{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:20:18Z","timestamp":1743038418162,"version":"3.40.3"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031263156"},{"type":"electronic","value":"9783031263163"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26316-3_33","type":"book-chapter","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:02:32Z","timestamp":1677657752000},"page":"554-570","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PromptLearner-CLIP: Contrastive Multi-Modal Action Representation Learning with\u00a0Context Optimization"],"prefix":"10.1007","author":[{"given":"Zhenxing","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaoyun","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoqilin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuqi","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR, pp. 6077\u20136086. IEEE, Salt Lake City, UT, USA (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. In: ICCV, pp. 6836\u20136846. IEEE, Montreal, Canada (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"33_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, pp. 813\u2013824. ACM, Virtual (2021)"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: CVPR, pp. 4724\u20134733. IEEE, Honolulu, HI, USA (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Choutas, V., Weinzaepfel, P., Revaud, J., Schmid, C.: PoTion: pose motion representation for action recognition. In: CVPR, pp. 7024\u20137033. IEEE, Salt Lake City (2018)","DOI":"10.1109\/CVPR.2018.00734"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Crasto, N., Weinzaepfel, P., Alahari, K., Schmid, C.: MARS: motion-augmented RGB stream for action recognition. In: CVPR, pp. 7874\u20137883. IEEE, Long Beach, CA, USA (2019)","DOI":"10.1109\/CVPR.2019.00807"},{"key":"33_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR, pp. 1\u201321. Virtual (2021)"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: ICCV, pp. 6824\u20136835. IEEE, Montreal, Canada (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Fan, L., Huang, W., Gan, C., Ermon, S., Gong, B., Huang, J.: End-to-end learning of motion representation for video understanding. In: CVPR, pp. 6016\u20136025. IEEE, Salt Lake City, UT, USA (2018)","DOI":"10.1109\/CVPR.2018.00630"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: CVPR, pp. 200\u2013210. IEEE, Seattle, WA, USA (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: CVPR, pp. 6202\u20136211. IEEE, Seoul, Korea (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9726\u20139735. IEEE, Seattle, WA, USA (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Huang, G., Bors, A.G.: Learning spatio-temporal representations with temporal squeeze pooling. In: ICASSP, pp. 2103\u20132107. IEEE, Barcelona, Spain (2020)","DOI":"10.1109\/ICASSP40776.2020.9054200"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Huang, G., Bors, A.G.: Busy-quiet video disentangling for video classification. In: WACV, pp. 1341\u20131350. IEEE, Waikoloa, HI, USA (2022)","DOI":"10.1109\/WACV51458.2022.00083"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Kar, A., Rai, N., Sikka, K., Sharma, G.: AdaScan: adaptive scan pooling in deep convolutional neural networks for human action recognition in videos. In: CVPR, pp. 5699\u20135708. IEEE, Honolulu, HI, USA (2017)","DOI":"10.1109\/CVPR.2017.604"},{"key":"33_CR16","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017)"},{"key":"33_CR17","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: NeurIPS, pp. 18661\u201318673. MIT Press, Virtual (2021)"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: ICCV, pp. 2556\u20132563. IEEE, Barcelona, Spain (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Lei, J., et al.: Less is more: clipBERT for video-and-language learning via sparse sampling. In: CVPR, pp. 7331\u20137341. IEEE, Virtual (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Li, J., Wei, P., Zhang, Y., Zheng, N.: A slow-i-fast-p architecture for compressed video action recognition. In: ACM MM, pp. 2039\u20132047. ACM, Seattle, WA, USA (2020)","DOI":"10.1145\/3394171.3413641"},{"issue":"11","key":"33_CR21","doi-asserted-by":"publisher","first-page":"2990","DOI":"10.1109\/TMM.2020.2965434","volume":"22","author":"J Li","year":"2020","unstructured":"Li, J., Liu, X., Zhang, W., Zhang, M., Song, J., Sebe, N.: Spatiotemporal attention networks for action recognition and detection. IEEE Trans. Multimedia 22(11), 2990\u20133001 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, Y., Zhou, Z., Qiao, Y.: SmallBigNet: integrating core and contextual views for video classification. In: CVPR, pp. 1092\u20131101. IEEE, Seattle, WA, USA (2020)","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L.: Tea: temporal excitation and aggregation for action recognition. In: CVPR, pp. 906\u2013915. IEEE, Seattle, WA, USA (2020)","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: ICCV, pp. 7082\u20137092. IEEE, Seoul, Korea (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: TEINet: towards an efficient architecture for video recognition. In: AAAI, pp. 11669\u201311676. AAAI, New York, USA (2020)","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., Lu, T.: TAM: temporal adaptive module for video recognition. In: ICCV, pp. 13708\u201313718. IEEE, Montreal, Canada (2021)","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., Asselmann, D.: Video transformer network. In: ICCV, pp. 3163\u20133172. IEEE, Montreal, Canada (2021)","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Pan, T., Song, Y., Yang, T., Jiang, W., Liu, W.: VideoMoCo: contrastive video representation learning with temporally adversarial examples. In: CVPR, pp. 11200\u201311209. IEEE, Virtual (2021)","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"33_CR29","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. ACM, Virtual (2021)"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Ranasinghe, K., Naseer, M., Khan, S., Khan, F.S., Ryoo, M.: Self-supervised video transformer. In: CVPR, pp. 2874\u20132884. IEEE, New Orleans, Louisiana, USA (2022)","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"33_CR31","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild (2012)"},{"key":"33_CR32","doi-asserted-by":"crossref","unstructured":"Thatipelli, A., Narayan, S., Khan, S., Anwer, R.M., Khan, F.S., Ghanem, B.: Spatio-temporal relation modeling for few-shot action recognition. In: CVPR, pp. 19958\u201319967. IEEE, New Orleans, Louisiana, USA (2022)","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: ICCV, pp. 4489\u20134497. IEEE, Santiago, Chile (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"33_CR34","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, pp. 6450\u20136459. IEEE, Salt Lake City, UT, USA (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Truong, T.D., et al.: DirecFormer: a directed attention in transformer approach to robust action recognition. In: CVPR, pp. 20030\u201320040. IEEE, New Orleans, Louisiana, USA (2022)","DOI":"10.1109\/CVPR52688.2022.01940"},{"key":"33_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998\u20136008. MIT Press, Long Beach, CA, USA (2017)"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, W., Li, W., Van Gool, L.: Appearance-and-relation networks for video classification. In: CVPR, pp. 1430\u20131439. IEEE, Salt Lake City, UT, USA (2018)","DOI":"10.1109\/CVPR.2018.00155"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: TDN: temporal difference networks for efficient action recognition. In: CVPR, pp. 1895\u20131904. IEEE, Virtual (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"issue":"11","key":"33_CR39","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2019","unstructured":"Wang, L., et al.: Temporal segment networks for action recognition in videos. IEEE Trans. Pattern Anal. Mach. Intell. 41(11), 2740\u20132755 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR40","unstructured":"Wang, M., Xing, J., Liu, Y.: ActionCLIP: a new paradigm for video action recognition (2021)"},{"key":"33_CR41","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: BEVT: BERT pretraining of video transformers. In: CVPR, pp. 14733\u201314743. IEEE, New Orleans, Louisiana, USA (2022)","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"33_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-3-030-01228-1_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Wang","year":"2018","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 413\u2013431. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_25"},{"key":"33_CR43","doi-asserted-by":"crossref","unstructured":"Wu, Z., Jiang, Y.G., Wang, X., Ye, H., Xue, X.: Multi-stream multi-class fusion of deep networks for video classification. In: ACM MM, pp. 791\u2013800. ACM, Amsterdam, Netherlands (2016)","DOI":"10.1145\/2964284.2964328"},{"key":"33_CR44","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"},{"issue":"10","key":"33_CR45","doi-asserted-by":"publisher","first-page":"4941","DOI":"10.1109\/TIP.2019.2917283","volume":"28","author":"B Xu","year":"2019","unstructured":"Xu, B., Ye, H., Zheng, Y., Wang, H., Luwang, T., Jiang, Y.: Dense dilated network for video action recognition. IEEE Trans. Image Process. 28(10), 4941\u20134953 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR46","doi-asserted-by":"crossref","unstructured":"Yang, C., Xu, Y., Shi, J., Dai, B., Zhou, B.: Temporal pyramid network for action recognition. In: CVPR, pp. 588\u2013597. IEEE, Seattle, WA, USA (2020)","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"33_CR47","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Dynamic graph attention for referring expression comprehension. In: ICCV, pp. 4643\u20134652. IEEE, Seoul, Korea (2019)","DOI":"10.1109\/ICCV.2019.00474"},{"key":"33_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hao, Y., Ngo, C.W.: Token shift transformer for video classification. In: ACM MM, pp. 917\u2013925. ACM, Chengdu, China (2021)","DOI":"10.1145\/3474085.3475272"},{"key":"33_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: VidTr: video transformer without convolutions. In: ICCV, pp. 13577\u201313587. IEEE, Montreal, Canada (2021)","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"33_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Wang, G., Luo, C., Zeng, W., Zha, Z.J.: Self-supervised visual representations learning by contrastive mask prediction. In: ICCV, pp. 10160\u201310169. IEEE, Virtual (2021)","DOI":"10.1109\/ICCV48922.2021.01000"},{"key":"33_CR51","doi-asserted-by":"publisher","first-page":"7970","DOI":"10.1109\/TIP.2020.3007826","volume":"29","author":"Y Zheng","year":"2020","unstructured":"Zheng, Y., Liu, Z., Lu, T., Wang, L.: Dynamic sampling networks for efficient action recognition in videos. IEEE Trans. Image Process. 29, 7970\u20137983 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR52","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130, 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"33_CR53","doi-asserted-by":"crossref","unstructured":"Zhu, L., Yang, Y.: ActBERT: learning global-local video-text representations. In: CVPR, pp. 8746\u20138755. IEEE, Seattle, WA, USA (2020)","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"33_CR54","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104108","volume":"107","author":"M Zong","year":"2021","unstructured":"Zong, M., Wang, R., Chen, X., Chen, Z., Gong, Y.: Motion saliency based multi-stream multiplier ResNets for action recognition. Image Vis. Comput. 107, 104108 (2021)","journal-title":"Image Vis. Comput."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26316-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:34:25Z","timestamp":1677659665000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26316-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263156","9783031263163"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26316-3_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","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":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","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 Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"33% - 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":"3.3","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":"2.6","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":"For the ACCV 2022 workshops 25 papers have been accepted from 40 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)"}}]}}