{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:31:48Z","timestamp":1777656708844,"version":"3.51.4"},"publisher-location":"Cham","reference-count":90,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729324","type":"print"},{"value":"9783031729331","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"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\/978-3-031-72933-1_10","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T12:02:53Z","timestamp":1727870573000},"page":"164-182","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Open Panoramic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4390-3044","authenticated-orcid":false,"given":"Junwei","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5245-2277","authenticated-orcid":false,"given":"Ruiping","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3670-4567","authenticated-orcid":false,"given":"Yufan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5419-9292","authenticated-orcid":false,"given":"Kunyu","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2186-3748","authenticated-orcid":false,"given":"Chengzhi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1090-667X","authenticated-orcid":false,"given":"Kailun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3471-328X","authenticated-orcid":false,"given":"Jiaming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8046-4945","authenticated-orcid":false,"given":"Rainer","family":"Stiefelhagen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Ai, H., Cao, Z., Zhu, J., Bai, H., Chen, Y., Wang, L.: Deep learning for omnidirectional vision: a survey and new perspectives. arXiv preprint arXiv:2205.10468 (2022)","DOI":"10.36227\/techrxiv.19807699.v1"},{"key":"10_CR2","unstructured":"Armeni, I., Sax, S., Zamir, A.R., Savarese, S.: Joint 2D-3D-semantic data for indoor scene understanding. arXiv preprint arXiv:1702.01105 (2017)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Athwale, A., Afrasiyabi, A., Lag\u00fce, J., Shili, I., Ahmad, O., Lalonde, J.F.: DarSwin: distortion aware radial swin transformer. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00545"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Berenguel-Baeta, B., Bermudez-Cameo, J., Guerrero, J.J.: FreDSNet: joint monocular depth and semantic segmentation with fast Fourier convolutions from single panoramas. In: ICRA (2023)","DOI":"10.2139\/ssrn.4488114"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J.R.R., Ferrari, V.: COCO-stuff: thing and stuff classes in context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: 3DV (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"10_CR7","unstructured":"Chen, J., et al.: Exploring open-vocabulary semantic segmentation without human labels. arXiv preprint arXiv:2306.00450 (2023)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Li, S., Lim, S.N., Torralba, A., Zhao, H.: Open-vocabulary panoptic segmentation with embedding modulation. arXiv preprint arXiv:2303.11324 (2023)","DOI":"10.1109\/ICCV51070.2023.00111"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Cho, S., Shin, H., Hong, S., An, S., Lee, S., Arnab, A., Seo, P.H., Kim, S.: CAT-Seg: cost aggregation for open-vocabulary semantic segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Dao, S.D., Shi, H., Phung, D., Cai, J.: Class enhancement losses with pseudo labels for open-vocabulary semantic segmentation. TMM (2023)","DOI":"10.1109\/TMM.2023.3330102"},{"key":"10_CR12","unstructured":"Ding, Z., Wang, J., Tu, Z.: Open-vocabulary universal image segmentation with MaskCLIP. In: ICML (2023)"},{"key":"10_CR13","unstructured":"Dong, B., Gu, J., Han, J., Xu, H., Zuo, W.: Towards universal vision-language omni-supervised segmentation. arXiv preprint arXiv:2303.06547 (2023)"},{"key":"10_CR14","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"10_CR16","unstructured":"Fu, X., et al.: PanopticNeRF-360: panoramic 3D-to-2D label transfer in urban scenes. arXiv preprint arXiv:2309.10815 (2023)"},{"key":"10_CR17","first-page":"1","volume":"71","author":"S Gao","year":"2022","unstructured":"Gao, S., Yang, K., Shi, H., Wang, K., Bai, J.: Review on panoramic imaging and its applications in scene understanding. TIM 71, 1\u201334 (2022)","journal-title":"TIM"},{"key":"10_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1007\/978-3-031-20059-5_31","volume-title":"Computer Vision \u2013 ECCV 2022","author":"G Ghiasi","year":"2022","unstructured":"Ghiasi, G., Gu, X., Cui, Y., Lin, T.Y.: Scaling open-vocabulary image segmentation with image-level labels. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 540\u2013557. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_31"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: MVP-SEG: multi-view prompt learning for open-vocabulary semantic segmentation. arXiv preprint arXiv:2304.06957 (2023)","DOI":"10.1007\/978-981-99-8555-5_13"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Guttikonda, S., Rambach, J.: Single frame semantic segmentation using multi-modal spherical images. In: WACV (2024)","DOI":"10.1109\/WACV57701.2024.00319"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Han, K., et al.: Global knowledge calibration for fast open-vocabulary segmentation. arXiv preprint arXiv:2303.09181 (2023)","DOI":"10.1109\/ICCV51070.2023.00080"},{"key":"10_CR22","first-page":"1","volume":"71","author":"X Hu","year":"2022","unstructured":"Hu, X., An, Y., Shao, C., Hu, H.: Distortion convolution module for semantic segmentation of panoramic images based on the image-forming principle. TIM 71, 1\u201312 (2022)","journal-title":"TIM"},{"key":"10_CR23","unstructured":"Jang, S., Na, J., Oh, D.: DaDA: distortion-aware domain adaptation for unsupervised semantic segmentation. In: NeurIPS (2022)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Jaus, A., Yang, K., Stiefelhagen, R.: Panoramic panoptic segmentation: towards complete surrounding understanding via unsupervised contrastive learning. In: IV (2021)","DOI":"10.1109\/IV48863.2021.9575904"},{"key":"10_CR25","first-page":"4438","volume":"24","author":"A Jaus","year":"2023","unstructured":"Jaus, A., Yang, K., Stiefelhagen, R.: Panoramic panoptic segmentation: insights into surrounding parsing for mobile agents via unsupervised contrastive learning. T-ITS 24, 4438\u20134453 (2023)","journal-title":"T-ITS"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Jiang, Q., et al.: Minimalist and high-quality panoramic imaging with PSF-aware transformers. TIP (2024)","DOI":"10.1109\/TIP.2024.3441370"},{"key":"10_CR27","first-page":"1250","volume":"8","author":"Q Jiang","year":"2022","unstructured":"Jiang, Q., Shi, H., Sun, L., Gao, S., Yang, K., Wang, K.: Annular computational imaging: capture clear panoramic images through simple lens. TCI 8, 1250\u20131264 (2022)","journal-title":"TCI"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Jiang, W., Wu, Y.: DFNet: semantic segmentation on panoramic images with dynamic loss weights and residual fusion block. In: ICRA (2018)","DOI":"10.1109\/ICRA.2019.8794476"},{"key":"10_CR29","unstructured":"Jiayun, L., Khandelwal, S., Sigal, L., Li, B.: Plug-and-play, dense-label-free extraction of open-vocabulary semantic segmentation from vision-language models. arXiv preprint arXiv:2311.17095 (2023)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Kim, J., Jeong, S., Sohn, K.: PASTS: toward effective distilling transformer for panoramic semantic segmentation. In: ICIP (2022)","DOI":"10.1109\/ICIP46576.2022.9897414"},{"key":"10_CR31","unstructured":"Li, B., Weinberger, K.Q., Belongie, S.J., Koltun, V., Ranftl, R.: Language-driven semantic segmentation. In: ICLR (2022)"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Li, J., Chen, P., Qian, S., Jia, J.: TagCLIP: improving discrimination ability of open-vocabulary semantic segmentation. arXiv preprint arXiv:2304.07547 (2023)","DOI":"10.1109\/TPAMI.2024.3454647"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Li, X., Wu, T., Qi, Z., Wang, G., Shan, Y., Li, X.: SGAT4PASS: spherical geometry-aware transformer for panoramic semantic segmentation. In: IJCAI (2023)","DOI":"10.24963\/ijcai.2023\/125"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Li, Z., Zhou, Q., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Open-vocabulary object segmentation with diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00705"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted CLIP. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Ling, Z., Xing, Z., Zhou, X., Cao, M., Zhou, G.: PanoSwin: a pano-style swin transformer for panorama understanding. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01703"},{"key":"10_CR37","unstructured":"Liu, Y., Ge, P., Liu, Q., Huang, D.: Multi-grained cross-modal alignment for learning open-vocabulary semantic segmentation from text supervision. arXiv preprint arXiv:2403.03707 (2024)"},{"key":"10_CR38","unstructured":"Luo, H., Bao, J., Wu, Y., He, X., Li, T.: SegCLIP: patch aggregation with learnable centers for open-vocabulary semantic segmentation. In: ICML (2023)"},{"key":"10_CR39","unstructured":"Ma, C., Yang, Y.H., Wang, Y., Zhang, Y., Xie, W.: Open-vocabulary semantic segmentation with frozen vision-language models. In: BMVC (2022)"},{"key":"10_CR40","unstructured":"Ma, C., Yang, Y., Ju, C., Zhang, F., Zhang, Y., Wang, Y.: Open-vocabulary semantic segmentation via attribute decomposition-aggregation. arXiv preprint arXiv:2309.00096 (2023)"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Ma, C., Zhang, J., Yang, K., Roitberg, A., Stiefelhagen, R.: DensePASS: dense panoramic semantic segmentation via unsupervised domain adaptation with attention-augmented context exchange. In: ITSC (2021)","DOI":"10.1109\/ITSC48978.2021.9564920"},{"key":"10_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-031-19818-2_4","volume-title":"Computer Vision \u2013 ECCV 2022","author":"J Mei","year":"2022","unstructured":"Mei, J., et al.: Waymo open dataset: panoramic video panoptic segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13689, pp. 53\u201372. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_4"},{"issue":"11","key":"10_CR43","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Mukhoti, J., et al.: Open vocabulary semantic segmentation with patch aligned contrastive learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Oin, J., et al.: FreeSeg: unified, universal and open-vocabulary image segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"10_CR46","first-page":"643","volume":"16","author":"S Orhan","year":"2021","unstructured":"Orhan, S., Bastanlar, Y.: Semantic segmentation of outdoor panoramic images. SIVP 16, 643\u2013650 (2021)","journal-title":"SIVP"},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Orsic, M., Kreso, I., Bevandic, P., Segvic, S.: In defense of pre-trained ImageNet architectures for real-time semantic segmentation of road-driving images. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01289"},{"key":"10_CR48","unstructured":"Poudel, R.P.K., Liwicki, S., Cipolla, R.: Fast-SCNN: fast semantic segmentation network. In: BMVC (2019)"},{"key":"10_CR49","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"10_CR50","doi-asserted-by":"crossref","unstructured":"Ray, B., Jung, J., Larabi, M.: A low-complexity video encoder for equirectangular projected 360 video content. In: ICASSP (2018)","DOI":"10.1109\/ICASSP.2018.8462368"},{"key":"10_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/978-3-031-19769-7_12","volume-title":"Computer Vision - ECCV 2022","author":"Z Shen","year":"2022","unstructured":"Shen, Z., Lin, C., Liao, K., Nie, L., Zheng, Z., Zhao, Y.: PanoFormer: panorama transformer for indoor 360$$^\\circ $$ depth estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13661, pp. 195\u2013211. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_12"},{"key":"10_CR52","first-page":"5570","volume":"24","author":"H Shi","year":"2023","unstructured":"Shi, H., et al.: PanoFlow: learning 360$$^\\circ $$ optical flow for surrounding temporal understanding. T-ITS 24, 5570\u20135585 (2023)","journal-title":"T-ITS"},{"key":"10_CR53","unstructured":"Takmaz, A., Fedele, E., Sumner, R.W., Pollefeys, M., Tombari, F., Engelmann, F.: OpenMask3D: open-vocabulary 3D instance segmentation. arXiv preprint arXiv:2306.13631 (2023)"},{"key":"10_CR54","doi-asserted-by":"crossref","unstructured":"Teng, Z., et al.: 360BEV: panoramic semantic mapping for indoor bird\u2019s-eye view. In: WACV (2024)","DOI":"10.1109\/WACV57701.2024.00044"},{"key":"10_CR55","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"10_CR56","unstructured":"Wang, J., et al.: Diffusion model is secretly a training-free open vocabulary semantic segmenter. arXiv preprint arXiv:2309.02773 (2023)"},{"key":"10_CR57","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: InternImage: exploring large-scale vision foundation models with deformable convolutions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"10_CR58","unstructured":"Wang, X., Li, S., Kallidromitis, K., Kato, Y., Kozuka, K., Darrell, T.: Hierarchical open-vocabulary universal image segmentation. arXiv preprint arXiv:2307.00764 (2023)"},{"key":"10_CR59","unstructured":"Wei, M., Yue, X., Zhang, W., Kong, S., Liu, X., Pang, J.: OV-PARTS: towards open-vocabulary part segmentation. arXiv preprint arXiv:2310.05107 (2023)"},{"key":"10_CR60","doi-asserted-by":"crossref","unstructured":"Wu, C., Zheng, J., Pfrommer, J., Beyerer, J.: Attention-based point cloud edge sampling. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00516"},{"key":"10_CR61","doi-asserted-by":"crossref","unstructured":"Wysocza\u2019nska, M., Ramamonjisoa, M., Trzci\u2019nski, T., Sim\u00e9oni, O.: CLIP-DIY: CLIP dense inference yields open-vocabulary semantic segmentation for-free. arXiv preprint arXiv:2309.14289 (2023)","DOI":"10.1109\/WACV57701.2024.00143"},{"key":"10_CR62","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"10_CR63","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: DAT++: spatially dynamic vision transformer with deformable attention. arXiv preprint arXiv:2309.01430 (2023)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"10_CR64","doi-asserted-by":"crossref","unstructured":"Xie, B., Cao, J., Xie, J., Khan, F.S., Pang, Y.: SED: a simple encoder-decoder for open-vocabulary semantic segmentation. arXiv preprint arXiv:2311.15537 (2023)","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"10_CR65","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: Efficient deformable ConvNets: rethinking dynamic and sparse operator for vision applications. arXiv preprint arXiv:2401.06197 (2024)","DOI":"10.1109\/CVPR52733.2024.00540"},{"key":"10_CR66","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"10_CR67","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Learning open-vocabulary semantic segmentation models from natural language supervision. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"10_CR68","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: SAN: side adapter network for open-vocabulary semantic segmentation. TPAMI (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"10_CR69","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"10_CR70","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1007\/978-3-031-19818-2_42","volume-title":"Computer Vision - ECCV 2022","author":"M Xu","year":"2022","unstructured":"Xu, M., Zhang, Z., Wei, F., Lin, Y., Cao, Y., Hu, H., Bai, X.: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13689, pp. 736\u2013753. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_42"},{"key":"10_CR71","doi-asserted-by":"crossref","unstructured":"Xu, X., Xiong, T., Ding, Z., Tu, Z.: MasQCLIP for open-vocabulary universal image segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00088"},{"key":"10_CR72","doi-asserted-by":"crossref","unstructured":"Yang, K., et al.: Can we PASS beyond the field of view? Panoramic annular semantic segmentation for real-world surrounding perception. In: IV (2019)","DOI":"10.1109\/IVS.2019.8814042"},{"key":"10_CR73","first-page":"4171","volume":"21","author":"K Yang","year":"2020","unstructured":"Yang, K., Hu, X., Bergasa, L.M., Romera, E., Wang, K.: PASS: panoramic annular semantic segmentation. T-ITS 21, 4171\u20134185 (2020)","journal-title":"T-ITS"},{"key":"10_CR74","doi-asserted-by":"crossref","unstructured":"Yang, K., Hu, X., Fang, Y., Wang, K., Stiefelhagen, R.: Omnisupervised omnidirectional semantic segmentation. T-ITS (2022)","DOI":"10.1109\/TITS.2020.3023331"},{"key":"10_CR75","first-page":"1866","volume":"30","author":"K Yang","year":"2021","unstructured":"Yang, K., Hu, X., Stiefelhagen, R.: Is context-aware CNN ready for the surroundings? Panoramic semantic segmentation in the wild. TIP 30, 1866\u20131881 (2021)","journal-title":"TIP"},{"key":"10_CR76","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":"10_CR77","doi-asserted-by":"crossref","unstructured":"Yang, M., Yu, K., Zhang, C., Li, Z., Yang, K.: DenseASPP for semantic segmentation in street scenes. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00388"},{"key":"10_CR78","unstructured":"Yin, W., Liu, Y., Shen, C., Hengel, A.V.D., Sun, B.: The devil is in the labels: semantic segmentation from sentences. arXiv preprint arXiv:2202.02002 (2022)"},{"key":"10_CR79","doi-asserted-by":"crossref","unstructured":"Yu, H., He, L., Jian, B., Feng, W., Liu, S.: PanelNet: understanding 360 indoor environment via panel representation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00091"},{"key":"10_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: A simple framework for open-vocabulary segmentation and detection. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"10_CR81","first-page":"9478","volume":"23","author":"J Zhang","year":"2022","unstructured":"Zhang, J., Ma, C., Yang, K., Roitberg, A., Peng, K., Stiefelhagen, R.: Transfer beyond the field of view: dense panoramic semantic segmentation via unsupervised domain adaptation. T-ITS 23, 9478\u20139491 (2022)","journal-title":"T-ITS"},{"key":"10_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yang, K., Ma, C., Rei\u00df, S., Peng, K., Stiefelhagen, R.: Bending reality: distortion-aware transformers for adapting to panoramic semantic segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01641"},{"key":"10_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Behind every domain there is a shift: adapting distortion-aware vision transformers for panoramic semantic segmentation. TPAMI (2024)","DOI":"10.1109\/TPAMI.2024.3408642"},{"key":"10_CR84","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"10_CR85","doi-asserted-by":"crossref","unstructured":"Zheng, J., Zhang, J., Yang, K., Peng, K., Stiefelhagen, R.: MateRobot: material recognition in wearable robotics for people with visual impairments. In: 2024 IEEE International Conference on Robotics and Automation (ICRA) (2024)","DOI":"10.1109\/ICRA57147.2024.10610333"},{"key":"10_CR86","doi-asserted-by":"crossref","unstructured":"Zheng, X., Pan, T., Luo, Y., Wang, L.: Look at the neighbor: distortion-aware unsupervised domain adaptation for panoramic semantic segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01713"},{"key":"10_CR87","doi-asserted-by":"crossref","unstructured":"Zheng, X., Zhu, J., Liu, Y., Cao, Z., Fu, C., Wang, L.: Both style and distortion matter: dual-path unsupervised domain adaptation for panoramic semantic segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00130"},{"key":"10_CR88","unstructured":"Zhou, H., et al.: Rethinking evaluation metrics of open-vocabulary segmentaion. arXiv preprint arXiv:2311.03352 (2023)"},{"key":"10_CR89","unstructured":"Zhou, Q., Liu, Y., Yu, C., Li, J., Wang, Z., Wang, F.: LMSeg: language-guided multi-dataset segmentation. In: ICLR (2023)"},{"key":"10_CR90","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable ConvNets V2: more deformable, better results. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00953"}],"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\/978-3-031-72933-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T12:34:32Z","timestamp":1727872472000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72933-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,3]]},"ISBN":["9783031729324","9783031729331"],"references-count":90,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72933-1_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,3]]},"assertion":[{"value":"3 October 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"}}]}}