{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:14:52Z","timestamp":1778080492417,"version":"3.51.4"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200588","type":"print"},{"value":"9783031200595","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\/978-3-031-20059-5_12","type":"book-chapter","created":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:02:50Z","timestamp":1666972970000},"page":"201-218","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Spatial and\u00a0Visual Perspective-Taking via\u00a0View Rotation and\u00a0Relation Reasoning for\u00a0Embodied Reference Understanding"],"prefix":"10.1007","author":[{"given":"Cheng","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sibei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"12_CR1","unstructured":"Agarap, A.F.: Deep learning using rectified linear units (ReLU). arXiv preprint arXiv:1803.08375 (2018)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Banerjee, P., Gokhale, T., Yang, Y., Baral, C.: Weakly supervised relative spatial reasoning for visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1908\u20131918 (2021)","DOI":"10.1109\/ICCV48922.2021.00192"},{"key":"12_CR3","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1177\/0146167297237008","volume":"23","author":"CD Batson","year":"1997","unstructured":"Batson, C.D., Early, S., Salvarani, G.: Perspective taking: imagining how another feels versus imaging how you would feel. Pers. Soc. Psychol. Bull. 23, 751\u2013758 (1997)","journal-title":"Pers. Soc. Psychol. Bull."},{"key":"12_CR4","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: Adabins: depth estimation using adaptive bins. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4009\u20134018 (2021)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: OpenPose: realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 172\u2013186 (2019)","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"12_CR6","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":"12_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Yourefit: embodied reference understanding with language and gesture. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1385\u20131395 (2021)","DOI":"10.1109\/ICCV48922.2021.00142"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Clinton, J.A., Magliano, J.P., Skowronski, J.J.: Gaining perspective on spatial perspective taking. J. Cogn. Psychol. 85\u201397 (2018)","DOI":"10.1080\/20445911.2017.1364254"},{"key":"12_CR9","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":"12_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"12_CR12","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing Systems (2014)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Fan, L., Qiu, S., Zheng, Z., Gao, T., Zhu, S.C., Zhu, Y.: Learning triadic belief dynamics in nonverbal communication from videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7312\u20137321 (2021)","DOI":"10.1109\/CVPR46437.2021.00723"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition (CVPR), pp. 2002\u20132011 (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"12_CR15","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1115\u20131124 (2017)","DOI":"10.1109\/CVPR.2017.470"},{"key":"12_CR16","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. In: International Conference on Learning Representations (2018)"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"12_CR18","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (2016)"},{"key":"12_CR19","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.neunet.2020.05.004","volume":"129","author":"A Kroner","year":"2020","unstructured":"Kroner, A., Senden, M., Driessens, K., Goebel, R.: Contextual encoder-decoder network for visual saliency prediction. Neural Netw. 129, 261\u2013270 (2020)","journal-title":"Neural Netw."},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Ladicky, L., Shi, J., Pollefeys, M.: Pulling things out of perspective. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 89\u201396 (2014)","DOI":"10.1109\/CVPR.2014.19"},{"key":"12_CR21","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 (CVPR), pp. 10880\u201310889 (2020)","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"12_CR22","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":"12_CR23","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1950\u20131959 (2019)","DOI":"10.1109\/CVPR.2019.00205"},{"key":"12_CR24","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 (CVPR), pp. 10034\u201310043 (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"12_CR25","unstructured":"Mao, J., Gan, C., Kohli, P., Tenenbaum, J.B., Wu, J.: The neuro-symbolic concept learner: interpreting scenes, words, and sentences from natural supervision. In: International Conference on Learning Representations (2019)"},{"key":"12_CR26","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Mertan, A., Duff, D.J., Unal, G.: Single image depth estimation: an overview. arXiv preprint arXiv:2104.06456 (2021)","DOI":"10.1016\/j.dsp.2022.103441"},{"key":"12_CR28","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":"12_CR29","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8026\u20138037 (2019)"},{"key":"12_CR30","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: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Qi, X., Liao, R., Liu, Z., Urtasun, R., Jia, J.: Geonet: geometric neural network for joint depth and surface normal estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 283\u2013291 (2018)","DOI":"10.1109\/CVPR.2018.00037"},{"key":"12_CR32","doi-asserted-by":"publisher","first-page":"107404","DOI":"10.1016\/j.patcog.2020.107404","volume":"106","author":"X Qin","year":"2020","unstructured":"Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R., Jagersand, M.: $$\\rm {U^2}$$-net: going deeper with nested u-structure for salient object detection. Pattern Recognit. 106, 107404 (2020)","journal-title":"Pattern Recognit."},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Qiu, S., Liu, H., Zhang, Z., Zhu, Y., Zhu, S.C.: Human-robot interaction in a shared augmented reality workspace. In: Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2020)","DOI":"10.1109\/IROS45743.2020.9340781"},{"key":"12_CR34","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Sadhu, A., Chen, K., Nevatia, R.: Zero-shot grounding of objects from natural language queries. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4694\u20134703 (2019)","DOI":"10.1109\/ICCV.2019.00479"},{"key":"12_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"12_CR37","unstructured":"Stacy, S., Zhao, Q., Zhao, M., Kleiman-Weiner, M., Gao, T.: Intuitive signaling through an \u201cimagined we\u201d. In: Proceedings of the Annual Meeting of the Cognitive Science Society (CogSci) (2020)"},{"key":"12_CR38","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1016\/j.cognition.2013.06.008","volume":"129","author":"A Surtees","year":"2013","unstructured":"Surtees, A., Apperly, I., Samson, D.: Similarities and differences in visual and spatial perspective-taking processes. Cognition 129, 426\u2013438 (2013)","journal-title":"Cognition"},{"key":"12_CR39","unstructured":"Tieleman, T., Hinton, G., et al.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA Neural Netw. Mach. Learn. 4, 26\u201331 (2012)"},{"key":"12_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"12_CR41","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1960\u20131968 (2019)","DOI":"10.1109\/CVPR.2019.00206"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wu, C.J., Zhu, Y., Joo, J.: Communicative learning with natural gestures for embodied navigation agents with human-in-the-scene. In: Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2021)","DOI":"10.1109\/IROS51168.2021.9636208"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Wang, X., Sebe, N.: PAD-Net: multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 675\u2013684 (2018)","DOI":"10.1109\/CVPR.2018.00077"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Cross-modal relationship inference for grounding referring expressions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4145\u20134154 (2019)","DOI":"10.1109\/CVPR.2019.00427"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Dynamic graph attention for referring expression comprehension. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4644\u20134653 (2019)","DOI":"10.1109\/ICCV.2019.00474"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Graph-structured referring expression reasoning in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9952\u20139961 (2020)","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"12_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1007\/978-3-030-58529-7_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Yang","year":"2020","unstructured":"Yang, S., Li, G., Yu, Y.: Propagating over phrase relations for one-stage visual grounding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 589\u2013605. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_35"},{"issue":"8","key":"12_CR48","doi-asserted-by":"publisher","first-page":"2765","DOI":"10.1109\/TPAMI.2020.2973983","volume":"43","author":"S Yang","year":"2020","unstructured":"Yang, S., Li, G., Yu, Y.: Relationship-embedded representation learning for grounding referring expressions. IEEE Trans. Pattern Anal. Mach. Intell. 43(8), 2765\u20132779 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-030-58568-6_23","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Yang","year":"2020","unstructured":"Yang, Z., Chen, T., Wang, L., Luo, J.: Improving one-stage visual grounding by recursive sub-query construction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 387\u2013404. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_23"},{"key":"12_CR50","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4683\u20134693 (2019)","DOI":"10.1109\/ICCV.2019.00478"},{"key":"12_CR51","unstructured":"Yi, K., Wu, J., Gan, C., Torralba, A., Kohli, P., Tenenbaum, J.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. In: Advances in Neural Information Processing Systems (2018)"},{"key":"12_CR52","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: Mattnet: modular attention network for referring expression comprehension. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1307\u20131315 (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"12_CR53","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":"12_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, H., Niu, Y., Chang, S.F.: Grounding referring expressions in images by variational context. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4158\u20134166 (2018)","DOI":"10.1109\/CVPR.2018.00437"}],"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\/978-3-031-20059-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:07:51Z","timestamp":1666973271000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20059-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200588","9783031200595"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20059-5_12","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":"29 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)"}}]}}