{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:30:52Z","timestamp":1778347852971,"version":"3.51.4"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726484","type":"print"},{"value":"9783031726491","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\/978-3-031-72649-1_21","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"367-384","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["TOD3Cap: Towards 3D Dense Captioning in\u00a0Outdoor Scenes"],"prefix":"10.1007","author":[{"given":"Bu","family":"Jin","sequence":"first","affiliation":[]},{"given":"Yupeng","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Pengfei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Weize","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yuhang","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Sujie","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Xinyu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jinwei","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Zhijie","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Haiyang","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Zhan","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Xiaoxiao","family":"Long","sequence":"additional","affiliation":[]},{"given":"Yilun","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"21_CR1","doi-asserted-by":"publisher","unstructured":"Achlioptas, P., Abdelreheem, A., Xia, F., Elhoseiny, M., Guibas, L.: Referit3D: neural listeners for fine-grained 3D object identification in real-world scenes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Proceedings, Part I 16, pp. 422\u2013440. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_25","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"21_CR2","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":"21_CR3","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":"21_CR4","doi-asserted-by":"crossref","unstructured":"Cai, D., Zhao, L., Zhang, J., Sheng, L., Xu, D.: 3DJCG: a unified framework for joint dense captioning and visual grounding on 3D point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16464\u201316473 (2022)","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"21_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"21_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/978-3-030-58565-5_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"DZ Chen","year":"2020","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: ScanRefer: 3D object localization in RGB-D scans using natural language. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 202\u2013221. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_13"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Wu, Q., Nie\u00dfner, M., Chang, A.X.: D3Net: a speaker-listener architecture for semi-supervised dense captioning and visual grounding in RGB-D scans. arXiv preprint arXiv:2112.01551, 2021.3 (2021)","DOI":"10.1007\/978-3-031-19824-3_29"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Chen, D.Y., Tian, X.P., Shen, Y.T., Ouhyoung, M.: On visual similarity based 3D model retrieval. Comput. Graph. Forum 22, 223\u2013232 (2003). Wiley Online Library","DOI":"10.1111\/1467-8659.00669"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: LL3DA: visual interactive instruction tuning for Omni-3D understanding, reasoning, and planning. arXiv preprint arXiv:2311.18651 (2023)","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhu, H., Chen, X., Lei, Y., Yu, G., Chen, T.: End-to-end 3D dense captioning with Vote2Cap-DETR. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11124\u201311133 (2023)","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Vote2Cap-DETR++: decoupling localization and describing for end-to-end 3D dense captioning. arXiv preprint arXiv:2309.02999 (2023)","DOI":"10.1109\/TPAMI.2024.3387838"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Z., Gholami, A., Nie\u00dfner, M., Chang, A.X.: Scan2Cap: context-aware dense captioning in RGB-D scans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3193\u20133203 (2021)","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Z., Hu, R., Chen, X., Nie\u00dfner, M., Chang, A.X.: Unit3D: a unified transformer for 3D dense captioning and visual grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18109\u201318119 (2023)","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"21_CR14","unstructured":"Cheng, S., et al.: Can vision-language models think from a first-person perspective? arXiv preprint arXiv:2311.15596 (2023)"},{"key":"21_CR15","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":"21_CR16","doi-asserted-by":"crossref","unstructured":"Deitke, M., et\u00a0al.: Objaverse-XL: a universe of 10M+ 3D objects. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Delitzas, A., Takmaz, A., Tombari, F., Sumner, R., Pollefeys, M., Engelmann, F.: SceneFun3D: fine-grained functionality and affordance understanding in 3D scenes. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01377"},{"key":"21_CR19","unstructured":"Hong, Y., et al.: 3D-LLM: injecting the 3D world into large language models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Hu, A., et al.: FIERY: future instance prediction in bird\u2019s-eye view from surround monocular cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Huang, C., Mees, O., Zeng, A., Burgard, W.: Visual language maps for robot navigation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 10608\u201310615. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"21_CR22","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"issue":"3","key":"21_CR23","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1109\/TCYB.2018.2879846","volume":"50","author":"X Huang","year":"2018","unstructured":"Huang, X., Peng, Y., Yuan, M.: MHTN: modal-adversarial hybrid transfer network for cross-modal retrieval. IEEE Trans. Cybern. 50(3), 1047\u20131059 (2018)","journal-title":"IEEE Trans. Cybern."},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Jia, B., et al.: SceneVerse: scaling 3D vision-language learning for grounded scene understanding. arXiv preprint arXiv:2401.09340 (2024)","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"21_CR25","doi-asserted-by":"publisher","unstructured":"Jiao, Y., Chen, S., Jie, Z., Chen, J., Ma, L., Jiang, Y.G.: MORE: multi-order relation mining for dense captioning in 3D scenes. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13695, pp. 528\u2013545. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_31","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Jin, B., et al.: ADAPT: action-aware driving caption transformer. arXiv preprint arXiv:2302.00673 (2023)","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"21_CR28","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"21_CR29","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: BEVFusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 2774\u20132781. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"21_CR31","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"21_CR32","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR33","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":"21_CR34","doi-asserted-by":"publisher","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.) Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Proceedings, Part XIV 16. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"21_CR35","unstructured":"Pidathala, P., Franz, D., Waller, J., Kushalnagar, R., Vogler, C.: Live captions in virtual reality (VR). arXiv preprint arXiv:2210.15072 (2022)"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep Hough voting for 3D object detection in point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Qian, T., Chen, J., Zhuo, L., Jiao, Y., Jiang, Y.G.: NuScenes-QA: a multi-modal visual question answering benchmark for autonomous driving scenario. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 4542\u20134550 (2024)","DOI":"10.1609\/aaai.v38i5.28253"},{"issue":"8","key":"21_CR38","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Sachdeva, E., et al.: Rank2Tell: a multimodal driving dataset for joint importance ranking and reasoning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 7513\u20137522 (2024)","DOI":"10.1109\/WACV57701.2024.00734"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Saha, A., Mendez, O., Russell, C., Bowden, R.: Translating images into maps. In: 2022 International Conference on Robotics and Automation (ICRA) (2022)","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Savva, M., et\u00a0al.: Habitat: a platform for embodied AI research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9339\u20139347 (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"21_CR42","unstructured":"Sima, C., et al.: DriveLM: driving with graph visual question answering. arXiv preprint arXiv:2312.14150 (2023)"},{"key":"21_CR43","unstructured":"Tian, X., et al.: DriveVLM: the convergence of autonomous driving and large vision-language models. arXiv preprint arXiv:2402.12289 (2024)"},{"key":"21_CR44","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":"21_CR45","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, C., Yu, J., Cai, W.: Spatiality-guided transformer for 3D dense captioning on point clouds. arXiv preprint arXiv:2204.10688 (2022)","DOI":"10.24963\/ijcai.2022\/194"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6629\u20136638 (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"21_CR48","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: DETR3D: 3D object detection from multi-view images via 3D-to-2D queries. In: Conference on Robot Learning, pp. 180\u2013191. PMLR (2022)"},{"key":"21_CR49","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":"21_CR50","doi-asserted-by":"crossref","unstructured":"Yu, T., Lin, X., Wang, S., Sheng, W., Huang, Q., Yu, J.: A comprehensive survey of 3D dense captioning: localizing and describing objects in 3D scenes. IEEE Trans. Circ. Syst. Video Technol. (2023)","DOI":"10.1109\/TCSVT.2023.3296889"},{"key":"21_CR51","doi-asserted-by":"crossref","unstructured":"Yuan, Z., et al.: X-Trans2Cap: cross-modal knowledge transfer using transformer for 3D dense captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8563\u20138573 (2022)","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"21_CR52","unstructured":"Zhang, R., et al.: LLaMA-adapter: efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)"},{"key":"21_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Gong, Z., Chang, A.X.: Multi3DRefer: grounding text description to multiple 3D objects. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15225\u201315236 (2023)","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"21_CR54","unstructured":"Zhong, Y., Xu, L., Luo, J., Ma, L.: Contextual modeling for 3D dense captioning on point clouds. arXiv preprint arXiv:2210.03925 (2022)"},{"key":"21_CR55","doi-asserted-by":"crossref","unstructured":"Zhu, F., Zhu, Y., Chang, X., Liang, X.: Vision-language navigation with self-supervised auxiliary reasoning tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10012\u201310022 (2020)","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"21_CR56","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Ma, X., Chen, Y., Deng, Z., Huang, S., Li, Q.: 3D-VisTa: pre-trained transformer for 3D vision and text alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2911\u20132921 (2023)","DOI":"10.1109\/ICCV51070.2023.00272"}],"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\/978-3-031-72649-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:18:53Z","timestamp":1732828733000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72649-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726484","9783031726491"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72649-1_21","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"}}]}}