{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:24:27Z","timestamp":1774599867290,"version":"3.50.1"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198113","type":"print"},{"value":"9783031198120","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19812-0_5","type":"book-chapter","created":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T14:03:42Z","timestamp":1667052222000},"page":"69-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Learning Visual Representation from\u00a0Modality-Shared Contrastive Language-Image Pre-training"],"prefix":"10.1007","author":[{"given":"Haoxuan","family":"You","sequence":"first","affiliation":[]},{"given":"Luowei","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Noel","family":"Codella","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Ruochen","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Shih-Fu","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Lu","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,30]]},"reference":[{"key":"5_CR1","unstructured":"Akbari, H., et al.: VATT: transformers for multimodal self-supervised learning from raw video, audio and text. arXiv preprint arXiv:2104.11178 (2021)"},{"key":"5_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"5_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"5_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/978-3-319-46493-0_22","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Cai","year":"2016","unstructured":"Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 354\u2013370. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_22"},{"key":"5_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1007\/978-3-030-58539-6_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Cao","year":"2020","unstructured":"Cao, J., Gan, Z., Cheng, Y., Yu, L., Chen, Y.-C., Liu, J.: Behind the scene: revealing the secrets of pre-trained vision-and-language models. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 565\u2013580. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_34"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: UNITER: learning universal image-text representations (2019)","DOI":"10.1007\/978-3-030-58577-8_7"},{"issue":"10","key":"5_CR7","doi-asserted-by":"publisher","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","volume":"105","author":"G Cheng","year":"2017","unstructured":"Cheng, G., Han, J., Lu, X.: Remote sensing image scene classification: benchmark and state of the art. Proc. IEEE 105(10), 1865\u20131883 (2017)","journal-title":"Proc. IEEE"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"5_CR9","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, pp. 215\u2013223 (2011)"},{"key":"5_CR10","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Desai, K., Johnson, J.: VirTex: learning visual representations from textual annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11162\u201311173 (2021)","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Dong, X., Yang, Y.: Searching for a robust neural architecture in four GPU hours. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1761\u20131770 (2019)","DOI":"10.1109\/CVPR.2019.00186"},{"key":"5_CR13","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"5_CR14","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results (2007). http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.html"},{"key":"5_CR15","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: 2004 Conference on Computer Vision and Pattern Recognition Workshop, p. 178. IEEE (2004)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision And Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"7","key":"5_CR19","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","volume":"12","author":"P Helber","year":"2019","unstructured":"Helber, P., Bischke, B., Dengel, A., Borth, D.: EuroSAT: a novel dataset and deep learning benchmark for land use and land cover classification. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 12(7), 2217\u20132226 (2019)","journal-title":"IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens."},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Hu, R., Singh, A.: Unit: multimodal multitask learning with a unified transformer. arXiv preprint arXiv:2102.10772 (2021)","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"5_CR21","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. arXiv preprint arXiv:2102.05918 (2021)"},{"key":"5_CR22","unstructured":"Kiela, D., et al.: The hateful memes challenge: detecting hate speech in multimodal memes. arXiv preprint arXiv:2005.04790 (2020)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"5_CR24","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)"},{"issue":"11","key":"5_CR25","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"5_CR26","unstructured":"Lee, S., Yu, Y., Kim, G., Breuel, T., Kautz, J., Song, Y.: Parameter efficient multimodal transformers for video representation learning. arXiv preprint arXiv:2012.04124 (2020)"},{"key":"5_CR27","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. arXiv preprint arXiv:2201.12086 (2022)"},{"key":"5_CR28","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Clip-event: connecting text and images with event structures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16420\u201316429 (2022)","DOI":"10.1109\/CVPR52688.2022.01593"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: UNIMO: towards unified-modal understanding and generation via cross-modal contrastive learning. arXiv preprint arXiv:2012.15409 (2020)","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"5_CR31","unstructured":"Li, Y., et al.: Supervision exists everywhere: a data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208 (2021)"},{"key":"5_CR32","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":"5_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Stent, S., Li, J., Gideon, J., Han, S.: LocTex: learning data-efficient visual representations from localized textual supervision. arXiv preprint arXiv:2108.11950 (2021)","DOI":"10.1109\/ICCV48922.2021.00217"},{"key":"5_CR35","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"5_CR36","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: VilBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. arXiv preprint arXiv:1908.02265 (2019)"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: multi-task vision and language representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10437\u201310446 (2020)","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Lu, K., Grover, A., Abbeel, P., Mordatch, I.: Pretrained transformers as universal computation engines. arXiv preprint arXiv:2103.05247 (2021)","DOI":"10.1609\/aaai.v36i7.20729"},{"key":"5_CR39","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Mu, N., Kirillov, A., Wagner, D., Xie, S.: Slip: self-supervision meets language-image pre-training. arXiv preprint arXiv:2112.12750 (2021)","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"5_CR41","unstructured":"Nagrani, A., Yang, S., Arnab, A., Jansen, A., Schmid, C., Sun, C.: Attention bottlenecks for multimodal fusion. arXiv preprint arXiv:2107.00135 (2021)"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing, pp. 722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"5_CR43","unstructured":"Pantic, M., Valstar, M., Rademaker, R., Maat, L.: Web-based database for facial expression analysis. In: 2005 IEEE International Conference on Multimedia and Expo, pp. 5-pp. IEEE (2005)"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3498\u20133505. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"5_CR45","unstructured":"Pham, H., et al.: Combined scaling for zero-shot transfer learning. arXiv preprint arXiv:2111.10050 (2021)"},{"key":"5_CR46","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":"5_CR47","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020 (2021)"},{"key":"5_CR48","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"5_CR49","unstructured":"Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1631\u20131642 (2013)"},{"key":"5_CR50","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw. 32, 323\u2013332 (2012)","DOI":"10.1016\/j.neunet.2012.02.016"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"issue":"2","key":"5_CR54","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":"5_CR55","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"5_CR56","doi-asserted-by":"crossref","unstructured":"Veeling, B.S., Linmans, J., Winkens, J., Cohen, T., Welling, M.: Rotation equivariant CNNs for digital pathology, June 2018","DOI":"10.1007\/978-3-030-00934-2_24"},{"key":"5_CR57","unstructured":"Wang, J., et al.: UFO: a unified transformer for vision-language representation learning. arXiv preprint arXiv:2111.10023 (2021)"},{"key":"5_CR58","unstructured":"Wang, W., Bao, H., Dong, L., Wei, F.: VLMO: unified vision-language pre-training with mixture-of-modality-experts. arXiv preprint arXiv:2111.02358 (2021)"},{"key":"5_CR59","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: SimVLM: simple visual language model pretraining with weak supervision. arXiv preprint arXiv:2108.10904 (2021)"},{"key":"5_CR60","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CVT: introducing convolutions to vision transformers. arXiv preprint arXiv:2103.15808 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"5_CR61","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3485\u20133492. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"5_CR62","unstructured":"Xiao, T., Singh, M., Mintun, E., Darrell, T., Doll\u00e1r, P., Girshick, R.: Early convolutions help transformers see better. arXiv preprint arXiv:2106.14881 (2021)"},{"key":"5_CR63","unstructured":"Yao, L., et al.: FILIP: fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783 (2021)"},{"key":"5_CR64","unstructured":"Yuan, L., et al.: Florence: a new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)"},{"key":"5_CR65","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: LiT: zero-shot transfer with locked-image text tuning. arXiv preprint arXiv:2111.07991 (2021)","DOI":"10.1109\/CVPR52688.2022.01759"},{"issue":"9","key":"5_CR66","doi-asserted-by":"publisher","first-page":"2936","DOI":"10.1109\/TPAMI.2021.3065138","volume":"43","author":"X Zheng","year":"2021","unstructured":"Zheng, X., et al.: MIGO-NAS: towards fast and generalizable neural architecture search. IEEE Trans. Pattern Anal. Mach. Intell. 43(9), 2936\u20132952 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR67","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: 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":"5_CR68","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13041\u201313049 (2020)","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19812-0_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T20:51:53Z","timestamp":1728247913000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19812-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198113","9783031198120"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19812-0_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"30 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}