLab2: A TensorFlow Library for Deep Labeling. arXiv: 2106.09748 (2021)"},{"key":"4_CR74","unstructured":"Weber, M., et al.: Step: segmenting and tracking every pixel. In: NeurIPS Track on Datasets and Benchmarks (2021)"},{"key":"4_CR75","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.312"},{"key":"4_CR76","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: UPSNet: a unified panoptic segmentation network. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00902"},{"key":"4_CR77","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1007\/978-3-642-33783-3_45","volume-title":"Computer Vision \u2013 ECCV 2012","author":"C Xu","year":"2012","unstructured":"Xu, C., Xiong, C., Corso, J.J.: Streaming hierarchical video segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 626\u2013639. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_45"},{"key":"4_CR78","doi-asserted-by":"crossref","unstructured":"Xu, Y., Liu, X., Liu, Y., Zhu, S.C.: Multi-view people tracking via hierarchical trajectory composition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.461"},{"key":"4_CR79","unstructured":"Yang, B., Bai, M., Liang, M., Zeng, W., Urtasun, R.: Auto4d: learning to label 4D objects from sequential point clouds. arXiv preprint arXiv:2101.06586 (2021)"},{"issue":"10","key":"4_CR80","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.1109\/TITS.2019.2938965","volume":"21","author":"K Yang","year":"2019","unstructured":"Yang, K., Hu, X., Bergasa, L.M., Romera, E., Wang, K.: Pass: Panoramic annular semantic segmentation. IEEE Trans. Intell. Transp. Syst. 21(10), 4171\u20134185 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"4_CR81","doi-asserted-by":"crossref","unstructured":"Yang, K., Zhang, J., Rei\u00df, S., Hu, X., Stiefelhagen, R.: Capturing omni-range context for omnidirectional segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00143"},{"key":"4_CR82","doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., Xu, N.: Video instance segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00529"},{"key":"4_CR83","unstructured":"Yang, T.J., et al.: DeeperLab: Single-Shot Image Parser. arXiv:1902.05093 (2019)"},{"key":"4_CR84","unstructured":"Yao, J., Fidler, S., Urtasun, R.: Describing the scene as a whole: joint object detection, scene classification and semantic segmentation. In: CVPR (2012)"},{"key":"4_CR85","doi-asserted-by":"crossref","unstructured":"Yogamani, S., et al.: Woodscape: a multi-task, multi-camera fisheye dataset for autonomous driving. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00940"},{"key":"4_CR86","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"4_CR87","doi-asserted-by":"crossref","unstructured":"Zakharov, S., Kehl, W., Bhargava, A., Gaidon, A.: Autolabeling 3D objects with differentiable rendering of SDF shape priors. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01224"},{"key":"4_CR88","doi-asserted-by":"crossref","unstructured":"Zendel, O., Sch\u00f6rghuber, M., Rainer, B., Murschitz, M., Beleznai, C.: Unifying panoptic segmentation for autonomous driving. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.02066"},{"key":"4_CR89","doi-asserted-by":"crossref","unstructured":"Zhang, C., Liwicki, S., Smith, W., Cipolla, R.: Orientation-aware semantic segmentation on icosahedron spheres. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00363"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19818-2_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T14:17:25Z","timestamp":1710339445000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19818-2_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198175","9783031198182"],"references-count":89,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19818-2_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}