{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T13:31:12Z","timestamp":1779888672290,"version":"3.53.1"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585570","type":"print"},{"value":"9783030585587","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\/978-3-030-58558-7_35","type":"book-chapter","created":{"date-parts":[[2020,10,28]],"date-time":"2020-10-28T09:03:08Z","timestamp":1603875788000},"page":"593-610","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":69,"title":["Large Scale Holistic Video Understanding"],"prefix":"10.1007","author":[{"given":"Ali","family":"Diba","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohsen","family":"Fayyaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vivek","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manohar","family":"Paluri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Gall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rainer","family":"Stiefelhagen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,29]]},"reference":[{"key":"35_CR1","unstructured":"Google Vision AI API. cloud.google.com\/vision"},{"key":"35_CR2","unstructured":"Sensifai Video Tagging API. www.sensifai.com"},{"key":"35_CR3","unstructured":"Abu-El-Haija, S., et al.: Youtube-8m: a large-scale video classification benchmark. arXiv:1609.08675 (2016)"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Chen, S., Jiang, Y.G.: Motion guided spatial attention for video captioning. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"35_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1007\/11744047_33","volume-title":"Computer Vision \u2013 ECCV 2006","author":"N Dalal","year":"2006","unstructured":"Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 428\u2013441. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744047_33"},{"key":"35_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/978-3-030-01225-0_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Damen","year":"2018","unstructured":"Damen, D., et al.: Scaling egocentric vision: the Epic-Kitchens dataset. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 753\u2013771. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_44"},{"key":"35_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-030-01225-0_18","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Diba","year":"2018","unstructured":"Diba, A., et al.: Spatio-temporal channel correlation networks for action classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 299\u2013315. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_18"},{"key":"35_CR11","unstructured":"Diba, A., et al.: Temporal 3D convnets using temporal transition layer. In: CVPR Workshops (2018)"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Van Gool, L.: Deep temporal linear encoding networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.168"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Van Gool, L., Stiefelhagen, R.: DynamoNet: dynamic action and motion network. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00629"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Fernando, B., Bilen, H., Gavves, E., Gould, S.: Self-supervised video representation learning with odd-one-out networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.607"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Fernando, B., Gavves, E., Oramas, J.M., Ghodrati, A., Tuytelaars, T.: Modeling video evolution for action recognition. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"35_CR19","doi-asserted-by":"publisher","first-page":"2782","DOI":"10.1109\/TPAMI.2013.65","volume":"35","author":"A Gaidon","year":"2013","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Temporal localization of actions with actoms. PAMI 35, 2782\u20132795 (2013)","journal-title":"PAMI"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: ActionVLAD: learning spatio-temporal aggregation for action classification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.337"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Tran, D., Torresani, L., Ramanan, D.: Distinit: learning video representations without a single labeled video. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00094"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Learning spatio-temporal features with 3D residual networks for action recognition. In: ICCV (2017)","DOI":"10.1109\/ICCVW.2017.373"},{"key":"35_CR25","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"35_CR26","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"35_CR27","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv:1705.06950 (2017)"},{"key":"35_CR28","doi-asserted-by":"crossref","unstructured":"Klaser, A., Marsza\u0142ek, M., Schmid, C.: A spatio-temporal descriptor based on 3d-gradients. In: BMVC (2008)","DOI":"10.5244\/C.22.99"},{"key":"35_CR29","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Stiefelhagen, R., Serre, T.: HMDB51: a large video database for human motion recognition. In: High Performance Computing in Science and Engineering (2013)","DOI":"10.1007\/978-3-642-33374-3_41"},{"key":"35_CR30","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Liu, S., Ren, Z., Yuan, J.: SibNet: sibling convolutional encoder for video captioning. In: ACMM (2018)","DOI":"10.1145\/3240508.3240667"},{"key":"35_CR32","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: Wordnet: a lexical database for English. Commun. ACM 38, 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"35_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/978-3-319-46448-0_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"I Misra","year":"2016","unstructured":"Misra, I., Zitnick, C.L., Hebert, M.: Shuffle and learn: unsupervised learning using temporal order verification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 527\u2013544. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_32"},{"key":"35_CR34","doi-asserted-by":"crossref","unstructured":"Ng, J.Y.H., Choi, J., Neumann, J., Davis, L.S.: ActionFlowNet: learning motion representation for action recognition. In: WACV (2018)","DOI":"10.1109\/WACV.2018.00179"},{"key":"35_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-642-15552-9_29","volume-title":"Computer Vision \u2013 ECCV 2010","author":"JC Niebles","year":"2010","unstructured":"Niebles, J.C., Chen, C.-W., Fei-Fei, L.: Modeling temporal structure of decomposable motion segments for activity classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6312, pp. 392\u2013405. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15552-9_29"},{"key":"35_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1007\/978-3-030-01264-9_39","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Ray","year":"2018","unstructured":"Ray, J., et al.: Scenes-objects-actions: a multi-task, multi-label video dataset. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 660\u2013676. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_39"},{"key":"35_CR37","doi-asserted-by":"crossref","unstructured":"Roethlingshoefer, V., Sharma, V., Stiefelhagen, R.: Self-supervised face-grouping on graph. In: ACM MM (2019)","DOI":"10.1145\/3343031.3351071"},{"key":"35_CR38","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: ICPR (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"35_CR39","doi-asserted-by":"crossref","unstructured":"Scovanner, P., Ali, S., Shah, M.: A 3-dimensional sift descriptor and its application to action recognition. In: ACM MM (2007)","DOI":"10.1145\/1291233.1291311"},{"key":"35_CR40","unstructured":"Sharma, V., Sarfraz, S., Stiefelhagen, R.: A simple and effective technique for face clustering in TV series. In: CVPR workshop on Brave New Motion Representations (2017)"},{"key":"35_CR41","doi-asserted-by":"crossref","unstructured":"Sharma, V., Tapaswi, M., Sarfraz, M.S., Stiefelhagen, R.: Self-supervised learning of face representations for video face clustering. In: International Conference on Automatic Face and Gesture Recognition (2019)","DOI":"10.1109\/FG.2019.8756609"},{"key":"35_CR42","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/TBIOM.2019.2947264","volume":"2","author":"V Sharma","year":"2019","unstructured":"Sharma, V., Tapaswi, M., Sarfraz, M.S., Stiefelhagen, R.: Video face clustering with self-supervised representation learning. IEEE Trans. Biometrics Behav. Identity Sci. 2, 145\u2013157 (2019)","journal-title":"IEEE Trans. Biometrics Behav. Identity Sci."},{"key":"35_CR43","doi-asserted-by":"crossref","unstructured":"Sharma, V., Tapaswi, M., Sarfraz, M.S., Stiefelhagen, R.: Clustering based contrastive learning for improving face representations. In: International Conference on Automatic Face and Gesture Recognition (2020)","DOI":"10.1109\/FG47880.2020.00011"},{"key":"35_CR44","unstructured":"Sharma, V., Tapaswi, M., Stiefelhagen, R.: Deep multimodal feature encoding for video ordering. In: ICCV Workshop on Holistic Video Understanding (2019)"},{"key":"35_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"35_CR46","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"35_CR47","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402 (2012)"},{"key":"35_CR48","doi-asserted-by":"crossref","unstructured":"Sun, L., Jia, K., Yeung, D.Y., Shi, B.E.: Human action recognition using factorized spatio-temporal convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.522"},{"key":"35_CR49","unstructured":"Tang, P., Wang, X., Shi, B., Bai, X., Liu, W., Tu, Z.: Deep fishernet for object classification. arXiv:1608.00182 (2016)"},{"key":"35_CR50","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"35_CR51","unstructured":"Tran, D., Ray, J., Shou, Z., Chang, S.F., Paluri, M.: Convnet architecture search for spatiotemporal feature learning. arXiv:1708.05038 (2017)"},{"key":"35_CR52","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00565"},{"key":"35_CR53","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"35_CR54","doi-asserted-by":"crossref","unstructured":"Wang, B., Ma, L., Zhang, W., Jiang, W., Wang, J., Liu, W.: Controllable video captioning with POS sequence guidance based on gated fusion network. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00273"},{"key":"35_CR55","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"35_CR56","doi-asserted-by":"crossref","unstructured":"Wang, J., Wang, W., Huang, Y., Wang, L., Tan, T.: M3: multimodal memory modelling for video captioning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00784"},{"key":"35_CR57","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, W., Li, W., Van Gool, L.: Appearance-and-relation networks for video classification. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00155"},{"key":"35_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1007\/978-3-319-10602-1_37","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Wang","year":"2014","unstructured":"Wang, L., Qiao, Yu., Tang, X.: Video action detection with relational dynamic-poselets. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 565\u2013580. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_37"},{"key":"35_CR59","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"35_CR60","doi-asserted-by":"crossref","unstructured":"Wei, D., Lim, J., Zisserman, A., Freeman, W.T.: Learning and using the arrow of time. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00840"},{"key":"35_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1007\/978-3-540-88688-4_48","volume-title":"Computer Vision \u2013 ECCV 2008","author":"G Willems","year":"2008","unstructured":"Willems, G., Tuytelaars, T., Van Gool, L.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5303, pp. 650\u2013663. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88688-4_48"},{"key":"35_CR62","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"35_CR63","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"35_CR64","doi-asserted-by":"crossref","unstructured":"Zhao, H., Yan, Z., Torresani, L., Torralba, A.: HACS: human action clips and segments dataset for recognition and temporal localization. arXiv:1712.09374 (2019)","DOI":"10.1109\/ICCV.2019.00876"}],"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\/978-3-030-58558-7_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:58:08Z","timestamp":1730105888000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58558-7_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585570","9783030585587"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58558-7_35","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":"29 October 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.","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)"}}]}}