{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:23:38Z","timestamp":1792513418962,"version":"4.5.0"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729942","type":"print"},{"value":"9783031729959","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"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\/978-3-031-72995-9_23","type":"book-chapter","created":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T14:15:45Z","timestamp":1732371345000},"page":"403-420","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":55,"title":["Dolphins: Multimodal Language Model for\u00a0Driving"],"prefix":"10.1007","author":[{"given":"Yingzi","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiachen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Pavone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaowei","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"23_CR1","unstructured":"Openai chat. https:\/\/chat.openai.com. Accessed 20 Oct 2023"},{"key":"23_CR2","unstructured":"Openai chat. https:\/\/openai.com\/research\/gpt-4v-system-card. Accessed 20 Oct 2023"},{"key":"23_CR3","unstructured":"TinyChat: large language model on the edge. https:\/\/hanlab.mit.edu\/blog\/tinychat. Accessed 20 Oct 2023"},{"key":"23_CR4","unstructured":"What are embeddings? https:\/\/platform.openai.com\/docs\/guides\/embeddings\/what-are-embeddings. Accessed 20 Oct 2023"},{"key":"23_CR5","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. ArXiv preprint arxiv: abs\/2204.14198 (2022), https:\/\/api.semanticscholar.org\/CorpusID:248476411"},{"key":"23_CR6","unstructured":"Awadalla, A., et al.: OpenFlamingo: an open-source framework for training large autoregressive vision-language models. ArXiv abs\/2308.01390 (2023), https:\/\/api.semanticscholar.org\/CorpusID:261043320"},{"key":"23_CR7","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. arXiv preprint arXiv:1903.11027 (2019)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"23_CR9","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal LLM\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)"},{"key":"23_CR10","unstructured":"Chen, L., Wu, P., Chitta, K., Jaeger, B., Geiger, A., Li, H.: End-to-end autonomous driving: challenges and frontiers. arXiv preprint arXiv:2306.16927 (2023)"},{"key":"23_CR11","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* chatGPT quality (March 2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"23_CR12","doi-asserted-by":"publisher","first-page":"75296","DOI":"10.1109\/ACCESS.2022.3192019","volume":"10","author":"D Coelho","year":"2022","unstructured":"Coelho, D., Oliveira, M.: A review of end-to-end autonomous driving in urban environments. IEEE Access 10, 75296\u201375311 (2022)","journal-title":"IEEE Access"},{"key":"23_CR13","unstructured":"Contributors, D.: DriveLM: drive on language. https:\/\/github.com\/OpenDriveLab\/DriveLM (2023)"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Cui, C., et\u00a0al.: A survey on multimodal large language models for autonomous driving. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 958\u2013979 (2024)","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"23_CR15","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. ArXiv preprint arxiv: abs\/2305.06500 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258615266"},{"key":"23_CR16","unstructured":"Ding, X., Han, J., Xu, H., Zhang, W., Li, X.: HiLM-D: towards high-resolution understanding in multimodal large language models for autonomous driving. arXiv preprint arXiv:2309.05186 (2023)"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Ding, X., Han, J., Xu, H., Liang, X., Zhang, W., Li, X.: Holistic autonomous driving understanding by bird\u2019s-eye-view injected multi-modal large models. arXiv preprint arXiv:2401.00988 (2024)","DOI":"10.1109\/CVPR52733.2024.01297"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Fu, D., et al.: Drive like a human: rethinking autonomous driving with large language models. arXiv preprint arXiv:2307.07162 (2023)","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"23_CR20","unstructured":"Han, W., Guo, D., Xu, C.Z., Shen, J.: DME-driver: integrating human decision logic and 3D scene perception in autonomous driving. arXiv preprint arXiv:2401.03641 (2024)"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"23_CR22","unstructured":"Jain, A., Del\u00a0Pero, L., Grimmett, H., Ondruska, P.: Autonomy 2.0: why is self-driving always 5 years away? arXiv preprint arXiv:2107.08142 (2021)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Jin, B., et al.: Adapt: action-aware driving caption transformer. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 7554\u20137561 (2023). https:\/\/api.semanticscholar.org\/CorpusID:256459842","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"23_CR24","unstructured":"Jin, Y., et al.: SurrealDriver: designing generative driver agent simulation framework in urban contexts based on large language model. arXiv preprint arXiv:2309.13193 (2023)"},{"issue":"6245","key":"23_CR25","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1126\/science.aaa8415","volume":"349","author":"MI Jordan","year":"2015","unstructured":"Jordan, M.I., Mitchell, T.M.: Machine learning: trends, perspectives, and prospects. Science 349(6245), 255\u2013260 (2015)","journal-title":"Science"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Kafle, K., Kanan, C.: An analysis of visual question answering algorithms. In: Proceedings of the IEEE international conference on computer vision. pp. 1965\u20131973 (2017)","DOI":"10.1109\/ICCV.2017.217"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Kim, J., Rohrbach, A., Darrell, T., Canny, J., Akata, Z.: Textual explanations for self-driving vehicles. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 563\u2013578 (2018)","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Kim, J., Rohrbach, A., Darrell, T., Canny, J.F., Akata, Z.: Textual explanations for self-driving vehicles. In: European Conference on Computer Vision (2018). https:\/\/api.semanticscholar.org\/CorpusID:51887402","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"23_CR29","unstructured":"Li, B., et al.: Mimic-it: multi-modal in-context instruction tuning. arXiv preprint arxiv: abs\/2306.05425 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259108295"},{"key":"23_CR30","unstructured":"Li, B., Zhang, Y., Chen, L., Wang, J., Yang, J., Liu, Z.: Otter: a multi-modal model with in-context instruction tuning. arXiv preprint arxiv: abs\/2305.03726 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258547300"},{"key":"23_CR31","unstructured":"Li, C., et al.: LLaVA-med: training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)"},{"key":"23_CR32","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.C.H.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arxiv: abs\/2301.12597 (2023). https:\/\/api.semanticscholar.org\/CorpusID:256390509"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Li, W., et\u00a0al.: AADS: augmented autonomous driving simulation using data-driven algorithms. Sci. robot. 4(28), eaaw0863 (2019)","DOI":"10.1126\/scirobotics.aaw0863"},{"key":"23_CR34","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arxiv:abs\/2304.08485 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258179774"},{"key":"23_CR35","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"issue":"8","key":"23_CR36","doi-asserted-by":"publisher","first-page":"6469","DOI":"10.1109\/JIOT.2020.3043716","volume":"8","author":"L Liu","year":"2020","unstructured":"Liu, L., et al.: Computing systems for autonomous driving: state of the art and challenges. IEEE Internet Things J. 8(8), 6469\u20136486 (2020)","journal-title":"IEEE Internet Things J."},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"23_CR38","unstructured":"Luo, R., et al.: Valley: video assistant with large language model enhanced ability. arXiv preprint arxiv: abs\/2306.07207 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259138706"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-chatGPT: towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"23_CR40","unstructured":"Mao, J., Qian, Y., Zhao, H., Wang, Y.: GPT-driver: learning to drive with GPT. arXiv preprint arxiv: abs\/2310.01415 (2023). https:\/\/api.semanticscholar.org\/CorpusID:263605637"},{"key":"23_CR41","unstructured":"Mao, J., Ye, J., Qian, Y., Pavone, M., Wang, Y.: A language agent for autonomous driving. arXiv preprint arXiv:2311.10813 (2023)"},{"key":"23_CR42","unstructured":"Marcu, A.M., et\u00a0al.: LingoQA: video question answering for autonomous driving. arXiv preprint arXiv:2312.14115 (2023)"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Ok-VQA: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE\/cvf Conference on Computer Vision and Pattern Recognition, pp. 3195\u20133204 (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"23_CR44","unstructured":"Mom, G.: The Evolution of Automotive Technology: A Handbook. SAE International (2023)"},{"key":"23_CR45","unstructured":"Mu, Y., et al.: EmbodiedGPT: vision-language pre-training via embodied chain of thought. arXiv preprint arXiv:2305.15021 (2023)"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Rubin, O., Herzig, J., Berant, J.: Learning to retrieve prompts for in-context learning. arXiv preprint arXiv:2112.08633 (2021)","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"23_CR48","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. arXiv preprint arxiv: abs\/2210.08402 (2022). https:\/\/api.semanticscholar.org\/CorpusID:252917726"},{"key":"23_CR49","doi-asserted-by":"crossref","unstructured":"Shao, H., Hu, Y., Wang, L., Waslander, S.L., Liu, Y., Li, H.: LMDrive: closed-loop end-to-end driving with large language models. arXiv preprint arXiv:2312.07488 (2023)","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"23_CR50","doi-asserted-by":"crossref","unstructured":"Soori, M., Arezoo, B., Dastres, R.: Artificial intelligence, machine learning and deep learning in advanced robotics, a review. Cognitive Robot. 3, 54\u201370 (2023)","DOI":"10.1016\/j.cogr.2023.04.001"},{"issue":"4","key":"23_CR51","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1109\/TNNLS.2020.3043505","volume":"33","author":"A Tampuu","year":"2020","unstructured":"Tampuu, A., Matiisen, T., Semikin, M., Fishman, D., Muhammad, N.: A survey of end-to-end driving: architectures and training methods. IEEE Trans. Neural Netw. Learn. Syst. 33(4), 1364\u20131384 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"23_CR52","unstructured":"Team, M.N.: Introducing MPT-7B: a new standard for open-source, commercially usable LLMs (2023). www.mosaicml.com\/blog\/mpt-7b. Accessed 05 May 2023"},{"key":"23_CR53","unstructured":"Tian, X., et al.: DriveVLM: the convergence of autonomous driving and large vision-language models. arXiv preprint arXiv:2402.12289 (2024)"},{"key":"23_CR54","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv preprint arxiv: abs\/2302.13971 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257219404"},{"key":"23_CR55","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"23_CR56","unstructured":"Touvron, H., et al.: LLaMA 2: open foundation and fine-tuned chat models. ArXiv abs\/2307.09288 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259950998"},{"key":"23_CR57","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"23_CR58","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence-video to text. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"23_CR59","unstructured":"Wang, W., et\u00a0al.: DriveMLM: aligning multi-modal large language models with behavioral planning states for autonomous driving. arXiv preprint arXiv:2312.09245 (2023)"},{"issue":"1","key":"23_CR60","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1109\/MITS.2020.3014152","volume":"13","author":"K Wong","year":"2020","unstructured":"Wong, K., Gu, Y., Kamijo, S.: Mapping for autonomous driving: opportunities and challenges. IEEE Intell. Transp. Syst. Mag. 13(1), 91\u2013106 (2020)","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"23_CR61","unstructured":"Wu, D., Han, W., Wang, T., Liu, Y.H., Zhang, X., Shen, J.: Language prompt for autonomous driving. arXiv preprint arxiv: abs\/2309.04379 (2023). https:\/\/api.semanticscholar.org\/CorpusID:261660217"},{"key":"23_CR62","unstructured":"Xu, Z., et al.: DriveGPT4: interpretable end-to-end autonomous driving via large language model. arXiv preprint arxiv: abs\/2310.01412 (2023). https:\/\/api.semanticscholar.org\/CorpusID:263605524"},{"key":"23_CR63","unstructured":"Yang, S., et al.: LiDAR-LLM: exploring the potential of large language models for 3D lidar understanding. arXiv preprint arXiv:2312.14074 (2023)"},{"key":"23_CR64","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2636\u20132645 (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"23_CR65","doi-asserted-by":"crossref","unstructured":"Yuan, J., Sun, S., Omeiza, D., Zhao, B., Newman, P., Kunze, L., Gadd, M.: RAG-driver: generalisable driving explanations with retrieval-augmented in-context learning in multi-modal large language model. arXiv preprint arXiv:2402.10828 (2024)","DOI":"10.15607\/RSS.2024.XX.075"},{"key":"23_CR66","unstructured":"Yuan, W., Pang, R.Y., Cho, K., Sukhbaatar, S., Xu, J., Weston, J.: Self-rewarding language models. arXiv preprint arXiv:2401.10020 (2024)"},{"key":"23_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-LLaMA: an instruction-tuned audio-visual language model for video understanding. arXiv preprint arxiv: abs\/2306.02858 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259075356","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"23_CR68","unstructured":"Zhang, S., et al.: GPT4RoI: instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601 (2023)"},{"key":"23_CR69","unstructured":"Zhao, B., Wu, B., Huang, T.: SVIT: scaling up visual instruction tuning. arXiv preprint arXiv:2307.04087 (2023)"},{"key":"23_CR70","unstructured":"Zhao, H., et al.: MMICL: empowering vision-language model with multi-modal in-context learning. arXiv preprint arXiv:2309.07915 (2023)"},{"key":"23_CR71","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arxiv: abs\/2304.10592 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258291930"},{"key":"23_CR72","unstructured":"Zhu, W., et al.: Multimodal c4: An open, billion-scale corpus of images interleaved with text. arXiv preprint arxiv: abs\/2304.06939 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258170467"}],"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\/978-3-031-72995-9_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T15:06:27Z","timestamp":1732374387000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72995-9_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031729942","9783031729959"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72995-9_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"24 November 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"}}]}}