{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:31:04Z","timestamp":1783823464503,"version":"3.55.0"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585709","type":"print"},{"value":"9783030585716","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58571-6_6","type":"book-chapter","created":{"date-parts":[[2020,11,8]],"date-time":"2020-11-08T16:02:34Z","timestamp":1604851354000},"page":"86-104","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":121,"title":["AR-Net: Adaptive Frame Resolution for Efficient Action Recognition"],"prefix":"10.1007","author":[{"given":"Yue","family":"Meng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chung-Ching","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rameswar","family":"Panda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prasanna","family":"Sattigeri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonid","family":"Karlinsky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aude","family":"Oliva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kate","family":"Saenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rogerio","family":"Feris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,9]]},"reference":[{"issue":"6","key":"6_CR1","first-page":"33","volume":"29","author":"EH Adelson","year":"1984","unstructured":"Adelson, E.H., Anderson, C.H., Bergen, J.R., Burt, P.J., Ogden, J.M.: Pyramid methods in image processing. RCA Eng. 29(6), 33\u201341 (1984)","journal-title":"RCA Eng."},{"key":"6_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/978-3-030-11018-5_25","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"A Araujo","year":"2019","unstructured":"Araujo, A., Negrevergne, B., Chevaleyre, Y., Atif, J.: Training compact deep learning models for video classification using circulant matrices. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11132, pp. 271\u2013286. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11018-5_25"},{"key":"6_CR3","unstructured":"Bengio, E., Bacon, P.L., Pineau, J., Precup, D.: Conditional computation in neural networks for faster models. arXiv preprint arXiv:1511.06297 (2015)"},{"key":"6_CR4","unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"6_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/978-3-319-46493-0_22","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Cai","year":"2016","unstructured":"Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 354\u2013370. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_22"},{"key":"6_CR7","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":"6_CR8","unstructured":"Chen, C.F., Fan, Q., Mallinar, N., Sercu, T., Feris, R.: Big-little net: An efficient multi-scale feature representation for visual and speech recognition. arXiv preprint arXiv:1807.03848 (2018)"},{"key":"6_CR9","unstructured":"Chen, W., Wilson, J., Tyree, S., Weinberger, K., Chen, Y.: Compressing neural networks with the hashing trick. In: International Conference on Machine Learning, pp. 2285\u20132294 (2015)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Ch\u00e9ron, G., Laptev, I., Schmid, C.: P-CNN: pose-based CNN features for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3218\u20133226 (2015)","DOI":"10.1109\/ICCV.2015.368"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Dong, X., Huang, J., Yang, Y., Yan, S.: More is less: a more complicated network with less inference complexity. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5840\u20135848 (2017)","DOI":"10.1109\/CVPR.2017.205"},{"key":"6_CR14","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":"6_CR15","unstructured":"Fan, Q., Chen, C.F.R., Kuehne, H., Pistoia, M., Cox, D.: More is less: learning efficient video representations by big-little network and depthwise temporal aggregation. In: Advances in Neural Information Processing Systems, pp. 2261\u20132270 (2019)"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"6_CR17","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":"6_CR18","doi-asserted-by":"crossref","unstructured":"Figurnov, M., et al.: Spatially adaptive computation time for residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1039\u20131048 (2017)","DOI":"10.1109\/CVPR.2017.194"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Gao, M., Yu, R., Li, A., Morariu, V.I., Davis, L.S.: Dynamic zoom-in network for fast object detection in large images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6926\u20136935 (2018)","DOI":"10.1109\/CVPR.2018.00724"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Gao, R., Oh, T.H., Grauman, K., Torresani, L.: Listen to look: Action recognition by previewing audio. arXiv preprint arXiv:1912.04487 (2019)","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J.: Finding action tubes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 759\u2013768 (2015)","DOI":"10.1109\/CVPR.2015.7298676"},{"issue":"10","key":"6_CR22","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1145\/84537.84552","volume":"33","author":"PW Glynn","year":"1990","unstructured":"Glynn, P.W.: Likelihood ratio gradient estimation for stochastic systems. Commun. ACM 33(10), 75\u201384 (1990)","journal-title":"Commun. ACM"},{"key":"6_CR23","unstructured":"Graves, A.: Adaptive computation time for recurrent neural networks. arXiv preprint arXiv:1603.08983 (2016)"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Guo, Y., Shi, H., Kumar, A., Grauman, K., Rosing, T., Feris, R.: SpotTune: transfer learning through adaptive fine-tuning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4805\u20134814 (2019)","DOI":"10.1109\/CVPR.2019.00494"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"6_CR26","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"},{"key":"6_CR27","unstructured":"Howard, A.G., et al.: MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"6_CR28","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: Alexnet-level accuracy with 50x fewer parameters and $$<$$0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016)"},{"key":"6_CR29","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with Gumbel-Softmax. arXiv preprint arXiv:1611.01144 (2016)"},{"issue":"2","key":"6_CR30","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1109\/TPAMI.2017.2670560","volume":"40","author":"YG Jiang","year":"2017","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 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"6_CR32","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"6_CR33","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 International Conference on Computer Vision, pp. 6232\u20136242 (2019)","DOI":"10.1109\/ICCV.2019.00633"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"6_CR35","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient ConvNets. arXiv preprint arXiv:1608.08710 (2016)"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"6_CR38","unstructured":"McGill, M., Perona, P.: Deciding how to decide: dynamic routing in artificial neural networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2363\u20132372 (2017)"},{"issue":"2","key":"6_CR39","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2019.2901464","volume":"42","author":"M Monfort","year":"2019","unstructured":"Monfort, M., et al.: Moments in time dataset: one million videos for event understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 502\u2013508 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR40","unstructured":"Monfort, M., et al.: Multi-moments in time: Learning and interpreting models for multi-action video understanding. arXiv preprint arXiv:1911.00232 (2019)"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Najibi, M., Singh, B., Davis, L.S.: AutoFocus: efficient multi-scale inference. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9745\u20139755 (2019)","DOI":"10.1109\/ICCV.2019.00984"},{"issue":"5","key":"6_CR42","doi-asserted-by":"publisher","first-page":"1844","DOI":"10.1016\/j.patcog.2014.11.006","volume":"48","author":"M Pedersoli","year":"2015","unstructured":"Pedersoli, M., Vedaldi, A., Gonzalez, J., Roca, X.: A coarse-to-fine approach for fast deformable object detection. Pattern Recogn. 48(5), 1844\u20131853 (2015)","journal-title":"Pattern Recogn."},{"issue":"7","key":"6_CR43","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1109\/34.56205","volume":"12","author":"P Perona","year":"1990","unstructured":"Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12(7), 629\u2013639 (1990)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR44","unstructured":"Piergiovanni, A., Angelova, A., Ryoo, M.S.: Tiny video networks. arXiv preprint arXiv:1910.06961 (2019)"},{"key":"6_CR45","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":"6_CR46","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"6_CR47","unstructured":"Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: International Conference on Machine Learning, pp. 1139\u20131147 (2013)"},{"key":"6_CR48","unstructured":"Tan, M., Le, Q.V.: EfficientNet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019)"},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"6_CR50","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5552\u20135561 (2019)","DOI":"10.1109\/ICCV.2019.00565"},{"key":"6_CR51","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: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"6_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01246-5_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Veit","year":"2018","unstructured":"Veit, A., Belongie, S.: Convolutional networks with adaptive inference graphs. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 3\u201318. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_1"},{"key":"6_CR53","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: CVPR 2011, pp. 3169\u20133176. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"6_CR54","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":"6_CR55","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"6_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/978-3-030-01261-8_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Wang","year":"2018","unstructured":"Wang, X., Yu, F., Dou, Z.-Y., Darrell, T., Gonzalez, J.E.: SkipNet: learning dynamic routing in convolutional networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 420\u2013436. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_25"},{"key":"6_CR57","doi-asserted-by":"crossref","unstructured":"Wen, W., Xu, C., Wu, C., Wang, Y., Chen, Y., Li, H.: Coordinating filters for faster deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 658\u2013666 (2017)","DOI":"10.1109\/ICCV.2017.78"},{"issue":"3\u20134","key":"6_CR58","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"6_CR59","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 International Conference on Computer Vision, pp. 6222\u20136231 (2019)","DOI":"10.1109\/ICCV.2019.00632"},{"key":"6_CR60","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: BlockDrop: dynamic inference paths in residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8817\u20138826 (2018)","DOI":"10.1109\/CVPR.2018.00919"},{"key":"6_CR61","unstructured":"Wu, Z., Xiong, C., Jiang, Y.G., Davis, L.S.: LiteEval: a coarse-to-fine framework for resource efficient video recognition. In: Advances in Neural Information Processing Systems, pp. 7778\u20137787 (2019)"},{"key":"6_CR62","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 Conference on Computer Vision and Pattern Recognition, pp. 1278\u20131287 (2019)","DOI":"10.1109\/CVPR.2019.00137"},{"key":"6_CR63","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":"6_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"6_CR65","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58571-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:03:33Z","timestamp":1731024213000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58571-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585709","9783030585716"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58571-6_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"9 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}