{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:27:28Z","timestamp":1777656448370,"version":"3.51.4"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732348","type":"print"},{"value":"9783031732355","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-73235-5_8","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:01:53Z","timestamp":1727589713000},"page":"131-148","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Hierarchical Temporal Context Learning for\u00a0Camera-Based Semantic Scene Completion"],"prefix":"10.1007","author":[{"given":"Bohan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhujin","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dalong","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Anastasiu, D.C., Karypis, G.: L2ap: fast cosine similarity search with prefix l-2 norm bounds. In: International Conference on Data Engineering. IEEE (2014)","DOI":"10.1109\/ICDE.2014.6816700"},{"key":"8_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"},{"key":"8_CR3","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: Adabins: depth estimation using adaptive bins. In: CVPR (2021)"},{"key":"8_CR4","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":"8_CR5","doi-asserted-by":"crossref","unstructured":"Cai, C., Ji, P., Yan, Q., Xu, Y.: Riav-mvs: recurrent-indexing an asymmetric volume for multi-view stereo. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00095"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Cai, Y., Chen, X., Zhang, C., Lin, K.Y., Wang, X., Li, H.: Semantic scene completion via integrating instances and scene in-the-loop. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00039"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Cao, A.Q., de\u00a0Charette, R.: Monoscene: monocular 3d semantic scene completion. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"8_CR8","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00425"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, R., Agia, C., Ren, Y., Li, X., Bingbing, L.: S3cnet: a sparse semantic scene completion network for lidar point clouds. In: Conference on Robot Learning (2021)","DOI":"10.1109\/ICRA48506.2021.9561305"},{"key":"8_CR10","unstructured":"Cheng, X., et al.: Hierarchical neural architecture search for deep stereo matching. In: NeurIPS, vol. 33 (2020)"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.89"},{"issue":"1","key":"8_CR12","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1057\/ejis.2010.61","volume":"21","author":"N Evangelopoulos","year":"2012","unstructured":"Evangelopoulos, N., Zhang, X., Prybutok, V.R.: Latent semantic analysis: five methodological recommendations. Eur. J. Inf. Syst. 21(1), 70\u201386 (2012)","journal-title":"Eur. J. Inf. Syst."},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Evangelopoulos, N.E.: Latent semantic analysis. Wiley Interdisc, Rev. Cogn. Sci. 4(6) (2013)","DOI":"10.1002\/wcs.1254"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Garbade, M., Chen, Y.T., Sawatzky, J., Gall, J.: Two stream 3d semantic scene completion. In: CVPRW (2019)","DOI":"10.1109\/CVPRW.2019.00055"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: 3d packing for self-supervised monocular depth estimation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"8_CR16","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. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Kopf, J., Rong, X., Huang, J.B.: Robust consistent video depth estimation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00166"},{"issue":"22","key":"8_CR18","doi-asserted-by":"publisher","first-page":"4893","DOI":"10.1016\/j.ins.2007.05.027","volume":"177","author":"T Korenius","year":"2007","unstructured":"Korenius, T., Laurikkala, J., Juhola, M.: On principal component analysis, cosine and euclidean measures in information retrieval. Inf. Sci. 177(22), 4893\u20134905 (2007)","journal-title":"Inf. Sci."},{"key":"8_CR19","unstructured":"Li, B., et al.: Stereoscene: bev-assisted stereo matching empowers 3d semantic scene completion (2023)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Li, J., Han, K., Wang, P., Liu, Y., Yuan, X.: Anisotropic convolutional networks for 3d semantic scene completion. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Li, S., Luo, Y., Zhu, Y., Zhao, X., Li, Y., Shan, Y.: Enforcing temporal consistency in video depth estimation. In: ICCV (2021)","DOI":"10.1109\/ICCVW54120.2021.00134"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Voxformer: sparse voxel transformer for camera-based 3d semantic scene completion. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Bevdepth: acquisition of reliable depth for multi-view 3d object detection. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"8_CR24","unstructured":"Lin, X., Lin, T., Pei, Z., Huang, L., Su, Z.: Sparse4d: multi-view 3d object detection with sparse spatial-temporal fusion. arXiv preprint arXiv:2211.10581 (2022)"},{"key":"8_CR25","first-page":"531","volume-title":"ECCV 2022","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: Petr: Position embedding transformation for multi-view 3d object detection. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, vol. 13687, pp. 531\u2013548. Springer, Heidelberg (2022)"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Petrv2: a unified framework for 3d perception from multi-camera images. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Long, X., Liu, L., Li, W., Theobalt, C., Wang, W.: Multi-view depth estimation using epipolar spatio-temporal networks. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00816"},{"key":"8_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Luo, X., Huang, J.B., Szeliski, R., Matzen, K., Kopf, J.: Consistent video depth estimation. ACM Trans. Graph. (ToG) 39 (2020)","DOI":"10.1145\/3386569.3392377"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Lovegrove, S.J., Davison, A.J.: Dtam: dense tracking and mapping in real-time. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"8_CR31","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":"8_CR32","unstructured":"Rahutomo, F., Kitasuka, T., Aritsugi, M.: Semantic cosine similarity. In: ICAST (2012)"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Ramachandran, L., Gehringer, E.F.: Automated assessment of review quality using latent semantic analysis. In: ICALT. IEEE (2011)","DOI":"10.1109\/ICALT.2011.46"},{"issue":"10","key":"8_CR34","doi-asserted-by":"publisher","first-page":"7205","DOI":"10.1109\/TPAMI.2021.3095302","volume":"44","author":"CB Rist","year":"2021","unstructured":"Rist, C.B., Emmerichs, D., Enzweiler, M., Gavrila, D.M.: Semantic scene completion using local deep implicit functions on lidar data. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 7205\u20137218 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Roldao, L., de\u00a0Charette, R., Verroust-Blondet, A.: Lmscnet: lightweight multiscale 3d semantic completion. In: 3DV (2020)","DOI":"10.1109\/3DV50981.2020.00021"},{"issue":"8","key":"8_CR36","doi-asserted-by":"publisher","first-page":"1978","DOI":"10.1007\/s11263-021-01504-5","volume":"130","author":"L Roldao","year":"2022","unstructured":"Roldao, L., De Charette, R., Verroust-Blondet, A.: 3d semantic scene completion: a survey. Int. J. Comput. Vision 130(8), 1978\u20132005 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Sarwar, B., Karypis, G., Konstan, J., Riedl, J.: Item-based collaborative filtering recommendation algorithms. In: WWW (2001)","DOI":"10.1145\/371920.372071"},{"key":"8_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.28"},{"key":"8_CR40","unstructured":"Straub, J., et\u00a0al.: The replica dataset: a digital replica of indoor spaces. arXiv preprint arXiv:1906.05797 (2019)"},{"key":"8_CR41","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: ICML (2019)"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Wang, F., Galliani, S., Vogel, C., Speciale, P., Pollefeys, M.: Patchmatchnet: learned multi-view patchmatch stereo. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01397"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Openoccupancy: a large scale benchmark for surrounding semantic occupancy perception. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, P., Yang, Z., Luo, C., Yang, Y., Xu, W.: Unos: unified unsupervised optical-flow and stereo-depth estimation by watching videos. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00826"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Watson, J., Mac\u00a0Aodha, O., Prisacariu, V., Brostow, G., Firman, M.: The temporal opportunist: self-supervised multi-frame monocular depth. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"8_CR46","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. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Wu, S.C., Tateno, K., Navab, N., Tombari, F.: Scfusion: real-time incremental scene reconstruction with semantic completion. In: 3DV (2020)","DOI":"10.1109\/3DV50981.2020.00090"},{"key":"8_CR48","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.ins.2015.02.024","volume":"307","author":"P Xia","year":"2015","unstructured":"Xia, P., Zhang, L., Li, F.: Learning similarity with cosine similarity ensemble. Inf. Sci. 307, 39\u201352 (2015)","journal-title":"Inf. Sci."},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Yan, X., et al.: Sparse single sweep lidar point cloud segmentation via learning contextual shape priors from scene completion. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i4.16419"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, H., Shen, C., Li, Y., Cao, Y., Liu, Y., Yan, Y.: Exploiting temporal consistency for real-time video depth estimation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00181"},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhao, H., Yao, A., Chen, Y., Zhang, L., Liao, H.: Efficient semantic scene completion network with spatial group convolution. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01258-8_45"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhu, Z., Du, D.: Occformer: dual-path transformer for vision-based 3d semantic occupancy prediction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00865"}],"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\/978-3-031-73235-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:12:18Z","timestamp":1727590338000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73235-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031732348","9783031732355"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73235-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}