{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:24:25Z","timestamp":1774599865701,"version":"3.50.1"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585679","type":"print"},{"value":"9783030585686","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58568-6_23","type":"book-chapter","created":{"date-parts":[[2020,11,12]],"date-time":"2020-11-12T14:03:09Z","timestamp":1605189789000},"page":"387-404","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":189,"title":["Improving One-Stage Visual Grounding by Recursive Sub-query Construction"],"prefix":"10.1007","author":[{"given":"Zhengyuan","family":"Yang","sequence":"first","affiliation":[]},{"given":"Tianlang","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Liwei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,13]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Bajaj, M., Wang, L., Sigal, L.: G3raphground: Graph-based language grounding. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00438"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Chen, D., Manning, C.D.: A fast and accurate dependency parser using neural networks. In: EMNLP, pp. 740\u2013750 (2014)","DOI":"10.3115\/v1\/D14-1082"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Chen, K., Kovvuri, R., Gao, J., Nevatia, R.: MSRC: multimodal spatial regression with semantic context for phrase grounding. In: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, pp. 23\u201331. ACM (2017)","DOI":"10.1145\/3078971.3078976"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Chen, K., Kovvuri, R., Nevatia, R.: Query-guided regression network with context policy for phrase grounding. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.95"},{"key":"23_CR5","unstructured":"Chen, X., Ma, L., Chen, J., Jie, Z., Liu, W., Luo, J.: Real-time referring expression comprehension by single-stage grounding network. arXiv preprint arXiv:1812.03426 (2018)"},{"key":"23_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1007\/978-3-319-46484-8_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"CB Choy","year":"2016","unstructured":"Choy, C.B., Xu, D., Gwak, J.Y., Chen, K., Savarese, S.: 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 628\u2013644. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_38"},{"key":"23_CR7","unstructured":"De Vries, H., Strub, F., Mary, J., Larochelle, H., Pietquin, O., Courville, A.C.: Modulating early visual processing by language. In: Advances in Neural Information Processing Systems, pp. 6594\u20136604 (2017)"},{"key":"23_CR8","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":"23_CR9","doi-asserted-by":"crossref","unstructured":"Dogan, P., Sigal, L., Gross, M.: Neural sequential phrase grounding (seqground). In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00430"},{"key":"23_CR10","unstructured":"Dumoulin, V., Shlens, J., Kudlur, M.: A learned representation for artistic style. In: ICLR (2017)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Escalante, H.J., et al.: The segmented and annotated IAPR TC-12 benchmark. CVIU (2010)","DOI":"10.1016\/j.cviu.2009.03.008"},{"key":"23_CR12","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","volume":"28","author":"K Greff","year":"2016","unstructured":"Greff, K., Srivastava, R.K., Koutn\u00edk, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: a search space odyssey. IEEE Trans. Neural Networks Learn. Syst. 28, 2222\u20132232 (2016)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, M., Andreas, J., Darrell, T., Saenko, K.: Modeling relationships in referential expressions with compositional modular networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.470"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., Darrell, T.: Natural language object retrieval. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.493"},{"key":"23_CR16","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. In: ICLR (2018)"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: Referitgame: referring to objects in photographs of natural scenes. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Deep attribute-preserving metric learning for natural language object retrieval. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 181\u2013189. ACM (2017)","DOI":"10.1145\/3123266.3123439"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Zhou, B., Yue, D., Wang, X.: Person search with natural language description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1970\u20131979 (2017)","DOI":"10.1109\/CVPR.2017.551"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Liao, Y., et al.: A real-time cross-modality correlation filtering method for referring expression comprehension. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10880\u201310889 (2020)","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"23_CR21","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":"23_CR22","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. In: ICLR (2017)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Liu, C., Lin, Z., Shen, X., Yang, J., Lu, X., Yuille, A.: Recurrent multimodal interaction for referring image segmentation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Liu, D., Zhang, H., Wu, F., Zha, Z.J.: Learning to assemble neural module tree networks for visual grounding. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00477"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, L., Yang, M.H.: Referring expression generation and comprehension via attributes. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.520"},{"key":"23_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Liu, X., Wang, Z., Shao, J., Wang, X., Li, H.: Improving referring expression grounding with cross-modal attention-guided erasing. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00205"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Luo, G., et al.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10034\u201310043 (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"23_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1007\/978-3-319-46493-0_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"VK Nagaraja","year":"2016","unstructured":"Nagaraja, V.K., Morariu, V.I., Davis, L.S.: Modeling context between objects for referring expression understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 792\u2013807. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_48"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: Film: Visual reasoning with a general conditioning layer. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"23_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-030-01258-8_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"BA Plummer","year":"2018","unstructured":"Plummer, B.A., Kordas, P., Kiapour, M.H., Zheng, S., Piramuthu, R., Lazebnik, S.: Conditional image-text embedding networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 258\u2013274. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_16"},{"key":"23_CR33","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. Int. J. Comput. Vis. (2017)","DOI":"10.1007\/s11263-016-0965-7"},{"key":"23_CR34","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"23_CR35","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"23_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/978-3-319-46448-0_49","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Rohrbach","year":"2016","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 817\u2013834. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_49"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Sadhu, A., Chen, K., Nevatia, R.: Zero-shot grounding of objects from natural language queries. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00479"},{"key":"23_CR38","first-page":"26","volume":"4","author":"T Tieleman","year":"2012","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-RMSPROP: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks Mach. Learn. 4, 26\u201330 (2012)","journal-title":"COURSERA: Neural Networks Mach. Learn."},{"key":"23_CR39","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104, 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Huang, J., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. IEEE Trans. Pattern Anal. Mach. Intell. (2018)","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Cao, J., Shen, C., Gao, L., Hengel, A.V.D.: Neighbourhood watch: referring expression comprehension via language-guided graph attention networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00206"},{"key":"23_CR43","unstructured":"Wolf, T., et al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"key":"23_CR44","unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems, pp. 802\u2013810 (2015)"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Cross-modal relationship inference for grounding referring expressions. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00427"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Dynamic graph attention for referring expression comprehension. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00474"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gong, B., Wang, L., Huang, W., Yu, D., Luo, J.: A fast and accurate one-stage approach to visual grounding. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00478"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: Mattnet: Modular attention network for referring expression comprehension. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"23_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"23_CR50","doi-asserted-by":"crossref","unstructured":"Yu, L., Tan, H., Bansal, M., Berg, T.L.: A joint speaker-listener-reinforcer model for referring expressions. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.375"},{"key":"23_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, H., Niu, Y., Chang, S.F.: Grounding referring expressions in images by variational context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00437"},{"key":"23_CR52","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Wu, Q., Shen, C., Reid, I., van den Hengel, A.: Parallel attention: a unified framework for visual object discovery through dialogs and queries. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00447"},{"key":"23_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391\u2013405. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_26"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58568-6_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:22:48Z","timestamp":1731370968000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58568-6_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585679","9783030585686"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58568-6_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"13 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}