{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:22:31Z","timestamp":1775607751304,"version":"3.50.1"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197710","type":"print"},{"value":"9783031197727","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\/978-3-031-19772-7_14","type":"book-chapter","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T22:09:58Z","timestamp":1666908598000},"page":"226-243","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["AdaFocusV3: On Unified Spatial-Temporal Dynamic Video Recognition"],"prefix":"10.1007","author":[{"given":"Yulin","family":"Wang","sequence":"first","affiliation":[]},{"given":"Yang","family":"Yue","sequence":"additional","affiliation":[]},{"given":"Xinhong","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Ali","family":"Hassani","sequence":"additional","affiliation":[]},{"given":"Victor","family":"Kulikov","sequence":"additional","affiliation":[]},{"given":"Nikita","family":"Orlov","sequence":"additional","affiliation":[]},{"given":"Shiji","family":"Song","sequence":"additional","affiliation":[]},{"given":"Humphrey","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Gao","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. arXiv preprint arXiv:2103.15691 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"14_CR2","unstructured":"Bengio, Y., Mesnil, G., Dauphin, Y., Rifai, S.: Better mixing via deep representations. In: ICML, pp. 552\u2013560. PMLR (2013)"},{"key":"14_CR3","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, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? a new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"14_CR5","unstructured":"Chen, J., Li, K., Deng, Q., Li, K., Philip, S.Y.: Distributed deep learning model for intelligent video surveillance systems with edge computing. IEEE Trans. Ind. Inform. (2019)"},{"key":"14_CR6","doi-asserted-by":"publisher","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP, pp. 1724\u20131734. Association for Computational Linguistics, Doha, October 2014. https:\/\/doi.org\/10.3115\/v1\/D14-1179, www.aclweb.org\/anthology\/D14-1179","DOI":"10.3115\/v1\/D14-1179"},{"issue":"1\u201368","key":"14_CR7","first-page":"1","volume":"2000","author":"RT Collins","year":"2000","unstructured":"Collins, R.T., et al.: A system for video surveillance and monitoring. VSAM Final Rep. 2000(1\u201368), 1 (2000)","journal-title":"VSAM Final Rep."},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Davidson, J., et al.: The Youtube video recommendation system. In: Proceedings of the Fourth ACM Conference on Recommender Systems, pp. 293\u2013296 (2010)","DOI":"10.1145\/1864708.1864770"},{"issue":"2","key":"14_CR9","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s13740-016-0060-9","volume":"5","author":"Y Deldjoo","year":"2016","unstructured":"Deldjoo, Y., Elahi, M., Cremonesi, P., Garzotto, F., Piazzolla, P., Quadrana, M.: Content-based video recommendation system based on stylistic visual features. J. Data Semant. 5(2), 99\u2013113 (2016)","journal-title":"J. Data Semant."},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"14_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1007\/978-3-030-58529-7_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Fan","year":"2020","unstructured":"Fan, L., et al.: RubiksNet: learnable 3D-shift for efficient video action recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 505\u2013521. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_30"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: CVPR, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: ICCV, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal multiplier networks for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4768\u20134777 (2017)","DOI":"10.1109\/CVPR.2017.787"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: CVPR, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Figurnov, M., et al.: Spatially adaptive computation time for residual networks. In: CVPR, pp. 1039\u20131048 (2017)","DOI":"10.1109\/CVPR.2017.194"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhang, T., Xu, C.: A unified personalized video recommendation via dynamic recurrent neural networks. In: ACM MM, pp. 127\u2013135 (2017)","DOI":"10.1145\/3123266.3123433"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Gao, R., Oh, T.H., Grauman, K., Torresani, L.: Listen to look: action recognition by previewing audio. In: CVPR, pp. 10457\u201310467 (2020)","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Ghodrati, A., Bejnordi, B.E., Habibian, A.: FrameExit: conditional early exiting for efficient video recognition. In: CVPR, pp. 15608\u201315618 (2021)","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Gong, X., Wang, H., Shou, M.Z., Feiszli, M., Wang, Z., Yan, Z.: Searching for two-stream models in multivariate space for video recognition. In: ICCV, pp. 8033\u20138042 (2021)","DOI":"10.1109\/ICCV48922.2021.00793"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: ICCV, pp. 5842\u20135850 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) (2021)","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: CVPR, pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"14_CR25","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"14_CR26","unstructured":"Huang, G., Chen, D., Li, T., Wu, F., van der Maaten, L., Weinberger, K.Q.: Multi-scale dense networks for resource efficient image classification. In: ICLR (2018)"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Ikizler, N., Forsyth, D.: Searching video for complex activities with finite state models. In: CVPR, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383168"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Jiang, B., Wang, M., Gan, W., Wu, W., Yan, J.: STM: spatiotemporal and motion encoding for action recognition. In: ICCV, pp. 2000\u20132009 (2019)","DOI":"10.1109\/ICCV.2019.00209"},{"issue":"2","key":"14_CR29","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1109\/TPAMI.2017.2670560","volume":"40","author":"YG Jiang","year":"2018","unstructured":"Jiang, Y.G., Wu, Z., Wang, J., Xue, X., Chang, S.F.: Exploiting feature and class relationships in video categorization with regularized deep neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(2), 352\u2013364 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR30","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Kim, H., Jain, M., Lee, J.T., Yun, S., Porikli, F.: Efficient action recognition via dynamic knowledge propagation. In: ICCV, pp. 13719\u201313728 (2021)","DOI":"10.1109\/ICCV48922.2021.01346"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Korbar, B., Tran, D., Torresani, L.: ScSampler: sampling salient clips from video for efficient action recognition. In: ICCV, pp. 6232\u20136242 (2019)","DOI":"10.1109\/ICCV.2019.00633"},{"key":"14_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1007\/978-3-030-01231-1_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Li","year":"2018","unstructured":"Li, D., Qiu, Z., Dai, Q., Yao, T., Mei, T.: Recurrent tubelet proposal and recognition networks for action detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 306\u2013322. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_19"},{"key":"14_CR34","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":"14_CR35","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: ICCV, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Lin, J., Duan, H., Chen, K., Lin, D., Wang, L.: OcSampler: compressing videos to one clip with single-step sampling. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01352"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: TeiNet: towards an efficient architecture for video recognition. In: AAAI, pp. 11669\u201311676 (2020)","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"14_CR38","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 (2021)","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Luo, C., Yuille, A.L.: Grouped spatial-temporal aggregation for efficient action recognition. In: ICCV, pp. 5512\u20135521 (2019)","DOI":"10.1109\/ICCV.2019.00561"},{"key":"14_CR40","doi-asserted-by":"crossref","unstructured":"Materzynska, J., Berger, G., Bax, I., Memisevic, R.: The jester dataset: a large-scale video dataset of human gestures. In: ICCVW (2019)","DOI":"10.1109\/ICCVW.2019.00349"},{"key":"14_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-030-58571-6_6","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Meng","year":"2020","unstructured":"Meng, Y., et al.: AR-Net: adaptive frame resolution for efficient action recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 86\u2013104. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_6"},{"key":"14_CR42","unstructured":"Meng, Y., et al.: AdaFuse: adaptive temporal fusion network for efficient action recognition. In: ICLR (2021)"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: CVPR, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Escalera, S., Lanz, O.: Gate-shift networks for video action recognition. In: CVPR, pp. 1102\u20131111 (2020)","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Sun, X., Panda, R., Chen, C.F.R., Oliva, A., Feris, R., Saenko, K.: Dynamic network quantization for efficient video inference. In: ICCV, pp. 7375\u20137385 (2021)","DOI":"10.1109\/ICCV48922.2021.00728"},{"key":"14_CR46","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 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"14_CR47","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: ICCV, pp. 5552\u20135561 (2019)","DOI":"10.1109\/ICCV.2019.00565"},{"key":"14_CR48","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 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"14_CR49","doi-asserted-by":"crossref","unstructured":"Upchurch, P., et al.: Deep feature interpolation for image content changes. In: CVPR, pp. 7064\u20137073 (2017)","DOI":"10.1109\/CVPR.2017.645"},{"key":"14_CR50","doi-asserted-by":"crossref","unstructured":"Verelst, T., Tuytelaars, T.: Dynamic convolutions: exploiting spatial sparsity for faster inference. In: CVPR, pp. 2320\u20132329 (2020)","DOI":"10.1109\/CVPR42600.2020.00239"},{"key":"14_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":"14_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, Z., Jiang, H., Song, S., Han, Y., Huang, G.: Adaptive focus for efficient video recognition. In: ICCV, October 2021","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"14_CR53","unstructured":"Wang, Y., Huang, R., Song, S., Huang, Z., Huang, G.: Not all images are worth 16x16 words: dynamic transformers for efficient image recognition. In: NeurIPS (2021)"},{"key":"14_CR54","unstructured":"Wang, Y., Lv, K., Huang, R., Song, S., Yang, L., Huang, G.: Glance and focus: a dynamic approach to reducing spatial redundancy in image classification. In: NeurIPS (2020)"},{"key":"14_CR55","unstructured":"Wang, Y., Pan, X., Song, S., Zhang, H., Huang, G., Wu, C.: Implicit semantic data augmentation for deep networks. In: NeurIPS, vol. 32 (2019)"},{"key":"14_CR56","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: AdaFocus v2: end-to-end training of spatial dynamic networks for video recognition. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"14_CR57","doi-asserted-by":"crossref","unstructured":"Wu, W., He, D., Tan, X., Chen, S., Wen, S.: Multi-agent reinforcement learning based frame sampling for effective untrimmed video recognition. In: ICCV, pp. 6222\u20136231 (2019a)","DOI":"10.1109\/ICCV.2019.00632"},{"key":"14_CR58","unstructured":"Wu, Z., Li, H., Xiong, C., Jiang, Y.G., Davis, L.S.: A dynamic frame selection framework for fast video recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2020b)"},{"key":"14_CR59","unstructured":"Wu, Z., Xiong, C., Jiang, Y.G., Davis, L.S.: LiteEval: acoarse-to-fine framework for resource efficient video recognition. In: NeurIPS (2019b)"},{"key":"14_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/978-3-030-58452-8_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Xie","year":"2020","unstructured":"Xie, Z., Zhang, Z., Zhu, X., Huang, G., Lin, S.: Spatially adaptive inference with stochastic feature sampling and interpolation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 531\u2013548. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_31"},{"key":"14_CR61","doi-asserted-by":"crossref","unstructured":"Yeung, S., Russakovsky, O., Mori, G., Fei-Fei, L.: End-to-end learning of action detection from frame glimpses in videos. In: CVPR, pp. 2678\u20132687 (2016)","DOI":"10.1109\/CVPR.2016.293"},{"key":"14_CR62","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, pp. 4694\u20134702 (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"14_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/978-3-030-01246-5_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 831\u2013846. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_49"},{"key":"14_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1007\/978-3-030-01216-8_43","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Zolfaghari","year":"2018","unstructured":"Zolfaghari, M., Singh, K., Brox, T.: ECO: efficient convolutional network for online video understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 695\u2013712. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_43"}],"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\/978-3-031-19772-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:52:34Z","timestamp":1710262354000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19772-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197710","9783031197727"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19772-7_14","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":"28 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)"}}]}}