{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:37:44Z","timestamp":1742956664211,"version":"3.40.3"},"publisher-location":"Cham","reference-count":74,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031731945"},{"type":"electronic","value":"9783031731952"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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\/978-3-031-73195-2_17","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T09:36:28Z","timestamp":1732613788000},"page":"287-304","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FuseTeacher: Modality-Fused Encoders are Strong Vision Supervisors"],"prefix":"10.1007","author":[{"given":"Chen-Wei","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liming","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pandeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuailei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"17_CR1","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image Transformers (2021)"},{"key":"17_CR2","unstructured":"Barbu, A., et al.: ObjectNet: a large-scale bias-controlled dataset for pushing the limits of object recognition models. In: Advances in Neural Information Processing Systems, pp. 9448\u20139458 (2019)"},{"key":"17_CR3","unstructured":"Betker, J., et al.: Improving image generation with better captions (2023). https:\/\/openai.com\/dall-e-3"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., Gool, L.V.: Food-101\u2013mining discriminative components with random forests. In: European Conference on Computer Vision, pp. 446\u2013461 (2014)","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"17_CR5","unstructured":"Byeon, M., Park, B., Kim, H., Lee, S., Baek, W., Kim, S.: COYO-700M: image-text pair dataset (2022). https:\/\/github.com\/kakaobrain\/coyo-dataset"},{"key":"17_CR6","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in Neural Information Processing Systems, pp. 9912\u20139924 (2020)"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"17_CR8","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"17_CR9","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607 (2020)"},{"key":"17_CR10","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server (2015)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3606\u20133613 (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: RandAugment: practical automated data augmentation with a reduced search space. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"17_CR14","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"17_CR15","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional Transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4171\u20134186 (2019)"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Dong, X., et\u00a0al.: MaskCLIP: masked self-distillation advances contrastive language-image pretraining. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10995\u201311005 (2023)","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"17_CR17","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"17_CR18","unstructured":"Fan, L., Krishnan, D., Isola, P., Katabi, D., Tian, Y.: Improving CLIP training with language rewrites. In: Advances in Neural Information Processing Systems (2023)"},{"key":"17_CR19","unstructured":"Fang, A., et al.: Data determines distributional robustness in contrastive language image pre-training (clip). In: International Conference on Machine Learning, pp. 6216\u20136234 (2022)"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: EVA: exploring the limits of masked visual representation learning at scale. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 19358\u201319369 (2023)","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"17_CR21","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, p. 178 (2004)"},{"key":"17_CR22","unstructured":"Gadre, S.Y., et al.: DataComp: in search of the next generation of multimodal datasets (2023)"},{"issue":"6","key":"17_CR23","doi-asserted-by":"publisher","first-page":"7457","DOI":"10.1109\/TPAMI.2022.3218275","volume":"45","author":"S Gao","year":"2023","unstructured":"Gao, S., Li, Z., Yang, M., Cheng, M., Han, J., Torr, P.H.S.: Large-scale unsupervised semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7457\u20137476 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR24","unstructured":"Grill, J.B., et\u00a0al.: Bootstrap your own latent-a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems, pp. 21271\u201321284 (2020)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: International Conference on Computer Vision, pp. 8320\u20138329 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 15262\u201315271 (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"17_CR30","doi-asserted-by":"publisher","unstructured":"Ilharco, G., et al.: Openclip (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Jeong, J., Zou, Y., Kim, T., Zhang, D., Ravichandran, A., Dabeer, O.: WinCLIP: zero-\/few-shot anomaly classification and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 19606\u201319616 (2023)","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"17_CR32","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Kong, X., Zhang, X.: Understanding masked image modeling via learning occlusion invariant feature. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6241\u20136251 (2023)","DOI":"10.1109\/CVPR52729.2023.00604"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"17_CR35","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"17_CR36","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)"},{"key":"17_CR37","unstructured":"Lee, J., et al.: UniCLIP: unified framework for contrastive language-image pre-training. In: Advances in Neural Information Processing Systems, pp. 1008\u20131019 (2022)"},{"key":"17_CR38","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900 (2022)"},{"key":"17_CR39","unstructured":"Li, J., Selvaraju, R.R., Gotmare, A.D., Joty, S.R., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: Advances in Neural Information Processing Systems (2021)"},{"key":"17_CR40","unstructured":"Li, P., et al.: MomentDiff: generative video moment retrieval from random to real. In: Advances in Neural Information Processing Systems, pp. 65948\u201365966 (2023)"},{"key":"17_CR41","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: Progressive spatio-temporal prototype matching for text-video retrieval. In: International Conference on Computer Vision, pp. 4100\u20134110 (2023)","DOI":"10.1109\/ICCV51070.2023.00379"},{"key":"17_CR42","unstructured":"Li, Y., et al.: Supervision exists everywhere: a data efficient contrastive language-image pre-training paradigm. In: International Conference on Learning Representations (2022)"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Liu, F., Chen, D., Guan, Z., Zhou, X., Zhu, J., Zhou, J.: RemoteCLIP: a vision language foundation model for remote sensing (2023)","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"17_CR44","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"17_CR45","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., et al.: CLIP4Clip: an empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"17_CR46","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M.B., Vedaldi, A.: Fine-grained visual classification of aircraft (2013)"},{"key":"17_CR47","doi-asserted-by":"crossref","unstructured":"Mu, N., Kirillov, A., Wagner, D.A., Xie, S.: SLIP: self-supervision meets language-image pre-training. In: European Conference on Computer Vision, vol. 13686, pp. 529\u2013544 (2022)","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Nilsback, M., Zisserman, A.: Automated flower classification over a large number of classes. In: ICVGIP, pp. 722\u2013729 (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"17_CR49","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision (2023)"},{"key":"17_CR50","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2text: describing images using 1 million captioned photographs. In: Advances in Neural Information Processing Systems, vol. 24 (2011)"},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3498\u20133505 (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"17_CR52","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024\u20138035 (2019)"},{"key":"17_CR53","doi-asserted-by":"crossref","unstructured":"Radenovic, F., et al.: Filtering, distillation, and hard negatives for vision-language pre-training (2023)","DOI":"10.1109\/CVPR52729.2023.00673"},{"key":"17_CR54","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":"17_CR55","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do ImageNet classifiers generalize to ImageNet? In: International Conference on Machine Learning, vol.\u00a097, pp. 5389\u20135400 (2019)"},{"key":"17_CR56","unstructured":"Schuhmann, C., et al.: LAION-5b: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems (2022)"},{"key":"17_CR57","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of CLIP-filtered 400 million image-text pairs (2021)"},{"key":"17_CR58","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: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"17_CR59","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2014)"},{"key":"17_CR60","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results, vol. 30 (2017)"},{"issue":"2","key":"17_CR61","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2812802","volume":"59","author":"B Thomee","year":"2016","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. Commun. ACM 59(2), 64\u201373 (2016)","journal-title":"Commun. ACM"},{"key":"17_CR62","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: MedCLIP: contrastive learning from unpaired medical images and text (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"17_CR63","doi-asserted-by":"crossref","unstructured":"Wei, J.W., Zou, K.: EDA: easy data augmentation techniques for boosting performance on text classification tasks. In: EMNLP-IJCNLP, pp. 6381\u20136387 (2019)","DOI":"10.18653\/v1\/D19-1670"},{"issue":"1","key":"17_CR64","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11263-014-0748-y","volume":"119","author":"J Xiao","year":"2016","unstructured":"Xiao, J., Ehinger, K.A., Hays, J., Torralba, A., Oliva, A.: SUN database: exploring a large collection of scene categories. Int. J. Comput. Vis. 119(1), 3\u201322 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"17_CR65","doi-asserted-by":"crossref","unstructured":"Xie, C.W., Sun, S., Xiong, X., Zheng, Y., Zhao, D., Zhou, J.: RA-CLIP: retrieval augmented contrastive language-image pre-training. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 19265\u201319274 (2023)","DOI":"10.1109\/CVPR52729.2023.01846"},{"key":"17_CR66","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: CiT: curation in training for effective vision-language data. In: International Conference on Computer Vision, pp. 15180\u201315189 (2023)","DOI":"10.1109\/ICCV51070.2023.01393"},{"key":"17_CR67","unstructured":"Yao, L., et al.: FILIP: fine-grained interactive language-image pre-training. In: International Conference on Learning Representations (2022)"},{"key":"17_CR68","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-031-19812-0_5","volume-title":"Computer Vision \u2013 ECCV 2022","author":"H You","year":"2022","unstructured":"You, H., et al.: Learning visual representation from modality-shared contrastive language-image pre-training. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 69\u201387. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_5"},{"key":"17_CR69","unstructured":"You, Y., et al.: Large batch optimization for deep learning: training BERT in 76 minutes. In: International Conference on Learning Representations (2020)"},{"key":"17_CR70","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguistics 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"17_CR71","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. Trans. Mach. Learn. Res. (2022)"},{"key":"17_CR72","unstructured":"Yuan, L., et al.: Florence: a new foundation model for computer vision (2021)"},{"key":"17_CR73","unstructured":"Zhao, L., Zheng, K., Zheng, Y., Zhao, D., Zhou, J.: RLEG: vision-language representation learning with diffusion-based embedding generation. In: International Conference on Machine Learning, pp. 42247\u201342258 (2023)"},{"key":"17_CR74","unstructured":"Zhou, J., et al.: iBOT: image BERT pre-training with online tokenizer. In: International Conference on Machine Learning (2022)"}],"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\/978-3-031-73195-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T10:11:38Z","timestamp":1732615898000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73195-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031731945","9783031731952"],"references-count":74,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73195-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 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"}}]}}