{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:27:31Z","timestamp":1780763251149,"version":"3.54.1"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733369","type":"print"},{"value":"9783031733376","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73337-6_1","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T23:02:27Z","timestamp":1730329347000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Weak-to-Strong Compositional Learning from\u00a0Generative Models for\u00a0Language-Based Object Detection"],"prefix":"10.1007","author":[{"given":"Kwanyong","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuniaki","family":"Saito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donghyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"1_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"1_CR2","unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves imagenet classification. arXiv preprint arXiv:2304.08466 (2023)"},{"key":"1_CR3","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)"},{"key":"1_CR4","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European conference on computer vision, pp. 213\u2013229. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12m: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"1_CR6","unstructured":"Chen, J., et\u00a0al.: Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426 (2023)"},{"key":"1_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"1_CR8","unstructured":"Dou, Z.Y., et al.: Coarse-to-fine vision-language pre-training with fusion in the backbone. Adv. Neural. Inf. Process. Syst. 35, 32942\u201332956 (2022)"},{"key":"1_CR9","unstructured":"Doveh, S., et\u00a0al.: Dense and aligned captions (DAC) promote compositional reasoning in VL models. Adv. Neural Inf. Proce. Syst. 36 (2024)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Doveh, S., et\u00a0al.: Teaching structured vision &language concepts to vision &language models. arXiv preprint arXiv:2211.11733 (2022)","DOI":"10.1109\/CVPR52729.2023.00261"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Fan, L., Chen, K., Krishnan, D., Katabi, D., Isola, P., Tian, Y.: Scaling laws of synthetic images for model training... for now. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7382\u20137392 (2024)","DOI":"10.1109\/CVPR52733.2024.00705"},{"key":"1_CR12","unstructured":"Gan, C., et\u00a0al.: Threedworld: A platform for interactive multi-modal physical simulation. arXiv preprint arXiv:2007.04954 (2020)"},{"key":"1_CR13","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: Lvis: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"1_CR15","unstructured":"He, R., et al.: Is synthetic data from generative models ready for image recognition? arXiv preprint arXiv:2210.07574 (2022)"},{"key":"1_CR16","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR17","unstructured":"Honnibal, M., Montani, I.: spaCy 2: natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing (2017). to appear"},{"key":"1_CR18","unstructured":"Hsieh, C.Y., Zhang, J., Ma, Z., Kembhavi, A., Krishna, R.: Sugarcrepe: fixing hackable benchmarks for vision-language compositionality. Adv. Neural Inf. Proce. Syst. 36 (2024)"},{"key":"1_CR19","doi-asserted-by":"publisher","unstructured":"Hsu, C.C., Tsai, Y.H., Lin, Y.Y., Yang, M.H.: Every pixel matters: center-aware feature alignment for domain adaptive object detector. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part IX 16, pp. 733\u2013748. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_42","DOI":"10.1007\/978-3-030-58545-7_42"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Hur, S., Shin, I., Park, K., Woo, S., Kweon, I.S.: Learning classifiers of prototypes and reciprocal points for universal domain adaptation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 531\u2013540 (2023)","DOI":"10.1109\/WACV56688.2023.00060"},{"key":"1_CR21","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision (2021)"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: Mdetr-modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Kim, D., Angelova, A., Kuo, W.: Region-aware pretraining for open-vocabulary object detection with vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11144\u201311154 (2023)","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"1_CR24","unstructured":"Lee, Y., Park, K., Cho, Y., Lee, Y.J., Hwang, S.J.: Koala: self-attention matters in knowledge distillation of latent diffusion models for memory-efficient and fast image synthesis. arXiv preprint arXiv:2312.04005 (2023)"},{"key":"1_CR25","unstructured":"Li, L., Dou, Z.Y., Peng, N., Chang, K.W.: Desco: learning object recognition with rich language descriptions. Adv. Neural Inf. Proce. Syst. 36 (2024)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"1_CR27","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1_CR28","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":"1_CR29","unstructured":"Liu, Y., et al.: Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference On Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Loper, E., Bird, S.: Nltk: The natural language toolkit. arXiv preprint cs\/0205028 (2002)","DOI":"10.3115\/1118108.1118117"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Ma, Z., Hong, J., Gul, M.O., Gandhi, M., Gao, I., Krishna, R.: Crepe: can vision-language foundation models reason compositionally? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10910\u201310921 (2023)","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"1_CR33","unstructured":"Mikami, H., Fukumizu, K., Murai, S., Suzuki, S., Kikuchi, Y., Suzuki, T., Maeda, S.i., Hayashi, K.: A scaling law for synthetic-to-real transfer: How much is your pre-training effective? arXiv preprint arXiv:2108.11018 (2021)"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Mishra, S., et al.: Task2sim: towards effective pre-training and transfer from synthetic data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9194\u20139204 (2022)","DOI":"10.1109\/CVPR52688.2022.00898"},{"key":"1_CR35","unstructured":"Nguyen, Q., Vu, T., Tran, A., Nguyen, K.: Dataset diffusion: diffusion-based synthetic data generation for pixel-level semantic segmentation. Adv. Neural Infor. Proce. Syst. 36 (2024)"},{"key":"1_CR36","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2text: describing images using 1 million captioned photographs. Adv. Neural Infor. Proce. Syst. 24 (2011)"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Park, K., Woo, S., Oh, S.W., Kweon, I.S., Lee, J.Y.: Mask-guided matting in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1992\u20132001 (2023)","DOI":"10.1109\/CVPR52729.2023.00198"},{"key":"1_CR38","first-page":"10869","volume":"33","author":"K Park","year":"2020","unstructured":"Park, K., Woo, S., Shin, I., Kweon, I.S.: Discover, hallucinate, and adapt: open compound domain adaptation for semantic segmentation. Adv. Neural. Inf. Process. Syst. 33, 10869\u201310880 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Peng, X., Sun, B., Ali, K., Saenko, K.: Learning deep object detectors from 3D models. In: Proceedings of the IEEE international conference on computer vision, pp. 1278\u20131286 (2015)","DOI":"10.1109\/ICCV.2015.151"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"1_CR41","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., Rombach, R.: Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Prakash, A., et al.: Structured domain randomization: bridging the reality gap by context-aware synthetic data. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 7249\u20137255. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794443"},{"key":"1_CR43","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1_CR45","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. Adv. Neural Infor. Proce. Syst. 28 (2015)"},{"key":"1_CR46","doi-asserted-by":"publisher","unstructured":"Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14, pp. 102\u2013118. Springer (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_7","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"1_CR47","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":"1_CR48","doi-asserted-by":"crossref","unstructured":"Sauer, A., Lorenz, D., Blattmann, A., Rombach, R.: Adversarial diffusion distillation. arXiv preprint arXiv:2311.17042 (2023)","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Schulter, S., et\u00a0al.: Omnilabel: a challenging benchmark for language-based object detection (2023)","DOI":"10.1109\/ICCV51070.2023.01098"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8430\u20138439 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"1_CR51","unstructured":"Shin, I., Park, K., Woo, S., Kweon, I.S.: Unsupervised domain adaptation for video semantic segmentation. arXiv preprint arXiv:2107.11052 (2021)"},{"key":"1_CR52","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Thrush, T., et al.: Winoground: probing vision and language models for visio-linguistic compositionality. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5238\u20135248 (2022)","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Tian, Y., Fan, L., Chen, K., Katabi, D., Krishnan, D., Isola, P.: Learning vision from models rivals learning vision from data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15887\u201315898 (2024)","DOI":"10.1109\/CVPR52733.2024.01504"},{"key":"1_CR55","unstructured":"Tian, Y., Fan, L., Isola, P., Chang, H., Krishnan, D.: Stablerep: synthetic images from text-to-image models make strong visual representation learners. Adv. Neural Infor. Proce. Syst. 36 (2024)"},{"key":"1_CR56","unstructured":"Touvron, H., et\u00a0al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"1_CR57","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Hung, W.C., Schulter, S., Sohn, K., Yang, M.H., Chandraker, M.: Learning to adapt structured output space for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7472\u20137481 (2018)","DOI":"10.1109\/CVPR.2018.00780"},{"key":"1_CR58","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Differential treatment for stuff and things: a simple unsupervised domain adaptation method for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12635\u201312644 (2020)","DOI":"10.1109\/CVPR42600.2020.01265"},{"key":"1_CR59","doi-asserted-by":"publisher","unstructured":"Woo, S., Park, K., Oh, S.W., Kweon, I.S., Lee, J.Y.: Bridging images and videos: A simple learning framework for large vocabulary video object detection. In: European Conference on Computer Vision, pp. 238\u2013258. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19806-9_14","DOI":"10.1007\/978-3-031-19806-9_14"},{"key":"1_CR60","unstructured":"Wu, W., et al.: Datasetdm: synthesizing data with perception annotations using diffusion models. Adv. Neural. Inf. Process. Syst. 36, 54683\u201354695 (2023)"},{"key":"1_CR61","unstructured":"Xie, C., Zhang, Z., Wu, Y., Zhu, F., Zhao, R., Liang, S.: Described object detection: liberating object detection with flexible expressions. Adv. Neural Infor. Proce. Syst. 36 (2024)"},{"key":"1_CR62","doi-asserted-by":"crossref","unstructured":"Xie, J., Li, W., Li, X., Liu, Z., Ong, Y.S., Loy, C.C.: Mosaicfusion: Diffusion models as data augmenters for large vocabulary instance segmentation. arXiv preprint arXiv:2309.13042 (2023)","DOI":"10.1007\/s11263-024-02223-3"},{"key":"1_CR63","unstructured":"Xu, T., Chen, W., Wang, P., Wang, F., Li, H., Jin, R.: Cdtrans: Cross-domain transformer for unsupervised domain adaptation. arXiv preprint arXiv:2109.06165 (2021)"},{"key":"1_CR64","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? In: International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=KRLUvxh8uaX"},{"key":"1_CR65","doi-asserted-by":"crossref","unstructured":"Zhao, T., et al.: Vl-checklist: Evaluating pre-trained vision-language models with objects, attributes and relations. arXiv preprint arXiv:2207.00221 (2022)","DOI":"10.18653\/v1\/2022.emnlp-demos.4"},{"key":"1_CR66","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: Regionclip: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"1_CR67","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: European Conference on Computer Vision, pp. 350\u2013368. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21","DOI":"10.1007\/978-3-031-20077-9_21"}],"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\/978-3-031-73337-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T15:00:04Z","timestamp":1732978804000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73337-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733369","9783031733376"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73337-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 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"}}]}}