{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:14:10Z","timestamp":1770333250842,"version":"3.49.0"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198298","type":"print"},{"value":"9783031198304","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\/978-3-031-19830-4_40","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T16:21:10Z","timestamp":1666369270000},"page":"705-723","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["NSNet: Non-saliency Suppression Sampler for\u00a0Efficient Video Recognition"],"prefix":"10.1007","author":[{"given":"Boyang","family":"Xia","sequence":"first","affiliation":[]},{"given":"Wenhao","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Haoran","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Su","sequence":"additional","affiliation":[]},{"given":"Dongliang","family":"He","sequence":"additional","affiliation":[]},{"given":"Haosen","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Xiaoran","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"40_CR1","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? arXiv preprint arXiv:2102.05095 (2021)"},{"key":"40_CR2","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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Han, Y., Wang, X., Sun, Y., Yang, Y.: Action keypoint network for efficient video recognition. arXiv preprint arXiv:2201.06304 (2022)","DOI":"10.1109\/TIP.2022.3191461"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Fan, H., Xu, Z., Zhu, L., Yan, C., Ge, J., Yang, Y.: Watching a small portion could be as good as watching all: towards efficient video classification. In: IJCAI International Joint Conference on Artificial Intelligence (2018)","DOI":"10.24963\/ijcai.2018\/98"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Fang, B., Wu, W., Liu, C., Zhou, Y., He, D., Wang, W.: MaMiCo: macro-to-micro semantic correspondence for self-supervised video representation learning. In: Proceedings of the ACMMM (2022)","DOI":"10.1145\/3503161.3547888"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Gao, R., Oh, T.H., Grauman, K., Torresani, L.: Listen to look: action recognition by previewing audio. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10457\u201310467 (2020)","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Ghodrati, A., Bejnordi, B.E., Habibian, A.: FrameExit: conditional early exiting for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15608\u201315618 (2021)","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Rohrbach, M., Sevilla-Lara, L.: SMART frame selection for action recognition 35(2), 1451\u20131459 (2021). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16235","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"40_CR11","doi-asserted-by":"publisher","first-page":"7436","DOI":"10.1109\/TPAMI.2021.3117837","volume":"44","author":"Y Han","year":"2021","unstructured":"Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44, 7436\u20137456 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"40_CR13","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":"40_CR14","doi-asserted-by":"crossref","unstructured":"Huang, D., et al.: ASCNet: self-supervised video representation learning with appearance-speed consistency. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8096\u20138105 (2021)","DOI":"10.1109\/ICCV48922.2021.00799"},{"issue":"4","key":"40_CR15","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1109\/TIP.2018.2877936","volume":"28","author":"W Huang","year":"2018","unstructured":"Huang, W., et al.: Toward efficient action recognition: principal backpropagation for training two-stream networks. IEEE Trans. Image Process. 28(4), 1773\u20131782 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"40_CR16","doi-asserted-by":"publisher","unstructured":"Ji, Z., Chen, K., Wang, H.: Step-wise hierarchical alignment network for image-text matching. In: Zhou, Z., (ed.) Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event\/Montreal, Canada, 19\u201327 August 2021, pp. 765\u2013771. ijcai.org (2021). https:\/\/doi.org\/10.24963\/ijcai.2021\/106","DOI":"10.24963\/ijcai.2021\/106"},{"issue":"2","key":"40_CR17","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). https:\/\/doi.org\/10.1109\/TPAMI.2017.2670560","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR18","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Kim, H., Jain, M., Lee, J.T., Yun, S., Porikli, F.: Efficient action recognition via dynamic knowledge propagation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13719\u201313728 (2021)","DOI":"10.1109\/ICCV48922.2021.01346"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Korbar, B., Tran, D., Torresani, L.: Scsampler: Sampling salient clips from video for efficient action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00633"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Li, H., Wu, Z., Shrivastava, A., Davis, L.S.: 2D or not 2D? Adaptive 3D convolution selection for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6155\u20136164 (2021)","DOI":"10.1109\/CVPR46437.2021.00609"},{"key":"40_CR22","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. 909\u2013918 (2020)","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"40_CR24","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13894\u201313903 (2022)","DOI":"10.1109\/CVPR52688.2022.01352"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Ma, L., Zhang, Y., Liu, W., Chang, S.F.: Multi-granularity generator for temporal action proposal. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3604\u20133613 (2019)","DOI":"10.1109\/CVPR.2019.00372"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"40_CR27","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":"40_CR28","unstructured":"Meng, Y., et al.: AdaFuse: adaptive temporal fusion network for efficient action recognition. arXiv preprint arXiv:2102.05775 (2021)"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Nguyen, P.X., Ramanan, D., Fowlkes, C.C.: Weakly-supervised action localization with background modeling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5502\u20135511 (2019)","DOI":"10.1109\/ICCV.2019.00560"},{"key":"40_CR30","doi-asserted-by":"crossref","unstructured":"Panda, R., et al.: AdaMML: adaptive multi-modal learning for efficient video recognition. arXiv preprint arXiv:2105.05165 (2021)","DOI":"10.1109\/ICCV48922.2021.00748"},{"key":"40_CR31","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"40_CR32","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"40_CR33","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"40_CR34","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":"40_CR35","doi-asserted-by":"crossref","unstructured":"Su, R., Ouyang, W., Zhou, L., Xu, D.: Improving action localization by progressive cross-stream cooperation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01229"},{"key":"40_CR36","doi-asserted-by":"crossref","unstructured":"Su, R., Yu, Q., Xu, D.: STVGBert: a visual-linguistic transformer based framework for spatio-temporal video grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1533\u20131542 (2021)","DOI":"10.1109\/ICCV48922.2021.00156"},{"key":"40_CR37","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7375\u20137385 (2021)","DOI":"10.1109\/ICCV48922.2021.00728"},{"key":"40_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"40_CR39","doi-asserted-by":"crossref","unstructured":"Tang, P., Wang, X., Bai, X., Liu, W.: Multiple instance detection network with online instance classifier refinement. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2843\u20132851 (2017)","DOI":"10.1109\/CVPR.2017.326"},{"key":"40_CR40","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":"40_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in neural information processing systems, pp. 5998\u20136008 (2017)"},{"key":"40_CR42","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":"40_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, L., Wu, Y., Yang, Y.: Symbiotic attention for egocentric action recognition with object-centric alignment. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)","DOI":"10.1109\/TPAMI.2020.3015894"},{"key":"40_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, Z., Jiang, H., Song, S., Han, Y., Huang, G.: Adaptive focus for efficient video recognition. arXiv preprint arXiv:2105.03245 (2021)","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"40_CR45","first-page":"2432","volume":"33","author":"Y Wang","year":"2020","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. Adv. Neural. Inf. Process. Syst. 33, 2432\u20132444 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"40_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: AdaFocus V2: end-to-end training of spatial dynamic networks for video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20062\u201320072 (2022)","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"40_CR47","doi-asserted-by":"crossref","unstructured":"Wei, Y., Feng, J., Liang, X., Cheng, M.M., Zhao, Y., Yan, S.: Object region mining with adversarial erasing: a simple classification to semantic segmentation approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1568\u20131576 (2017)","DOI":"10.1109\/CVPR.2017.687"},{"key":"40_CR48","doi-asserted-by":"publisher","unstructured":"Werbos, P.J.: Applications of advances in nonlinear sensitivity analysis. In: System modeling and optimization, pp. 762\u2013770. Springer, Berlin, Heidelberg (1982). https:\/\/doi.org\/10.1007\/BFb0006203","DOI":"10.1007\/BFb0006203"},{"key":"40_CR49","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Weakly-supervised spatio-temporal anomaly detection in surveillance video. IJCAI (2021)","DOI":"10.24963\/ijcai.2021\/162"},{"key":"40_CR50","doi-asserted-by":"crossref","unstructured":"Wu, W., He, D., Lin, T., Li, F., Gan, C., Ding, E.: MVFNet: multi-view fusion network for efficient video recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2943\u20132951 (2021)","DOI":"10.1609\/aaai.v35i4.16401"},{"key":"40_CR51","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6222\u20136231 (2019)","DOI":"10.1109\/ICCV.2019.00632"},{"key":"40_CR52","doi-asserted-by":"crossref","unstructured":"Wu, W., He, D., Tan, X., Chen, S., Yang, Y., Wen, S.: Dynamic inference: a new approach toward efficient video action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 676\u2013677 (2020)","DOI":"10.1109\/CVPRW50498.2020.00346"},{"key":"40_CR53","unstructured":"Wu, W., Sun, Z., Ouyang, W.: Transferring textual knowledge for visual recognition. arXiv e-prints pp. arXiv-2207 (2022)"},{"key":"40_CR54","doi-asserted-by":"crossref","unstructured":"Wu, W., et al.: DSANet: dynamic segment aggregation network for video-level representation learning. In Proceedings of the ACMMM (2021)","DOI":"10.1145\/3474085.3475344"},{"key":"40_CR55","unstructured":"Wu, Z., Xiong, C., Jiang, Y.G., Davis, L.S.: LiteEval: a coarse-to-fine framework for resource efficient video recognition. arXiv preprint arXiv:1912.01601 (2019)"},{"key":"40_CR56","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, C., Ma, C.Y., Socher, R., Davis, L.S.: AdaFrame: adaptive frame selection for fast video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1278\u20131287 (2019)","DOI":"10.1109\/CVPR.2019.00137"},{"key":"40_CR57","doi-asserted-by":"crossref","unstructured":"Xia, B., Wang, Z., Wu, W., Wang, H., Han, J.: Temporal saliency query network for efficient video recognition. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19830-4_42"},{"key":"40_CR58","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"40_CR59","doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: Temporal action proposal generation with background constraint. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 3054\u20133062 (2022)","DOI":"10.1609\/aaai.v36i3.20212"},{"key":"40_CR60","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2678\u20132687 (2016)","DOI":"10.1109\/CVPR.2016.293"},{"key":"40_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-58607-2_1","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Zhang","year":"2020","unstructured":"Zhang, M., Song, G., Zhou, H., Liu, Y.: Discriminability distillation in group representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 1\u201319. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_1"},{"key":"40_CR62","doi-asserted-by":"publisher","first-page":"7970","DOI":"10.1109\/TIP.2020.3007826","volume":"29","author":"YD Zheng","year":"2020","unstructured":"Zheng, Y.D., 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":"40_CR63","doi-asserted-by":"crossref","unstructured":"Zhu, C., et al.: Fine-grained video categorization with redundancy reduction attention. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 136\u2013152 (2018)","DOI":"10.1007\/978-3-030-01228-1_9"}],"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\/978-3-031-19830-4_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T00:02:41Z","timestamp":1666396961000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19830-4_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198298","9783031198304"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19830-4_40","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)"}}]}}