{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:08:16Z","timestamp":1789124896250,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376015","type":"print"},{"value":"9783032376022","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\/978-3-032-37602-2_27","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:27:32Z","timestamp":1789122452000},"page":"470-489","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from\u00a0YouTube Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4137-0417","authenticated-orcid":false,"given":"Haoming","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lichen","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2536-3302","authenticated-orcid":false,"given":"Tianfang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4536-0953","authenticated-orcid":false,"given":"Jingyu","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6905-4478","authenticated-orcid":false,"given":"Zhizhong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9346-1196","authenticated-orcid":false,"given":"Xin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8926-4162","authenticated-orcid":false,"given":"Yanyun","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6945-7437","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Avetisyan, A., Dahnert, M., Dai, A., Savva, M., Chang, A.X., Nie\u00dfner, M.: Scan2CAD: learning cad model alignment in RGB-D scans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2614\u20132623 (2019)","DOI":"10.1109\/CVPR.2019.00272"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Cao, A.Q., De Charette, R.: MonoScene: monocular 3D semantic scene completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3991\u20134001 (2022)","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Chambon, L., Zablocki, E., Boulch, A., Chen, M., Cord, M.: GaussRender: learning 3D occupancy with gaussian rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 27010\u201327020 (2025)","DOI":"10.1109\/ICCV51701.2025.02507"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., Zhang, Z., Qu, Y., Zhang, R., Tan, X., Xie, Y.: Building a strong pre-training baseline for universal 3D large-scale perception. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19925\u201319935 (June 2024)","DOI":"10.1109\/CVPR52733.2024.01883"},{"key":"27_CR6","unstructured":"Chen, J., Xu, H., Wang, Y., Chau, L.P.: OccProphet: Pushing efficiency frontier of camera-only 4D occupancy forecasting with observer-forecaster-refiner framework. arXiv preprint arXiv:2502.15180 (2025)"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Lin, K.Y., Qian, C., Zeng, G., Li, H.: 3D sketch-aware semantic scene completion via semi-supervised structure prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4193\u20134202 (2020)","DOI":"10.1109\/CVPR42600.2020.00425"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Feng, R., Chang, H.J., Tse, T.H.E., Kim, B., Chang, Y., Gao, Y.: High-resolution spatiotemporal modeling with global-local state space models for video-based human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8929\u20138938 (2025)","DOI":"10.1109\/ICCV51701.2025.00835"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Gong, J., et al.: Omni-supervised point cloud segmentation via gradual receptive field component reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11673\u201311682 (2021)","DOI":"10.1109\/CVPR46437.2021.01150"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Gong, J., et al.: Boundary-aware geometric encoding for semantic segmentation of point clouds. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1424\u20131432 (2021)","DOI":"10.1609\/aaai.v35i2.16232"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Hayler, A., Wimbauer, F., Muhle, D., Rupprecht, C., Cremers, D.: S4C: Self-supervised semantic scene completion with neural fields. arXiv preprint arXiv:2310.07522 (2023)","DOI":"10.1109\/3DV62453.2024.00133"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Hou, J., Xie, S., Graham, B., Dai, A., Nie\u00dfner, M.: Pri3D: Can 3D priors help 2D representation learning? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5693\u20135702 (2021)","DOI":"10.1109\/ICCV48922.2021.00564"},{"key":"27_CR15","unstructured":"Huang, J., Huang, G., Zhu, Z., Yun, Y., Du, D.: BEVDet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, B., Zhou, J., Lu, J.: SelfOcc: self-supervised vision-based 3D occupancy prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19946\u201319956 (2024)","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, Y., Zhou, J., Lu, J.: Tri-perspective view for vision-based 3D semantic occupancy prediction. arXiv preprint arXiv:2302.07817 (2023)","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, H., et al.: Symphonize 3D semantic scene completion with contextual instance queries. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20258\u201320267 (2024)","DOI":"10.1109\/CVPR52733.2024.01915"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, H., et al.: GaussTR: foundation model-aligned gaussian transformer for self-supervised 3D spatial understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11960\u201311970 (2025)","DOI":"10.1109\/CVPR52734.2025.01117"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023)","DOI":"10.1145\/3592433"},{"key":"27_CR21","unstructured":"Kong, W., et\u00a0al.: HunyuanVideo: A systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Li, J., Han, K., Wang, P., Liu, Y., Yuan, X.: Anisotropic convolutional networks for 3D semantic scene completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3351\u20133359 (2020)","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Li, J., He, X., Zhou, C., Cheng, X., Wen, Y., Zhang, D.: ViewFormer: Exploring spatiotemporal modeling for multi-view 3D occupancy perception via view-guided transformers. arXiv preprint arXiv:2405.04299 (2024)","DOI":"10.1007\/978-3-031-72775-7_6"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: AGO: adaptive grounding for open world 3D occupancy prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8645\u20138655 (2025)","DOI":"10.1109\/ICCV51701.2025.00809"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: VoxFormer: sparse voxel transformer for camera-based 3D semantic scene completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: BEVFormer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. arXiv preprint arXiv:2203.17270 (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"27_CR27","unstructured":"Li, Z., et al.: FB-OCC: 3D occupancy prediction based on forward-backward view transformation. arXiv:2307.01492 (2023)"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Lin, K., Chen, P., Huang, D., Li, T.H., Tan, M., Gan, C.: Learning vision-and-language navigation from YouTube videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8317\u20138326 (2023)","DOI":"10.1109\/ICCV51070.2023.00764"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Deep dual consecutive network for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 525\u2013534 (2021)","DOI":"10.1109\/CVPR46437.2021.00059"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Ma, Q., Tan, X., Qu, Y., Ma, L., Zhang, Z., Xie, Y.: COTR: compact occupancy transformer for vision-based 3D occupancy prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19936\u201319945 (2024)","DOI":"10.1109\/CVPR52733.2024.01884"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"27_CR32","unstructured":"Oquab, M., et al.: DINOv2: Learning robust visual features without supervision (2023)"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Roldao, L., De Charette, R., Verroust-Blondet, A.: LMSCNet: lightweight multiscale 3D semantic completion. In: 2020 International Conference on 3D Vision (3DV), pp. 111\u2013119. IEEE (2020)","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Sautier, C., Puy, G., Gidaris, S., Boulch, A., Bursuc, A., Marlet, R.: Image-to-lidar self-supervised distillation for autonomous driving data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9891\u20139901 (2022)","DOI":"10.1109\/CVPR52688.2022.00966"},{"key":"27_CR35","doi-asserted-by":"publisher","first-page":"25278","DOI":"10.52202\/068431-1833","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR36","unstructured":"Schuhmann, C., et al.: LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"27_CR37","unstructured":"Shah, D., Osi\u0144ski, B., Levine, S.: LM-Nav: robotic navigation with large pre-trained models of language, vision, and action. In: Conference on Robot Learning, pp. 492\u2013504. PMLR (2023)"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Computer Vision\u2013ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part V 12, pp. 746\u2013760. Springer (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: EmbodiedOcc++: Boosting embodied 3d occupancy prediction with plane regularization and uncertainty sampler. arXiv preprint arXiv:2504.09540 (2025)","DOI":"10.1145\/3746027.3754740"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: DUSt3R: geometric 3D vision made easy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20697\u201320709 (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"27_CR42","doi-asserted-by":"crossref","unstructured":"Wang, S., et al.: Not all voxels are equal: hardness-aware semantic scene completion with self-distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14792\u201314801 (2024)","DOI":"10.1109\/CVPR52733.2024.01401"},{"key":"27_CR43","unstructured":"Wang, Y., et al.: Permutation-equivariant visual geometry learning. arXiv preprint arXiv:2507.13347 (2025)"},{"key":"27_CR44","unstructured":"Wei, J., Yuan, S., Li, P., Hu, Q., Gan, Z., Ding, W.: OccLLaMA: An occupancy-language-action generative world model for autonomous driving. arXiv preprint arXiv:2409.03272 (2024)"},{"key":"27_CR45","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhao, L., Zheng, W., Zhu, Z., Zhou, J., Lu, J.: SurroundOcc: Multi-camera 3d occupancy prediction for autonomous driving. arXiv preprint arXiv:2303.09551 (2023)","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"27_CR46","doi-asserted-by":"crossref","unstructured":"Wu, S.C., Tateno, K., Navab, N., Tombari, F.: SCFusion: real-time incremental scene reconstruction with semantic completion. In: 2020 International Conference on 3D Vision (3DV), pp. 801\u2013810. IEEE (2020)","DOI":"10.1109\/3DV50981.2020.00090"},{"key":"27_CR47","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zheng, W., Zuo, S., Huang, Y., Zhou, J., Lu, J.: EmbodiedOcc: Embodied 3D occupancy prediction for vision-based online scene understanding. arXiv preprint arXiv:2412.04380 (2024)","DOI":"10.1109\/ICCV51701.2025.02446"},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912\u20131920 (2015)","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"27_CR49","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2945\u20132954 (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"27_CR50","doi-asserted-by":"crossref","unstructured":"Xu, T., Lu, H., Yan, X., Cai, Y., Liu, B., Chen, Y.: Occ-LLM: Enhancing autonomous driving with occupancy-based large language models. arXiv preprint arXiv:2502.06419 (2025)","DOI":"10.1109\/ICRA55743.2025.11127665"},{"key":"27_CR51","doi-asserted-by":"crossref","unstructured":"Xu, X., et al.: 4D contrastive Superflows are dense 3D representation learners. In: European Conference on Computer Vision, pp. 58\u201380. Springer (2024)","DOI":"10.1007\/978-3-031-73232-4_4"},{"key":"27_CR52","doi-asserted-by":"crossref","unstructured":"Yang, C., et al.: BEVFormer v2: Adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision, ArXiv (2022)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"27_CR53","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: Driving in the occupancy world: Vision-centric 4D occupancy forecasting and planning via world models for autonomous driving. arXiv preprint arXiv:2408.14197 (2024)","DOI":"10.1609\/aaai.v39i9.33010"},{"key":"27_CR54","doi-asserted-by":"crossref","unstructured":"Yao, J., et al.: NDC-scene: boost monocular 3D semantic scene completion in normalized device coordinates space. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9421\u20139431. IEEE Computer Society (2023)","DOI":"10.1109\/ICCV51070.2023.00867"},{"key":"27_CR55","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, Y., Chen, Y., Zhang, Z.: Monocular occupancy prediction for scalable indoor scenes. In: European Conference on Computer Vision, pp. 38\u201354. Springer (2024)","DOI":"10.1007\/978-3-031-73404-5_3"},{"key":"27_CR56","unstructured":"Zhang, C., et al.: OccNeRF: Advancing 3D occupancy prediction in lidar-free environments. arXiv preprint arXiv:2312.09243 (2023)"},{"key":"27_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhu, Z., Du, D.: OccFormer: Dual-path transformer for vision-based 3D semantic occupancy prediction. arXiv preprint arXiv:2304.05316 (2023)","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"27_CR58","unstructured":"Zhang, Z., et al.: RoboOcc: Enhancing the geometric and semantic scene understanding for robots. arXiv preprint arXiv:2504.14604 (2025)"},{"key":"27_CR59","doi-asserted-by":"crossref","unstructured":"Zheng, W., Chen, W., Huang, Y., Zhang, B., Duan, Y., Lu, J.: OccWorld: Learning a 3D occupancy world model for autonomous driving. arXiv preprint arXiv: 2311.16038 (2023)","DOI":"10.1007\/978-3-031-72624-8_4"},{"issue":"6","key":"27_CR60","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2017","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1452\u20131464 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: Learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817 (2018)","DOI":"10.1145\/3197517.3201323"},{"key":"27_CR62","doi-asserted-by":"crossref","unstructured":"Zhou, X., Wang, J., Wang, Y., Wei, Y., Dong, N., Yang, M.H.: AutoOcc: automatic open-ended semantic occupancy annotation via vision-language guided gaussian splatting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3367\u20133377 (2025)","DOI":"10.1109\/ICCV51701.2025.00322"},{"key":"27_CR63","doi-asserted-by":"crossref","unstructured":"Zou, J., et al.: UniM 2 AE: multi-modal masked autoencoders with unified 3D representation for 3D perception in autonomous driving. In: European Conference on Computer Vision, pp. 296\u2013313. Springer (2024)","DOI":"10.1007\/978-3-031-72670-5_17"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37602-2_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:27:51Z","timestamp":1789122471000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37602-2_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376015","9783032376022"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37602-2_27","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":"12 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}