{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:56:30Z","timestamp":1784044590104,"version":"3.55.0"},"publisher-location":"Cham","reference-count":85,"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_3","type":"book-chapter","created":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T19:17:15Z","timestamp":1732389435000},"page":"36-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["V-IRL: Grounding Virtual Intelligence in\u00a0Real Life"],"prefix":"10.1007","author":[{"given":"Jihan","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runyu","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ellis","family":"Brown","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saining","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"3_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"3_CR2","unstructured":"Alayrac, J.B., et\u00a0al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS (2022)"},{"key":"3_CR3","unstructured":"Anderson, P., et\u00a0al.: On evaluation of embodied navigation agents. arXiv preprint arXiv:1807.06757 (2018)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"3_CR5","unstructured":"Anil, R., et\u00a0al.: PaLM 2 technical report. arXiv preprint arXiv:2305.10403 (2023)"},{"key":"3_CR6","unstructured":"Asano, Y.M., Rupprecht, C., Zisserman, A., Vedaldi, A.: PASS: an ImageNet replacement for self-supervised pretraining without humans. In: NeurIPS (2021)"},{"key":"3_CR7","unstructured":"Awadalla, A., et\u00a0al.: OpenFlamingo: an open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390 (2023)"},{"key":"3_CR8","unstructured":"Berner, C., et\u00a0al.: Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)"},{"key":"3_CR9","unstructured":"Brohan, A., et al.: RT-2: vision-language-action models transfer web knowledge to robotic control. arXiv preprint arXiv:2307.15818 (2023)"},{"key":"3_CR10","unstructured":"Brohan, A., et\u00a0al.: Do as I can, not as I say: grounding language in robotic affordances. In: CoRL (2023)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: 3DV (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"3_CR12","unstructured":"Chaplot, D.S., Gandhi, D.P., Gupta, A., Salakhutdinov, R.R.: Object goal navigation using goal-oriented semantic exploration. In: NeurIPS (2020)"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Chen, H., Suhr, A., Misra, D., Snavely, N., Artzi, Y.: TOUCHDOWN: natural language navigation and spatial reasoning in visual street environments. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01282"},{"key":"3_CR14","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":"3_CR15","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"3_CR16","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: NeurIPS (2023)"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Ding, R., Yang, J., Xue, C., Zhang, W., Bai, S., Qi, X.: PLA: language-driven open-vocabulary 3D scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7010\u20137019 (2023)","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Ding, R., Yang, J., Xue, C., Zhang, W., Bai, S., Qi, X.: Lowis3D: language-driven open-world instance-level 3D scene understanding. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3410324"},{"key":"3_CR20","unstructured":"Driess, D., et al.: PaLM-E: an embodied multimodal language model. In: ICML (2023)"},{"key":"3_CR21","unstructured":"Du, Y., et\u00a0al.: PP-OCR: a practical ultra lightweight OCR system. arxiv 2020. arXiv preprint arXiv:2009.09941 (2020)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Dubey, A., Ramanathan, V., Pentland, A., Mahajan, D.: Adaptive methods for real-world domain generalization. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01411"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Gu, X., Cui, Y., Lin, T.Y.: Scaling open-vocabulary image segmentation with image-level labels. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"3_CR24","unstructured":"Google Map Team: Google map platform. https:\/\/mapsplatform.google.com\/"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"3_CR26","unstructured":"Hong, S., et al.: MetaGPT: meta programming for a multi-agent collaborative framework. In: ICLR (2023)"},{"key":"3_CR27","unstructured":"Huang, W., Abbeel, P., Pathak, D., Mordatch, I.: Language models as zero-shot planners: extracting actionable knowledge for embodied agents. In: ICML (2022)"},{"key":"3_CR28","unstructured":"Huang, W., Wang, C., Zhang, R., Li, Y., Wu, J., Fei-Fei, L.: VoxPoser: composable 3D value maps for robotic manipulation with language models. arXiv preprint arXiv:2307.05973 (2023)"},{"key":"3_CR29","unstructured":"Huang, W., et\u00a0al.: Inner Monologue: embodied reasoning through planning with language models. In: CoRL (2022)"},{"key":"3_CR30","unstructured":"K\u00fcttler, H., et al.: The NetHack learning environment. In: NeurIPS (2020)"},{"issue":"7","key":"3_CR31","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset V4. Int. J. Comput. Vis. 128(7), 1956\u20131981 (2020). https:\/\/doi.org\/10.1007\/s11263-020-01316-z","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR32","unstructured":"Lauren\u00e7on, H., et\u00a0al.: OBELICS: an open web-scale filtered dataset of interleaved image-text documents. In: NeurIPS (2023)"},{"key":"3_CR33","unstructured":"Li, A.C., Brown, E., Efros, A.A., Pathak, D.: Internet Explorer: targeted representation learning on the open web. In: International Conference on Machine Learning, pp. 19385\u201319406. PMLR (2023)"},{"key":"3_CR34","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation. In: ICLR (2022)"},{"key":"3_CR35","unstructured":"Li, G., Hammoud, H.A.A.K., Itani, H., Khizbullin, D., Ghanem, B.: CAMEL: communicative agents for mind exploration of large language model society. In: NeurIPS (2023)"},{"key":"3_CR36","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Liang, J., et al.: Code as Policies: language model programs for embodied control. In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"Lin, K., Agia, C., Migimatsu, T., Pavone, M., Bohg, J.: Text2Motion: from natural language instructions to feasible plans. arXiv preprint arXiv:2303.12153 (2023)","DOI":"10.1007\/s10514-023-10131-7"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Lindenberger, P., Sarlin, P.E., Pollefeys, M.: LightGlue: local feature matching at light speed. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"3_CR42","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"3_CR43","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":"3_CR44","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281 (2023)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"3_CR45","unstructured":"Liu, Z., Bahety, A., Song, S.: REFLECT: summarizing robot experiences for failure explanation and correction. In: CoRL (2023)"},{"key":"3_CR46","unstructured":"Makoviychuk, V., et\u00a0al.: Isaac Gym: high performance GPU-based physics simulation for robot learning. In: NeurIPS (2021)"},{"key":"3_CR47","unstructured":"Minderer, M., Gritsenko, A., Houlsby, N.: Scaling open-vocabulary object detection. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"3_CR48","doi-asserted-by":"publisher","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13670, pp. 728\u2013755. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"3_CR49","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"3_CR50","unstructured":"Nakano, R., et\u00a0al.: WebGPT: browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332 (2021)"},{"key":"3_CR51","doi-asserted-by":"crossref","unstructured":"Park, J.S., O\u2019Brien, J., Cai, C.J., Morris, M.R., Liang, P., Bernstein, M.S.: Generative agents: interactive simulacra of human behavior. In: UIST (2023)","DOI":"10.1145\/3586183.3606763"},{"key":"3_CR52","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"3_CR53","unstructured":"Ramaswamy, V.V., et al.: GeoDE: a geographically diverse evaluation dataset for object recognition. In: NeurIPS (2023)"},{"key":"3_CR54","unstructured":"Rojas, W.A.G., Diamos, S., Kini, K.R., Kanter, D., Reddi, V.J., Coleman, C.: The Dollar street dataset: images representing the geographic and socioeconomic diversity of the world. In: NeurIPS (2022)"},{"key":"3_CR55","doi-asserted-by":"crossref","unstructured":"Savva, M., et\u00a0al.: Habitat: a platform for embodied AI research. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"3_CR56","unstructured":"Schick, T., et al.: ToolFormer: language models can teach themselves to use tools. In: NeurIPS (2023)"},{"key":"3_CR57","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: NeurIPS (2022)"},{"key":"3_CR58","doi-asserted-by":"crossref","unstructured":"Schumann, R., Riezler, S.: Generating landmark navigation instructions from maps as a graph-to-text problem. In: ACL (2020)","DOI":"10.18653\/v1\/2021.acl-long.41"},{"key":"3_CR59","doi-asserted-by":"crossref","unstructured":"Schumann, R., Zhu, W., Feng, W., Fu, T.J., Riezler, S., Wang, W.Y.: VELMA: verbalization embodiment of LLM agents for vision and language navigation in street view. arXiv preprint arXiv:2307.06082 (2023)","DOI":"10.1609\/aaai.v38i17.29858"},{"key":"3_CR60","doi-asserted-by":"crossref","unstructured":"Shao, H., et al.: LMDrive: closed-loop end-to-end driving with large language models. arXiv preprint arXiv:2312.07488 (2023)","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"3_CR61","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"3_CR62","unstructured":"Shinn, N., Labash, B., Gopinath, A.: Reflexion: an autonomous agent with dynamic memory and self-reflection. In: NeurIPS (2023)"},{"key":"3_CR63","unstructured":"Significant Gravitas: AutoGPT (2023). https:\/\/github.com\/Significant-Gravitas\/AutoGPT"},{"key":"3_CR64","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: EVA-CLIP: improved training techniques for CLIP at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"key":"3_CR65","doi-asserted-by":"crossref","unstructured":"Tang, L., et al.: Mind the interference: retaining pre-trained knowledge in parameter efficient continual learning of vision-language models. arXiv preprint arXiv:2407.05342 (2024)","DOI":"10.1007\/978-3-031-72764-1_20"},{"key":"3_CR66","doi-asserted-by":"crossref","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. Commun. ACM 59(2), 64\u201373 (2016)","DOI":"10.1145\/2812802"},{"key":"3_CR67","unstructured":"Touvron, H., et\u00a0al.: LLAMA 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"3_CR68","unstructured":"Wang, G., et al.: Voyager: an open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291 (2023)"},{"key":"3_CR69","unstructured":"Wei, J., et\u00a0al.: Chain-of-thought prompting elicits reasoning in large language models. In: NeurIPS (2022)"},{"key":"3_CR70","doi-asserted-by":"crossref","unstructured":"Wooldridge, M., Jennings, N.R.: Intelligent agents: theory and practice. In: The Knowledge Engineering Review (1995)","DOI":"10.1017\/S0269888900008122"},{"key":"3_CR71","unstructured":"Wu, Q., et al.: AutoGen: enabling next-gen LLM applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155 (2023)"},{"key":"3_CR72","unstructured":"Xi, Z., et al.: The rise and potential of large language model based agents: a survey. arXiv preprint arXiv:2309.07864 (2023)"},{"key":"3_CR73","doi-asserted-by":"crossref","unstructured":"Xia, F., Zamir, A.R., He, Z., Sax, A., Malik, J., Savarese, S.: Gibson ENV: real-world perception for embodied agents. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00945"},{"key":"3_CR74","doi-asserted-by":"crossref","unstructured":"Xiang, F., et al.: SAPIEN: a simulated part-based interactive environment. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"3_CR75","unstructured":"Xu, H., et al.: Demystifying clip data. arXiv preprint arXiv:2309.16671 (2023)"},{"key":"3_CR76","doi-asserted-by":"crossref","unstructured":"Yang, J., Ding, R., Deng, W., Wang, Z., Qi, X.: RegionPLC: regional point-language contrastive learning for open-world 3D scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19823\u201319832 (2024)","DOI":"10.1109\/CVPR52733.2024.01874"},{"key":"3_CR77","unstructured":"Yao, S., et al.: ReAct: synergizing reasoning and acting in language models. In: ICLR (2023)"},{"key":"3_CR78","unstructured":"Ye, Q., et\u00a0al.: mPLUG-Owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"3_CR79","unstructured":"Yenamandra, S., et\u00a0al.: HomeRobot: open-vocabulary mobile manipulation. In: CoRL (2023)"},{"key":"3_CR80","unstructured":"Yuan, L., et\u00a0al.: Florence: a new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)"},{"key":"3_CR81","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. arXiv preprint arXiv:2303.15343 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"3_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: A simple framework for open-vocabulary segmentation and detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1020\u20131031 (2023)","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"3_CR83","doi-asserted-by":"publisher","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13669, pp. 350\u2013368. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"3_CR84","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:2304.10592 (2023)"},{"key":"3_CR85","unstructured":"Zhu, X., et al.: Ghost in the Minecraft: generally capable agents for open-world environments via large language models with text-based knowledge and memory. arXiv preprint arXiv:2305.17144 (2023)"}],"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_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T20:03:11Z","timestamp":1732392191000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72995-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031729942","9783031729959"],"references-count":85,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72995-9_3","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"}}]}}