{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T13:02:28Z","timestamp":1784552548311,"version":"3.55.0"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727740","type":"print"},{"value":"9783031727757","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\/978-3-031-72775-7_22","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"382-400","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["EgoLifter: Open-World 3D Segmentation for\u00a0Egocentric Perception"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1342-3307","authenticated-orcid":false,"given":"Qiao","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7788-9982","authenticated-orcid":false,"given":"Zhaoyang","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5948-3452","authenticated-orcid":false,"given":"Duncan","family":"Frost","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5323-1170","authenticated-orcid":false,"given":"Simon","family":"Green","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2339-1262","authenticated-orcid":false,"given":"Julian","family":"Straub","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5318-5621","authenticated-orcid":false,"given":"Chris","family":"Sweeney","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-NeRF 360: unbounded anti-aliased neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5470\u20135479 (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"22_CR2","unstructured":"Bhalgat, Y., Laina, I., Henriques, J.F., Zisserman, A., Vedaldi, A.: Contrastive lift: 3d object instance segmentation by slow-fast contrastive fusion. In: Advances in Neural Information Processing Systems (2023)"},{"key":"22_CR3","first-page":"25971","volume":"36","author":"J Cen","year":"2023","unstructured":"Cen, J., et al.: Segment anything in 3D with NerFS. Adv. Neural. Inf. Process. Syst. 36, 25971\u201325990 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, F., Wang, Y., Liu, H.: Text-to-3d using gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21401\u201321412 (2024)","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Crabtree, A., Tolmie, P.: A day in the life of things in the home. In: Proceedings of the 19th ACM Conference on Computer-Supported Cooperative Work & Social Computing, pp. 1738\u20131750 (2016)","DOI":"10.1145\/2818048.2819954"},{"key":"22_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/978-3-030-01225-0_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Damen","year":"2018","unstructured":"Damen, D., et al.: Scaling egocentric vision: the epic-kitchens dataset. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 753\u2013771. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_44"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Duan, Y., Wei, F., Dai, Q., He, Y., Chen, W., Chen, B.: 4d-rotor gaussian splatting: towards efficient novel view synthesis for dynamic scenes. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657463"},{"key":"22_CR8","unstructured":"Engel, J., et al.: Project aria: a new tool for egocentric multi-modal AI research. arXiv preprint arXiv:2308.13561 (2023)"},{"key":"22_CR9","unstructured":"Engelmann, F., Manhardt, F., Niemeyer, M., Tateno, K., Pollefeys, M., Tombari, F.: OpenNeRF: open set 3D neural scene segmentation with pixel-wise features and rendered novel views. In: International Conference on Learning Representations (2024)"},{"key":"22_CR10","first-page":"33768","volume":"35","author":"H Gao","year":"2022","unstructured":"Gao, H., Li, R., Tulsiani, S., Russell, B., Kanazawa, A.: Monocular dynamic view synthesis: a reality check. Adv. Neural. Inf. Process. Syst. 35, 33768\u201333780 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR11","unstructured":"Grauman, K., et\u00a0al.: Ego-Exo4D: understanding skilled human activity from first-and third-person perspectives. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19383\u201319400 (2024)"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Gu, Q., et\u00a0al.: ConceptGraphs: open-vocabulary 3d scene graphs for perception and planning. In: IEEE International Conference on Robotics and Automation (2023)","DOI":"10.1109\/ICRA57147.2024.10610243"},{"issue":"2","key":"22_CR13","doi-asserted-by":"publisher","first-page":"3022","DOI":"10.1109\/LRA.2022.3145488","volume":"7","author":"Q Gu","year":"2022","unstructured":"Gu, Q., Okorn, B., Held, D.: OSSID: online self-supervised instance detection by (and for) pose estimation. IEEE Robot. Autom. Lett. 7(2), 3022\u20133029 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Howard, A., et\u00a0al.: Searching for mobileNetV3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Huang, C., Mees, O., Zeng, A., Burgard, W.: Audio visual language maps for robot navigation. In: Proceedings of the International Symposium on Experimental Robotics (ISER), Chiang Mai, Thailand (2023)","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Jatavallabhula, K.M., et al.: ConceptFusion: open-set multimodal 3D mapping. In: Robotics: Science and Systems (2023)","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Keetha, N., et al.: SplaTAM: splat track & map 3D Gaussians for dense RGB-D SLAM. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21357\u201321366 (2024)","DOI":"10.1109\/CVPR52733.2024.02018"},{"issue":"4","key":"22_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. (ToG) 42(4), 1\u201314 (2023)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.M., Goldberg, K., Kanazawa, A., Tancik, M.: LERF: language embedded radiance fields. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Kim, C.M., Wu, M., Kerr, J., Goldberg, K., Tancik, M., Kanazawa, A.: Garfield: group anything with radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21530\u201321539 (2024)","DOI":"10.1109\/CVPR52733.2024.02034"},{"key":"22_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"22_CR23","first-page":"23311","volume":"35","author":"S Kobayashi","year":"2022","unstructured":"Kobayashi, S., Matsumoto, E., Sitzmann, V.: Decomposing nerf for editing via feature field distillation. Adv. Neural. Inf. Process. Syst. 35, 23311\u201323330 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR24","unstructured":"Liu, K., et al.: 3D open-vocabulary segmentation with foundation models. arXiv preprint arXiv:2305.14093 (2023)"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"22_CR26","unstructured":"Lu, S., Chang, H., Jing, E.P., Boularias, A., Bekris, K.: OVIR-3D: open-vocabulary 3D instance retrieval without training on 3D data. In: Conference on Robot Learning, pp. 1610\u20131620. PMLR (2023)"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Luiten, J., Kopanas, G., Leibe, B., Ramanan, D.: Dynamic 3D Gaussians: tracking by persistent dynamic view synthesis. In: 2024 International Conference on 3D Vision (3DV), pp. 800\u2013809. IEEE (2024)","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"22_CR28","unstructured":"Lv, Z., et al.: Aria everyday activities dataset. arXiv preprint arXiv:2402.13349 (2024)"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Radwan, N., Sajjadi, M.S., Barron, J.T., Dosovitskiy, A., Duckworth, D.: NeRF in the wild: neural radiance fields for unconstrained photo collections. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7210\u20137219 (2021)","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Matsuki, H., Murai, R., Kelly, P.H., Davison, A.J.: Gaussian splatting slam. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18039\u201318048 (2024)","DOI":"10.1109\/CVPR52733.2024.01708"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Mazur, K., Sucar, E., Davison, A.J.: Feature-realistic neural fusion for real-time, open set scene understanding. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 8201\u20138207. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160800"},{"issue":"11","key":"22_CR32","doi-asserted-by":"publisher","first-page":"205","DOI":"10.21105\/joss.00205","volume":"2","author":"L McInnes","year":"2017","unstructured":"McInnes, L., Healy, J., Astels, S.: HDBSCAN: hierarchical density based clustering. J. Open Source Softw. 2(11), 205 (2017)","journal-title":"J. Open Source Softw."},{"issue":"1","key":"22_CR33","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","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. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Mirzaei, A., et al.: SPIn-NeRF: multiview segmentation and perceptual inpainting with neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20669\u201320679 (2023)","DOI":"10.1109\/CVPR52729.2023.01980"},{"key":"22_CR35","unstructured":"OpenAI: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"22_CR36","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Pan, X., et al.: Aria digital twin: a new benchmark dataset for egocentric 3D machine perception. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20133\u201320143 (2023)","DOI":"10.1109\/ICCV51070.2023.01842"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Peng, S., et\u00a0al.: OpenScene: 3D scene understanding with open vocabularies. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 815\u2013824 (2023)","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Qin, M., Li, W., Zhou, J., Wang, H., Pfister, H.: LangSplat: 3D language gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20051\u201320060 (2024)","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"22_CR40","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Ren, Z., Agarwala, A., Russell, B., Schwing, A.G., Wang, O.: Neural volumetric object selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6133\u20136142 (2022)","DOI":"10.1109\/CVPR52688.2022.00604"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015, Part III. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"22_CR44","unstructured":"Shafiullah, N.M.M., Paxton, C., Pinto, L., Chintala, S., Szlam, A.: Clip-fields: weakly supervised semantic fields for robotic memory. In: Bekris, K.E., Hauser, K., Herbert, S.L., Yu, J. (eds.) Robotics: Science and Systems (2023)"},{"key":"22_CR45","unstructured":"Shen, W., Yang, G., Yu, A., Wong, J., Kaelbling, L.P., Isola, P.: Distilled feature fields enable few-shot language-guided manipulation. In: 7th Annual Conference on Robot Learning (2023)"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Siddiqui, Y., et al.: Panoptic lifting for 3D scene understanding with neural fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9043\u20139052 (2023)","DOI":"10.1109\/CVPR52729.2023.00873"},{"key":"22_CR47","unstructured":"Straub, J., et al.: The replica dataset: a digital replica of indoor spaces. arXiv preprint arXiv:1906.05797 (2019)"},{"key":"22_CR48","unstructured":"Sun, J., Qiu, J., Zheng, C., Tucker, J., Yu, J., Schwager, M.: Aria-NeRF: multimodal egocentric view synthesis. arXiv preprint arXiv:2311.06455 (2023)"},{"key":"22_CR49","unstructured":"Takmaz, A., Fedele, E., Sumner, R.W., Pollefeys, M., Tombari, F., Engelmann, F.: OpenMask3D: open-vocabulary 3D instance segmentation. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"22_CR50","doi-asserted-by":"crossref","unstructured":"Tancik, M., et\u00a0al.: Nerfstudio: a modular framework for neural radiance field development. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201312 (2023)","DOI":"10.1145\/3588432.3591516"},{"key":"22_CR51","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: DreamGaussian: generative gaussian splatting for efficient 3D content creation. arXiv preprint arXiv:2309.16653 (2023)"},{"key":"22_CR52","unstructured":"Tsagkas, N., Mac\u00a0Aodha, O., Lu, C.X.: Vl-fields: towards language-grounded neural implicit spatial representations. arXiv preprint arXiv:2305.12427 (2023)"},{"key":"22_CR53","unstructured":"Tscherlnezki, V., et al.: Epic fields: marrying 3D geometry and video understanding. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"22_CR54","doi-asserted-by":"crossref","unstructured":"Tschernezki, V., Laina, I., Larlus, D., Vedaldi, A.: Neural feature fusion fields: 3D distillation of self-supervised 2D image representations. In: International Conference on 3D Vision (3DV). IEEE (2022)","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"22_CR55","doi-asserted-by":"crossref","unstructured":"Tschernezki, V., Larlus, D., Vedaldi, A.: NeuralDiff: segmenting 3D objects that move in egocentric videos. In: 2021 International Conference on 3D Vision (3DV), pp. 910\u2013919. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00099"},{"key":"22_CR56","doi-asserted-by":"crossref","unstructured":"Wu, G., et al.: 4D Gaussian splatting for real-time dynamic scene rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20310\u201320320 (2024)","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"22_CR57","doi-asserted-by":"crossref","unstructured":"Yan, C., et al.: GS-SLAM: dense visual slam with 3D Gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19595\u201319604 (2024)","DOI":"10.1109\/CVPR52733.2024.01853"},{"key":"22_CR58","unstructured":"Yan, Y., et al.: Street Gaussians for modeling dynamic urban scenes. arXiv preprint arXiv:2401.01339 (2024)"},{"key":"22_CR59","unstructured":"Yang, Z., Yang, H., Pan, Z., Zhu, X., Zhang, L.: Real-time photorealistic dynamic scene representation and rendering with 4D Gaussian splatting. arXiv preprint arXiv:2310.10642 (2023)"},{"key":"22_CR60","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gao, X., Zhou, W., Jiao, S., Zhang, Y., Jin, X.: Deformable 3D Gaussians for high-fidelity monocular dynamic scene reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20331\u201320341 (2024)","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"22_CR61","doi-asserted-by":"crossref","unstructured":"Ye, M., Danelljan, M., Yu, F., Ke, L.: Gaussian grouping: segment and edit anything in 3D scenes. arXiv preprint arXiv:2312.00732 (2023)","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"22_CR62","doi-asserted-by":"crossref","unstructured":"Yi, T., et al.: GaussianDreamer: fast generation from text to 3D Gaussians by bridging 2D and 3D diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"22_CR63","doi-asserted-by":"crossref","unstructured":"Ying, H., et al.: OmniSeg3D: omniversal 3D segmentation via hierarchical contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20612\u201320622 (2024)","DOI":"10.1109\/CVPR52733.2024.01948"},{"key":"22_CR64","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: Feature 3DGS: supercharging 3D Gaussian splatting to enable distilled feature fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21676\u201321685 (2024)","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"22_CR65","doi-asserted-by":"crossref","unstructured":"Zhou, X., Lin, Z., Shan, X., Wang, Y., Sun, D., Yang, M.H.: DrivingGaussian: composite Gaussian splatting for surrounding dynamic autonomous driving scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21634\u201321643 (2024)","DOI":"10.1109\/CVPR52733.2024.02044"},{"key":"22_CR66","doi-asserted-by":"crossref","unstructured":"Zuo, X., Samangouei, P., Zhou, Y., Di, Y., Li, M.: FMGS: foundation model embedded 3D gaussian splatting for holistic 3D scene understanding. arXiv preprint arXiv:2401.01970 (2024)","DOI":"10.1007\/s11263-024-02183-8"}],"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\/978-3-031-72775-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:21:52Z","timestamp":1732828912000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72775-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031727740","9783031727757"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72775-7_22","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"}}]}}