{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:30:30Z","timestamp":1778081430715,"version":"3.51.4"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198359","type":"print"},{"value":"9783031198366","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\/978-3-031-19836-6_2","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T09:04:58Z","timestamp":1666343098000},"page":"19-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Sports Video Analysis on\u00a0Large-Scale Data"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5518-093X","authenticated-orcid":false,"given":"Dekun","family":"Wu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2471-9680","authenticated-orcid":false,"given":"He","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7458-8052","authenticated-orcid":false,"given":"Xingce","family":"Bao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3433-1329","authenticated-orcid":false,"given":"Richard P.","family":"Wildes","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Aafaq, N., Akhtar, N., Liu, W., Gilani, S.Z., Mian, A.: Spatio-temporal dynamics and semantic attribute enriched visual encoding for video captioning. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.01277"},{"issue":"6","key":"2_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355390","volume":"52","author":"N Aafaq","year":"2019","unstructured":"Aafaq, N., Mian, A., Liu, W., Gilani, S.Z., Shah, M.: Video description: a survey of methods, datasets, and evaluation metrics. ACM Comput. Surv. 52(6), 1\u201337 (2019)","journal-title":"ACM Comput. Surv."},{"key":"2_CR3","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of ACL (2005)"},{"key":"2_CR4","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding. In: Proceedings of ICML (2021)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Bi, J., Luo, J., Xu, C.: Procedure planning in instructional videos via contextual modeling and model-based policy learning. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01532"},{"key":"2_CR6","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"2_CR7","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: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"2_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the Kinetics dataset. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"2_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/978-3-030-58621-8_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C-Y Chang","year":"2020","unstructured":"Chang, C.-Y., Huang, D.-A., Xu, D., Adeli, E., Fei-Fei, L., Niebles, J.C.: Procedure planning in instructional videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 334\u2013350. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_20"},{"key":"2_CR11","unstructured":"Chen, D., Dolan, W.: Collecting highly parallel data for paraphrase evaluation. In: Proceedings of ACL (2011)"},{"key":"2_CR12","unstructured":"Chen, S., Song, Y., Zhao, Y., Qiu, J., Jin, Q., Hauptmann, A.G.: RUC+CMU: system report for dense captioning events in videos. CoRR abs\/1806.08854 (2018)"},{"key":"2_CR13","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":"2_CR14","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL (2019)"},{"key":"2_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Jhamtani, H., Gangal, V., Hovy, E., Neubig, G., Berg-Kirkpatrick, T.: Learning to generate move-by-move commentary for chess games from large-scale social forum data. In: Proceedings of ACL (2018)","DOI":"10.18653\/v1\/P18-1154"},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"Jocher, G., et al.: YOLOv5:v6.0 (2021). https:\/\/doi.org\/10.5281\/zenodo.5563715","DOI":"10.5281\/zenodo.5563715"},{"key":"2_CR20","unstructured":"Kay, W., et al.: The Kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Niebles, J.C.: Dense-captioning events in videos. In: Proceedings ICCV (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Arslan, A., Serre, T.: The language of actions: recovering the syntax and semantics of goal-directed human activities. In: Proceedings of CVPR (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: Proceedings of ACL (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"2_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1007\/978-3-030-01231-1_32","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Li","year":"2018","unstructured":"Li, Y., Li, Y., Vasconcelos, N.: RESOUND: towards action recognition without representation bias. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 520\u2013535. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_32"},{"key":"2_CR25","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"2_CR27","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":"2_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"issue":"7","key":"2_CR30","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1109\/TPAMI.2012.242","volume":"35","author":"WL Lu","year":"2013","unstructured":"Lu, W.L., Ting, J.A., Little, J.J., Murphy, K.P.: Learning to track and identify players from broadcast sports videos. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1704\u20131716 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Lu, W.L., Ting, J.A., Murphy, K.P., Little, J.J.: Identifying players in broadcast sports videos using conditional random fields. In: proceedings of CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995562"},{"key":"2_CR32","unstructured":"Luo, H., et al.: UniVL: a unified video and language pre-training model for multimodal understanding and generation. CoRR abs\/2002.06353 (2020)"},{"issue":"3","key":"2_CR33","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/0004-3702(77)90026-1","volume":"9","author":"MF Medress","year":"1977","unstructured":"Medress, M.F., et al.: Speech understanding systems: report of a steering committee. Artif. Intell. 9(3), 307\u2013316 (1977)","journal-title":"Artif. Intell."},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: HowTo100M: learning a text-video embedding by watching hundred million narrated video clips. In: Proceedings of CVPR (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"2_CR35","unstructured":"NBA: Official website. http:\/\/www.nba.com\/"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Pan, B., et al.: Spatio-temporal graph for video captioning with knowledge distillation. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of ACL (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"2_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1007\/978-3-030-58589-1_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"JS Park","year":"2020","unstructured":"Park, J.S., Darrell, T., Rohrbach, A.: Identity-aware multi-sentence video description. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 360\u2013378. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_22"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Pei, W., Zhang, J., Wang, X., Ke, L., Shen, X., Tai, Y.W.: Memory-attended recurrent network for video captioning. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.00854"},{"issue":"8","key":"2_CR40","doi-asserted-by":"publisher","first-page":"2617","DOI":"10.1109\/TCSVT.2019.2921655","volume":"30","author":"M Qi","year":"2019","unstructured":"Qi, M., Wang, Y., Li, A., Luo, J.: Sports video captioning via attentive motion representation and group relationship modeling. IEEE Trans. Circ. Syst. Video Technol. 30(8), 2617\u20132633 (2019)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"2_CR41","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of ICML (2021)"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: FineGym: a hierarchical video dataset for fine-grained action understanding. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Shi, B., Ji, L., Niu, Z., Duan, N., Zhou, M., Chen, X.: Learning semantic concepts and temporal alignment for narrated video procedural captioning. In: Proceedings of MM (2020)","DOI":"10.1145\/3394171.3413498"},{"key":"2_CR45","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":"2_CR46","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: Proceedings of ICCV (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"2_CR48","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDER: consensus-based image description evaluation. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. In: Proceedings of NAACL (2015)","DOI":"10.3115\/v1\/N15-1173"},{"key":"2_CR51","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":"2_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-030-01267-0_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Xie","year":"2018","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 318\u2013335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_19"},{"key":"2_CR53","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: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.571"},{"issue":"2","key":"2_CR54","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1109\/TPAMI.2019.2946823","volume":"44","author":"Y Yan","year":"2022","unstructured":"Yan, Y., et al.: Fine-grained video captioning via graph-based multi-granularity interaction learning. IEEE Trans. Pattern Anal. Mach. Intell. 44(2), 666\u2013683 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR55","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Describing videos by exploiting temporal structure. In: Proceedings of ICCV (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"2_CR56","unstructured":"Yehao, L., Yingwei, P., Jingwen, C., Ting, Y., Tao, M.: X-modaler: a versatile and high-performance codebase for cross-modal analytics. In: Proceedings of MM (2021)"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Yu, H., Cheng, S., Ni, B., Wang, M., Zhang, J., Yang, X.: Fine-grained video captioning for sports narrative. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00629"},{"key":"2_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, C., Gupta, A., Zisserman, A.: Temporal query networks for fine-grained video understanding. In: Proceedings of CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"2_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, J., Peng, Y.: Object-aware aggregation with bidirectional temporal graph for video captioning. In: Proceedings of CVPR (2019)","DOI":"10.1109\/CVPR.2019.00852"},{"key":"2_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Object relational graph with teacher-recommended learning for video captioning. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"2_CR61","doi-asserted-by":"crossref","unstructured":"Zhao, H., Hadji, I., Dvornik, N., Derpanis, K.G., Wildes, R.P., Jepson, A.D.: P3IV: probabilistic procedure planning from instructional videos with weak supervision. In: Proceedings of CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00295"},{"key":"2_CR62","doi-asserted-by":"crossref","unstructured":"Zheng, Q., Wang, C., Tao, D.: Syntax-aware action targeting for video captioning. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"2_CR63","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"2_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-030-58558-7_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Zhu","year":"2020","unstructured":"Zhu, L., Rematas, K., Curless, B., Seitz, S.M., Kemelmacher-Shlizerman, I.: Reconstructing NBA players. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 177\u2013194. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_11"},{"key":"2_CR65","unstructured":"Zhu, Y., et al.: A comprehensive study of deep video action recognition. arXiv preprint arXiv:2012.06567 (2020)"}],"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\/978-3-031-19836-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T23:04:11Z","timestamp":1666652651000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19836-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198359","9783031198366"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19836-6_2","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":"22 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)"}}]}}