{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:10:30Z","timestamp":1789035030846,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371959","type":"print"},{"value":"9783032371966","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\/978-3-032-37196-6_3","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:34:24Z","timestamp":1789032864000},"page":"37-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OccDirector: Language-Guided Behavior and\u00a0Interaction Generation in\u00a04D Occupancy Space"],"prefix":"10.1007","author":[{"given":"Zhuding","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dubing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiasen","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-zhong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yida","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"issue":"24","key":"3_CR1","doi-asserted-by":"publisher","first-page":"9577","DOI":"10.3390\/s22249577","volume":"22","author":"SY Alaba","year":"2022","unstructured":"Alaba, S.Y., Ball, J.E.: A survey on deep-learning-based lidar 3D object detection for autonomous driving. Sensors 22(24), 9577 (2022)","journal-title":"Sensors"},{"key":"3_CR2","unstructured":"Barratt, S., Sharma, R.: A note on the inception score. arXiv preprint arXiv:1801.01973 (2018)"},{"key":"3_CR3","unstructured":"Bian, H., Kong, L., Xie, H., Pan, L., Qiao, Y., Liu, Z.: Dynamiccity: large-scale 4D occupancy generation from dynamic scenes. arXiv preprint arXiv:2410.18084 (2024)"},{"key":"3_CR4","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. arXiv preprint arXiv:1801.01401 (2018)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"issue":"12","key":"3_CR6","doi-asserted-by":"publisher","first-page":"10164","DOI":"10.1109\/TPAMI.2024.3435937","volume":"46","author":"L Chen","year":"2024","unstructured":"Chen, L., Wu, P., Chitta, K., Jaeger, B., Geiger, A., Li, H.: End-to-end autonomous driving: challenges and frontiers. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 10164\u201310183 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Chen, R., et al.: Unimlvg: unified framework for multi-view long video generation with comprehensive control capabilities for autonomous driving. arXiv preprint arXiv:2412.04842 (2024)","DOI":"10.1109\/ICCV51701.2025.02361"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Diehl, C., Sykora, Q., Agro, B., Gilles, T., Casas, S., Urtasun, R.: DIO: decomposable implicit 4D occupancy-flow world model. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 27456\u201327466 (2025)","DOI":"10.1109\/CVPR52734.2025.02557"},{"issue":"3","key":"3_CR9","doi-asserted-by":"publisher","first-page":"3870","DOI":"10.1109\/JIOT.2025.3635092","volume":"13","author":"W Dong","year":"2025","unstructured":"Dong, W., et al.: End-to-end autonomous driving: from classic paradigm to large model empowerment\u2013a comprehensive survey. IEEE Internet Things J. 13(3), 3870\u20133898 (2025)","journal-title":"IEEE Internet Things J."},{"key":"3_CR10","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Gao, R., Chen, K., Xiao, B., Hong, L., Li, Z., Xu, Q.: Magicdrive-v2: high-resolution long video generation for autonomous driving with adaptive control. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 28135\u201328144 (2025)","DOI":"10.1109\/ICCV51701.2025.02612"},{"key":"3_CR12","unstructured":"Gao, R., et al.: Magicdrive: street view generation with diverse 3D geometry control. arXiv preprint arXiv:2310.02601 (2023)"},{"key":"3_CR13","doi-asserted-by":"publisher","first-page":"91560","DOI":"10.52202\/079017-2906","volume":"37","author":"S Gao","year":"2024","unstructured":"Gao, S., et al.: Vista: a generalizable driving world model with high fidelity and versatile controllability. Adv. Neural. Inf. Process. Syst. 37, 91560\u201391596 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR14","unstructured":"Gu, S., et al.: Dome: taming diffusion model into high-fidelity controllable occupancy world model. arXiv preprint arXiv:2410.10429 (2024)"},{"key":"3_CR15","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, p. 30 (2017)"},{"key":"3_CR16","unstructured":"Hu, A., et al.: Gaia-1: a generative world model for autonomous driving. arXiv preprint arXiv:2309.17080 (2023)"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Khurana, T., Hu, P., Held, D., Ramanan, D.: Point cloud forecasting as a proxy for 4D occupancy forecasting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1116\u20131124 (2023)","DOI":"10.1109\/CVPR52729.2023.00114"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Kim, S.W., Philion, J., Torralba, A., Fidler, S.: Drivegan: towards a controllable high-quality neural simulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5820\u20135829 (2021)","DOI":"10.1109\/CVPR46437.2021.00576"},{"key":"3_CR19","unstructured":"Koishigarina, D., Uselis, A., Oh, S.J.: Clip behaves like a bag-of-words model cross-modally but not UNI-modally. arXiv preprint arXiv:2502.03566 (2025)"},{"key":"3_CR20","unstructured":"Kong, W., et al.: Hunyuanvideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Lee, J., Lee, S., Jo, C., Im, W., Seon, J., Yoon, S.E.: Semcity: semantic scene generation with triplane diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28337\u201328347 (2024)","DOI":"10.1109\/CVPR52733.2024.02677"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Li, B., et al.: Uniscene: unified occupancy-centric driving scene generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 11971\u201311981 (2025)","DOI":"10.1109\/CVPR52734.2025.01118"},{"key":"3_CR23","unstructured":"Li, L., et al.: Data-centric evolution in autonomous driving: a comprehensive survey of big data system, data mining, and closed-loop technologies. arXiv preprint arXiv:2401.12888 (2024)"},{"key":"3_CR24","unstructured":"Liang, A., et al.: Worldlens: full-spectrum evaluations of driving world models in real world. arXiv preprint arXiv:2512.10958 (2025)"},{"key":"3_CR25","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"3_CR26","unstructured":"Liu, Y., et al.: Sora: a review on background, technology, limitations, and opportunities of large vision models. arXiv preprint arXiv:2402.17177 (2024)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Ma, B., Zong, Z., Song, G., Li, H., Liu, Y.: Exploring the role of large language models in prompt encoding for diffusion models. arXiv preprint arXiv:2406.11831 (2024)","DOI":"10.52202\/079017-3760"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Ma, J., et al.: Cam4docc: benchmark for camera-only 4D occupancy forecasting in autonomous driving applications. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21486\u201321495 (2024)","DOI":"10.1109\/CVPR52733.2024.02030"},{"key":"3_CR29","unstructured":"Ma, X., et al.: Latte: latent diffusion transformer for video generation. arXiv preprint arXiv:2401.03048 (2024)"},{"key":"3_CR30","unstructured":"Mei, J., et al.: Dreamforge: motion-aware autoregressive video generation for multi-view driving scenes. arXiv preprint arXiv:2409.04003 (2024)"},{"key":"3_CR31","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"issue":"140","key":"3_CR32","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR33","unstructured":"Ruan, B.K., Tsui, H.T., Li, Y.H., Shuai, H.H.: Traffic scene generation from natural language description for autonomous vehicles with large language model. arXiv preprint arXiv:2409.09575 (2024)"},{"key":"3_CR34","unstructured":"Russell, L., et al.: Gaia-2: a controllable multi-view generative world model for autonomous driving. arXiv preprint arXiv:2503.20523 (2025)"},{"key":"3_CR35","doi-asserted-by":"publisher","first-page":"36479","DOI":"10.52202\/068431-2643","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Shi, Y., et al.: Come: adding scene-centric forecasting control to occupancy world model. arXiv preprint arXiv:2506.13260 (2025)","DOI":"10.52202\/085713-0004"},{"key":"3_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"3_CR39","doi-asserted-by":"publisher","first-page":"64318","DOI":"10.52202\/075280-2809","volume":"36","author":"X Tian","year":"2023","unstructured":"Tian, X., et al.: Occ3d: a large-scale 3D occupancy prediction benchmark for autonomous driving. Adv. Neural. Inf. Process. Syst. 36, 64318\u201364330 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Tong, S., et al.: Metamorph: multimodal understanding and generation via instruction tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17001\u201317012 (2025)","DOI":"10.1109\/ICCV51701.2025.01579"},{"key":"3_CR41","unstructured":"Tong, W., et al.: Scene as occupancy. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8406\u20138415 (2023)"},{"key":"3_CR42","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"3_CR43","unstructured":"Wan, T., et al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"3_CR44","unstructured":"Wang, L., et al.: Occsora: 4D occupancy generation models as world simulators for autonomous driving. arXiv preprint arXiv:2405.20337 (2024)"},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, Z., Huang, G., Chen, X., Zhu, J., Lu, J.: Drivedreamer: towards real-world-drive world models for autonomous driving. In: European Conference on Computer Vision, pp. 55\u201372. Springer (2024)","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Openoccupancy: a large scale benchmark for surrounding semantic occupancy perception. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17850\u201317859 (2023)","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Uniocc: a unified benchmark for occupancy forecasting and prediction in autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 25560\u201325570 (2025)","DOI":"10.1109\/ICCV51701.2025.02371"},{"issue":"3","key":"3_CR48","doi-asserted-by":"publisher","first-page":"8439","DOI":"10.1109\/LRA.2022.3188435","volume":"7","author":"J Wilson","year":"2022","unstructured":"Wilson, J., et al.: Motionsc: data set and network for real-time semantic mapping in dynamic environments. IEEE Robot. Autom. Lett. 7(3), 8439\u20138446 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"3_CR49","unstructured":"Wu, C., et al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"3_CR50","doi-asserted-by":"crossref","unstructured":"Wu, C., et al.: Janus: decoupling visual encoding for unified multimodal understanding and generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12966\u201312977 (2025)","DOI":"10.1109\/CVPR52734.2025.01210"},{"key":"3_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102671","volume":"114","author":"H Xu","year":"2025","unstructured":"Xu, H., Chen, J., Meng, S., Wang, Y., Chau, L.P.: A survey on occupancy perception for autonomous driving: the information fusion perspective. Inf. Fusion 114, 102671 (2025)","journal-title":"Inf. Fusion"},{"key":"3_CR52","unstructured":"Yang, A., et al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"3_CR53","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Mmada: multimodal large diffusion language models. arXiv preprint arXiv:2505.15809 (2025)","DOI":"10.52202\/085713-4636"},{"key":"3_CR54","doi-asserted-by":"crossref","unstructured":"Yang, Y., Liang, A., Mei, J., Ma, Y., Liu, Y., Lee, G.H.: X-scene: large-scale driving scene generation with high fidelity and flexible controllability. arXiv preprint arXiv:2506.13558 (2025)","DOI":"10.52202\/085713-3487"},{"key":"3_CR55","unstructured":"Yang, Z., et al.: Geniedrive: towards physics-aware driving world model with 4D occupancy guided video generation. arXiv preprint arXiv:2512.12751 (2025)"},{"key":"3_CR56","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., Zou, J.: When and why vision-language models behave like bags-of-words, and what to do about it? arXiv preprint arXiv:2210.01936 (2022)"},{"key":"3_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhu, Z., Du, D.: Occformer: dual-path transformer for vision-based 3D semantic occupancy prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9433\u20139443 (2023)","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"3_CR58","doi-asserted-by":"crossref","unstructured":"Zhao, G., et al.: Drivedreamer-2: LLM-enhanced world models for diverse driving video generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 10412\u201310420 (2025)","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"3_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. In: European Conference on Computer Vision, pp. 55\u201372. Springer (2024)","DOI":"10.1007\/978-3-031-72624-8_4"}],"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\/978-3-032-37196-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:34:45Z","timestamp":1789032885000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37196-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371959","9783032371966"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37196-6_3","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":"11 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"}}]}}