{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T06:11:44Z","timestamp":1771913504608,"version":"3.50.1"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734038","type":"print"},{"value":"9783031734045","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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\/978-3-031-73404-5_20","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T16:03:13Z","timestamp":1730217793000},"page":"339-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["REVISION: Rendering Tools Enable Spatial Fidelity in\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0961-9569","authenticated-orcid":false,"given":"Agneet","family":"Chatterjee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6533-8617","authenticated-orcid":false,"given":"Yiran","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5593-2804","authenticated-orcid":false,"given":"Tejas","family":"Gokhale","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0126-8976","authenticated-orcid":false,"given":"Yezhou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7549-723X","authenticated-orcid":false,"given":"Chitta","family":"Baral","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"20_CR1","unstructured":"Bai, J., et al.: Qwen-VL: a versatile vision-language model for understanding, localization, text reading, and beyond (2023). https:\/\/arxiv.org\/abs\/2308.12966"},{"key":"20_CR2","unstructured":"Bavishi, R., et al.: Introducing our multimodal models (2023). https:\/\/www.adept.ai\/blog\/fuyu-8b"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Chatterjee, A., et al.: Getting it right: improving spatial consistency in text-to-image models (2024). https:\/\/arxiv.org\/abs\/2404.01197","DOI":"10.1007\/978-3-031-72670-5_12"},{"issue":"4","key":"20_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models. ACM Trans. Graph. (TOG) 42(4), 1\u201310 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"20_CR5","unstructured":"Chen, J., et al.: Pixart-$$alpha $$: fast training of diffusion transformer for photorealistic text-to-image synthesis. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"20_CR6","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event. Proceedings of Machine Learning Research, vol.\u00a0119, pp. 1691\u20131703. PMLR (2020). http:\/\/proceedings.mlr.press\/v119\/chen20s.html"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance (2023)","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Cho, J., Zala, A., Bansal, M.: Dall-eval: probing the reasoning skills and social biases of text-to-image generation models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3043\u20133054 (2023)","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"20_CR9","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=vvoWPYqZJA"},{"key":"20_CR10","doi-asserted-by":"publisher","unstructured":"Dayma, B., et al.: Dall$$\\cdot $$e mini (2021). https:\/\/doi.org\/10.5281\/zenodo.5146400, https:\/\/github.com\/borisdayma\/dalle-mini","DOI":"10.5281\/zenodo.5146400"},{"key":"20_CR11","unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=PUIqjT4rzq7"},{"key":"20_CR12","unstructured":"Feng, W., et al.: LayoutGPT: compositional visual planning and generation with large language models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"20_CR13","unstructured":"Fu, C., et\u00a0al.: MME: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint abs\/2306.13394 (2023), https:\/\/arxiv.org\/abs\/2306.13394"},{"key":"20_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/978-3-030-58589-1_23","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Gokhale","year":"2020","unstructured":"Gokhale, T., Banerjee, P., Baral, C., Yang, Y.: VQA-LOL: visual question answering under the lens of logic. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 379\u2013396. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_23"},{"key":"20_CR15","unstructured":"Gokhale, T., et al.: Benchmarking spatial relationships in text-to-image generation. arXiv preprint arXiv:2212.10015 (2022)"},{"issue":"11","key":"20_CR16","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"20_CR17","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-or, D.: Prompt-to-prompt image editing with cross-attention control. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=_CDixzkzeyb"},{"key":"20_CR18","unstructured":"Huang, K., Sun, K., Xie, E., Li, Z., Liu, X.: T2i-compbench: a comprehensive benchmark for open-world compositional text-to-image generation. In: Advances in Neural Information Processing Systems, vol. 36, pp. 78723\u201378747 (2023)"},{"key":"20_CR19","doi-asserted-by":"publisher","unstructured":"Johnson, J., Hariharan, B., van\u00a0der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.B.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017, pp. 1988\u20131997. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.215","DOI":"10.1109\/CVPR.2017.215"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Kamath, A., Hessel, J., Chang, K.W.: What\u2019s \u201cup\u201d with vision-language models? Investigating their struggle with spatial reasoning. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 9161\u20139175 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.568"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Gligen: open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Super-clevr: a virtual benchmark to diagnose domain robustness in visual reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14963\u201314973 (2023)","DOI":"10.1109\/CVPR52729.2023.01437"},{"key":"20_CR23","unstructured":"Lian, L., Li, B., Yala, A., Darrell, T.: LLM-grounded diffusion: enhancing prompt understanding of text-to-image diffusion models with large language models. arXiv preprint abs\/2305.13655 (2023). https:\/\/arxiv.org\/abs\/2305.13655"},{"key":"20_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"20_CR25","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"20_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1007\/978-3-031-19790-1_26","volume-title":"Computer Vision - ECCV 2022","author":"N Liu","year":"2022","unstructured":"Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13677, pp. 423\u2013439. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_26"},{"key":"20_CR27","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":"20_CR28","unstructured":"Meng, C., et al.: Sdedit: guided image synthesis and editing with stochastic differential equations. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022). https:\/\/openreview.net\/forum?id=aBsCjcPu_tE"},{"key":"20_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-031-20080-9_42","volume-title":"Computer Vision - ECCV 2022","author":"M Minderer","year":"2022","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 728\u2013755. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42"},{"key":"20_CR30","unstructured":"Nichol, A.Q., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesv\u00e1ri, C., Niu, G., Sabato, S. (eds.) International Conference on Machine Learning, ICML 2022, 17\u201323 July 2022, Baltimore, Maryland, USA. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 16784\u201316804. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/nichol22a.html"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Parmar, G., Kumar\u00a0Singh, K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y.: Zero-shot image-to-image translation. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Patel, M., Kim, C., Cheng, S., Baral, C., Yang, Y.: Eclipse: a resource-efficient text-to-image prior for image generations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9069\u20139078 (2024)","DOI":"10.1109\/CVPR52733.2024.00866"},{"key":"20_CR33","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=di52zR8xgf"},{"key":"20_CR34","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"20_CR35","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents, 1(2), 3. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"20_CR36","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8821\u20138831. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/ramesh21a.html"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Razzhigaev, A., et al.: Kandinsky: an improved text-to-image synthesis with image prior and latent diffusion. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 286\u2013295 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.25"},{"key":"20_CR38","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":"20_CR39","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems, vol. 35, pp. 36479\u201336494 (2022)"},{"key":"20_CR40","unstructured":"Salimans, T., Goodfellow, I.J., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Lee, D.D., Sugiyama, M., von Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 5\u201310 December 2016, Barcelona, Spain, pp. 2226\u20132234 (2016). https:\/\/proceedings.neurips.cc\/paper\/2016\/hash\/8a3363abe792db2d8761d6403605aeb7-Abstract.html"},{"key":"20_CR41","doi-asserted-by":"publisher","unstructured":"Sampat, S.K., Kumar, A., Yang, Y., Baral, C.: CLEVR_HYP: a challenge dataset and baselines for visual question answering with hypothetical actions over images. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3692\u20133709. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.289, https:\/\/aclanthology.org\/2021.naacl-main.289","DOI":"10.18653\/v1\/2021.naacl-main.289"},{"key":"20_CR42","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 7\u201312 December 2015, Montreal, Quebec, Canada, pp. 3483\u20133491 (2015). https:\/\/proceedings.neurips.cc\/paper\/2015\/hash\/8d55a249e6baa5c06772297520da2051-Abstract.html"},{"key":"20_CR43","doi-asserted-by":"publisher","unstructured":"Stammer, W., Schramowski, P., Kersting, K.: Right for the right concept: revising neuro-symbolic concepts by interacting with their explanations. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, 19\u201325 June 2021, pp. 3619\u20133629. Computer Vision Foundation\/IEEE (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00362, https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/html\/Stammer_Right_for_the_Right_Concept_Revising_Neuro-Symbolic_Concepts_by_Interacting_CVPR_2021_paper.html","DOI":"10.1109\/CVPR46437.2021.00362"},{"key":"20_CR44","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint abs\/2312.11805 (2023). https:\/\/arxiv.org\/abs\/2312.11805"},{"key":"20_CR45","doi-asserted-by":"crossref","unstructured":"Wake, N., Kanehira, A., Sasabuchi, K., Takamatsu, J., Ikeuchi, K.: Gpt-4v (ision) for robotics: multimodal task planning from human demonstration. arXiv preprint arXiv:2311.12015 (2023)","DOI":"10.1109\/LRA.2024.3477090"},{"key":"20_CR46","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. arXiv preprint abs\/2401.10891 (2024). https:\/\/arxiv.org\/abs\/2401.10891"},{"key":"20_CR47","unstructured":"Yang, L., et al.: Improving diffusion-based image synthesis with context prediction. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"20_CR48","unstructured":"Yang, Z., et al.: The dawn of LMMS: preliminary explorations with gpt-4v (ision), 9(1), 1. arXiv preprint arXiv:2309.17421 (2023)"},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Yang, Z., et\u00a0al.: Reco: region-controlled text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14246\u201314255 (2023)","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"20_CR50","unstructured":"Yi, K., et al.: CLEVRER: collision events for video representation and reasoning. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, 26\u201330 April 2020. OpenReview.net (2020). https:\/\/openreview.net\/forum?id=HkxYzANYDB"},{"key":"20_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"20_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":"20_CR53","unstructured":"Zhang, T., Zhang, Y., Vineet, V., Joshi, N., Wang, X.: Controllable text-to-image generation with gpt-4. arXiv preprint arXiv:2305.18583 (2023)"},{"key":"20_CR54","unstructured":"Zhang, X., et al.: Realcompo: dynamic equilibrium between realism and compositionality improves text-to-image diffusion models. arXiv preprint arXiv:2402.12908 (2024)"}],"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\/978-3-031-73404-5_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T19:46:16Z","timestamp":1745523976000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73404-5_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031734038","9783031734045"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73404-5_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 October 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"}}]}}