{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T16:42:59Z","timestamp":1774370579988,"version":"3.50.1"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T00:00:00Z","timestamp":1678233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T00:00:00Z","timestamp":1678233600000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s11263-023-01771-4","type":"journal-article","created":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T01:02:20Z","timestamp":1678237340000},"page":"1550-1565","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Extreme Low-Resolution Action Recognition with Confident Spatial-Temporal Attention Transfer"],"prefix":"10.1007","volume":"131","author":[{"given":"Yucai","family":"Bai","sequence":"first","affiliation":[]},{"given":"Qin","family":"Zou","sequence":"additional","affiliation":[]},{"given":"Xieyuanli","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Lingxi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zhengming","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,8]]},"reference":[{"key":"1771_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, S., Hu, S. X., Damianou, A., Lawrence, N. D., & Dai, Z. (2019). Variational information distillation for knowledge transfer. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9163\u20139171).","DOI":"10.1109\/CVPR.2019.00938"},{"key":"1771_CR2","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., & Schmid, C. (2021). Vivit: A video vision transformer. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 6836\u20136846).","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"1771_CR3","unstructured":"Baranyi, P. (2021). Rank#2 solutions of TinyAction challenge of CVPR workshop. https:\/\/www.crcv.ucf.edu\/tiny-actions-challenge-cvpr2021\/submissions\/ALONG.pdf."},{"key":"1771_CR4","unstructured":"Bertasius, G., Wang, H., & Torresani, L. (2021, July). Is space-time attention all you need for video understanding? In Proceedings of the 38th International Conference on Machine Learning(ICML), Vol. 2, No. 3, p. 4."},{"key":"1771_CR5","doi-asserted-by":"crossref","unstructured":"Beyer, L., Zhai, X., Royer, A., Markeeva, L., Anil, R., & Kolesnikov, A. (2022). Knowledge distillation: A good teacher is patient and consistent. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10925\u201310934).","DOI":"10.1109\/CVPR52688.2022.01065"},{"key":"1771_CR6","doi-asserted-by":"crossref","unstructured":"Biswas, S., Bowyer, K. W., & Flynn, P. J. (2010). Multidimensional scaling for matching low-resolution facial images. In Proceedings of the IEEE international conference on biometrics: Theory, applications and systems (BTAS) (pp. 1\u20136).","DOI":"10.1109\/BTAS.2010.5634479"},{"key":"1771_CR7","doi-asserted-by":"crossref","unstructured":"Boyle, M., Edwards, C., & Greenberg, S. (2000). The effects of filtered video on awareness and privacy. In Proceedings of the ACM conference on computer supported cooperative work (pp. 1\u201310).","DOI":"10.1145\/358916.358935"},{"key":"1771_CR8","doi-asserted-by":"crossref","unstructured":"Cao, S., Zou, Q., Mao, X., & Wang, Z. (2021). Metric learning for anti-compression facial forgery detection. In Proceedings of the ACM conference on multimedia (pp. 1\u20139).","DOI":"10.1145\/3474085.3475347"},{"key":"1771_CR9","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017). Quo vadis, action recognition? a new model and the kinetics dataset. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 6299\u20136308).","DOI":"10.1109\/CVPR.2017.502"},{"key":"1771_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., Kalantidis, Y., Li, J., Yan, S., & Feng, J. (2018). Multi-fiber networks for video recognition. In Proceedings of the European conference on computer vision (ECCV) (pp. 364\u2013380).","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"1771_CR11","doi-asserted-by":"crossref","unstructured":"Chen, J., Wu, J., Konrad, J., & Ishwar, P. (2017). Semi-coupled two-stream fusion convnets for action recognition at extremely low resolutions. In Proceedings of the IEEE winter conference on applications of computer vision (WACV) (pp. 139\u2013147).","DOI":"10.1109\/WACV.2017.23"},{"key":"1771_CR12","doi-asserted-by":"publisher","first-page":"7028","DOI":"10.1609\/aaai.v35i8.16865","volume":"35","author":"D Chen","year":"2021","unstructured":"Chen, D., Mei, J.-P., Zhang, Y., Wang, C., Wang, Z., Feng, Y., & Chen, C. (2021). Cross-layer distillation with semantic calibration. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 7028\u20137036.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"6","key":"1771_CR13","doi-asserted-by":"publisher","first-page":"2568","DOI":"10.1109\/TMECH.2018.2821767","volume":"23","author":"L Chen","year":"2018","unstructured":"Chen, L., Shan, Y., Tian, W., Li, B., & Cao, D. (2018). A fast and efficient double-tree rrt-like sampling-based planner applying on mobile robotic systems. IEEE\/ASME Transactions on Mechatronics, 23(6), 2568\u20132578.","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"key":"1771_CR14","doi-asserted-by":"crossref","unstructured":"Demir, U., Rawat, Y. S., & Shah, M. (2021). Tinyvirat: Low-resolution video action recognition. In 2020 25th international conference on pattern recognition (ICPR) (pp. 7387\u20137394). IEEE.","DOI":"10.1109\/ICPR48806.2021.9412541"},{"key":"1771_CR15","doi-asserted-by":"crossref","unstructured":"Dollar, P., Rabaud, V., Cottrell, G., & Belongie, S. (2005). Behavior recognition via sparse spatio-temporal features. In Proceedings of the IEEE international workshop on visual surveillance and performance evaluation of tracking and surveillance (pp. 65\u201372).","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"1771_CR16","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne\u00a0Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., & Darrell, T. (2015). Long-term recurrent convolutional networks for visual recognition and description. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2625\u20132634).","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"1771_CR17","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., & Uszkoreit, J. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. In International conference on learning representations."},{"key":"1771_CR18","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J. & Feichtenhofer, C. (2021). Multiscale vision transformers. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 6824\u20136835).","DOI":"10.1109\/ICCV48922.2021.00675"},{"issue":"1","key":"1771_CR19","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.jvcir.2011.06.004","volume":"23","author":"C Fookes","year":"2012","unstructured":"Fookes, C., Lin, F., Chandran, V., & Sridharan, S. (2012). Evaluation of image resolution and super-resolution on face recognition performance. Journal of Visual Communication and Image Representation, 23(1), 75\u201393.","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"1771_CR20","doi-asserted-by":"crossref","unstructured":"Gao, C., Xu, J., Zou, Y., & Huang, J.-B. (2020). Drg: Dual relation graph for human-object interaction detection. In Proceedings of the European conference on computer vision (ECCV) (pp. 696\u2013712).","DOI":"10.1007\/978-3-030-58610-2_41"},{"issue":"5","key":"1771_CR21","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1109\/TIP.2003.811513","volume":"12","author":"BK Gunturk","year":"2003","unstructured":"Gunturk, B. K., Batur, A. U., Altunbasak, Y., Hayes, M. H., & Mersereau, R. M. (2003). Eigenface-domain super-resolution for face recognition. IEEE Transactions on Image Processing, 12(5), 597\u2013606.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1771_CR22","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., & Satoh, Y. (2018). Can spatiotemporal 3d cnns retrace the history of 2d CNNs and imagenet. In Proceedings of the conference on computer vision and pattern recognition (CVPR) (pp. 6546\u20136555).","DOI":"10.1109\/CVPR.2018.00685"},{"key":"1771_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1771_CR24","unstructured":"He, J., Zhang, Z., Xu, Z., & Luo, Z. (2022). Rank#1 solutions of tinyaction challenge of cvpr workshop."},{"key":"1771_CR25","unstructured":"Hinton, G. E., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531."},{"key":"1771_CR26","unstructured":"Huang, Z., & Wang, N. (2017). Like what you like: Knowledge distill via neuron selectivity transfer. arXiv preprint arXiv:1707.01219."},{"key":"1771_CR27","doi-asserted-by":"publisher","first-page":"7945","DOI":"10.1609\/aaai.v35i9.16969","volume":"35","author":"M Ji","year":"2021","unstructured":"Ji, M., Heo, B., & Park, S. (2021). Show, attend and distill: Knowledge distillation via attention-based feature matching. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 7945\u20137952.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"5","key":"1771_CR28","doi-asserted-by":"publisher","first-page":"2173","DOI":"10.1109\/TIP.2018.2883522","volume":"28","author":"L Jin","year":"2019","unstructured":"Jin, L., Shu, X., Li, K., Li, Z., Qi, G.-J., & Tang, J. (2019). Deep ordinal hashing with spatial attention. IEEE Transactions on Image Processing, 28(5), 2173\u20132186.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1771_CR29","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., & Natsev, P. & Suleyman, M. (2017). The kinetics human action video dataset. arXiv preprint arXiv:1705.06950."},{"key":"1771_CR30","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011). Hmdb: A large video database for human motion recognition. In Proceedings of the international conference on computer vision (ICCV) (pp. 2556\u20132563).","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"1771_CR31","doi-asserted-by":"crossref","unstructured":"Laptev, L. (2003). Space-time interest points. In: Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 432\u2013439).","DOI":"10.1109\/ICCV.2003.1238378"},{"key":"1771_CR32","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., & Wang, L. (2020). Tea: Temporal excitation and aggregation for action recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 909\u2013918).","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"1771_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, H., Chen, Z., Wang, Z., & Ouyang, W. (2020). Disentangling and unifying graph convolutions for skeleton-based action recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 143\u2013152).","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"1771_CR34","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., & Asselmann, D. (2021). Video transformer network. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 3163\u20133172).","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"1771_CR35","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., & Cho, M. (2019). Relational knowledge distillation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 3967\u20133976).","DOI":"10.1109\/CVPR.2019.00409"},{"key":"1771_CR36","first-page":"13292","volume":"34","author":"DY Park","year":"2021","unstructured":"Park, D. Y., Cha, M.-H., Kim, D., Han, B., et al. (2021). Learning student-friendly teacher networks for knowledge distillation. Advances in Neural Information Processing Systems, 34, 13292\u201313303.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1771_CR37","doi-asserted-by":"crossref","unstructured":"Purwanto, D., Renanda Adhi\u00a0Pramono, R., Chen, Y.-T., & Fang, W.-H. (2019). Extreme low resolution action recognition with spatial-temporal multi-head self-attention and knowledge distillation. In Proceedings of the IEEE international conference on computer vision workshops (ICCVW).","DOI":"10.1109\/ICCVW.2019.00125"},{"issue":"8","key":"1771_CR38","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1109\/LSP.2019.2923918","volume":"26","author":"D Purwanto","year":"2019","unstructured":"Purwanto, D., Pramono, R. R. A., Chen, Y.-T., & Fang, W.-H. (2019). Three-stream network with bidirectional self-attention for action recognition in extreme low resolution videos. IEEE Signal Processing Letters, 26(8), 1187\u20131191.","journal-title":"IEEE Signal Processing Letters"},{"key":"1771_CR39","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., & Mei, T. (2017). Learning spatio-temporal representation with pseudo-3d residual networks. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 5533\u20135541).","DOI":"10.1109\/ICCV.2017.590"},{"key":"1771_CR40","doi-asserted-by":"crossref","unstructured":"Raval, N., Srivastava, A., Lebeck, K., Cox, L., & Machanavajjhala, A. (2014). Markit: Privacy markers for protecting visual secrets. In Proceedings of the ACM international joint conference on pervasive and ubiquitous computing: adjunct publication (pp. 1289\u20131295).","DOI":"10.1145\/2638728.2641707"},{"issue":"8","key":"1771_CR41","doi-asserted-by":"publisher","first-page":"3770","DOI":"10.1109\/TIP.2012.2192285","volume":"21","author":"C Ren","year":"2012","unstructured":"Ren, C., Dai, D., & Yan, H. (2012). Coupled kernel embedding for low-resolution face image recognition. IEEE Transactions on Image Processing, 21(8), 3770\u20133783.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1771_CR42","doi-asserted-by":"crossref","unstructured":"Russo, P., Ticca, S., Alati, E., & Pirri, F. (2021). Learning to See Through a Few Pixels: Multi Streams Network for Extreme Low-Resolution Action Recognition. IEEE Access, 9, 12019\u201312026","DOI":"10.1109\/ACCESS.2021.3050514"},{"key":"1771_CR43","doi-asserted-by":"crossref","unstructured":"Ryoo, M. S., Kim, K., & Yang, H. J. (2017). Extreme low resolution activity recognition with multi-siamese embedding learning. In Proceedings of the AAAI conference on artificial intelligence (pp. 7315\u20137322).","DOI":"10.1609\/aaai.v32i1.12299"},{"key":"1771_CR44","doi-asserted-by":"crossref","unstructured":"Ryoo, M. S., Rothrock, B., & Matthies, L. (2015). Pooled motion features for first-person videos. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 896\u2013904).","DOI":"10.1109\/CVPR.2015.7298691"},{"key":"1771_CR45","doi-asserted-by":"crossref","unstructured":"Ryoo, M. S., Rothrock, B., Fleming, C., & Yang, H. J. (2017). Privacy-preserving human activity recognition from extreme low resolution. In Proceedings of the AAAI conference on artificial intelligence (pp. 4255\u20134262).","DOI":"10.1609\/aaai.v31i1.11233"},{"key":"1771_CR46","doi-asserted-by":"crossref","unstructured":"Sadanand, S., & Corso, J. J. (2012). Action bank: A high-level representation of activity in video. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1234\u20131241).","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"1771_CR47","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., & Lin, D. (2020). Intra- and inter-action understanding via temporal action parsing. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 730\u2013739).","DOI":"10.1109\/CVPR42600.2020.00081"},{"key":"1771_CR48","doi-asserted-by":"crossref","unstructured":"Shekhar, S., Patel, V. M., & Chellappa, R. (2011). Synthesis-based recognition of low resolution faces. In Proceedings of the international joint conference on biometrics (IJCB) (pp. 1\u20136).","DOI":"10.1109\/IJCB.2011.6117545"},{"key":"1771_CR49","unstructured":"Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. In Proceedings of the advances in neural information processing systems (NIPS) (pp. 568\u2013576)."},{"key":"1771_CR50","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In Proceedings of the international conference on learning representations (ICLR)."},{"key":"1771_CR51","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402."},{"key":"1771_CR52","first-page":"6906","volume":"34","author":"S Stanton","year":"2021","unstructured":"Stanton, S., Izmailov, P., Kirichenko, P., Alemi, A. A., & Wilson, A. G. (2021). Does knowledge distillation really work? Advances in Neural Information Processing Systems, 34, 6906\u20136919.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1771_CR53","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2818\u20132826).","DOI":"10.1109\/CVPR.2016.308"},{"key":"1771_CR54","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3d convolutional networks. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 4489\u20134497).","DOI":"10.1109\/ICCV.2015.510"},{"key":"1771_CR55","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2018). A closer look at spatiotemporal convolutions for action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 6450\u20136459).","DOI":"10.1109\/CVPR.2018.00675"},{"key":"1771_CR56","doi-asserted-by":"crossref","unstructured":"Veeriah, V., Zhuang, N., & Qi, G.-J. (2015). Differential recurrent neural networks for action recognition. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 4041\u20134049).","DOI":"10.1109\/ICCV.2015.460"},{"key":"1771_CR57","doi-asserted-by":"crossref","unstructured":"Wang, H., & Schmid, C. (2013). Action recognition with improved trajectories. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 3551\u20133558).","DOI":"10.1109\/ICCV.2013.441"},{"key":"1771_CR58","doi-asserted-by":"crossref","unstructured":"Wang, X., & Tang, X. (2003). Face hallucination and recognition. In Proceedings of the international conference on audio- and video-based biometric person authentication (pp. 486\u2013494).","DOI":"10.1007\/3-540-44887-X_58"},{"key":"1771_CR59","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chang, S., Yang, Y., Liu, D., & Huang, T. S. (2016). Studying very low resolution recognition using deep networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4792\u20134800).","DOI":"10.1109\/CVPR.2016.518"},{"key":"1771_CR60","unstructured":"Wang, T., Geng, T., Wang, J., & Zheng, F. (2022). Rank#3 solutions of tinyaction challenge of CVPR workshop."},{"key":"1771_CR61","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Van\u00a0Gool, L. (2016). Temporal segment networks: Towards good practices for deep action recognition. In Proceedings of the European conference on computer vision (ECCV) (pp. 20\u201336).","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"1771_CR62","doi-asserted-by":"crossref","unstructured":"Weinland, D., \u00d6zuysal, M., & Fua, P. (2010). Making action recognition robust to occlusions and viewpoint changes. In Proceedings of the European conference on computer vision (ECCV) (pp. 635\u2013648).","DOI":"10.1007\/978-3-642-15558-1_46"},{"key":"1771_CR63","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., & Murphy, K. (2017). Rethinking spatiotemporal feature learning for video understanding. arXiv preprint arXiv:1712.04851."},{"key":"1771_CR64","unstructured":"Xu, G., Liu, Z., & Loy, C. C. (2020). Computation-efficient knowledge distillation via uncertainty-aware mixup. arXiv preprint arXiv:2012.09413."},{"key":"1771_CR65","doi-asserted-by":"crossref","unstructured":"Xu, M., Sharghi, A., Chen, X., & Crandall, D. J. (2018). Fully-coupled two-stream spatiotemporal networks for extremely low resolution action recognition. In Proceedings of the IEEE winter conference on applications of computer vision (WACV) (pp. 1607\u20131615).","DOI":"10.1109\/WACV.2018.00178"},{"key":"1771_CR66","doi-asserted-by":"crossref","unstructured":"Yang, C., Xu, Y., Shi, J., Dai, B., & Zhou, B. (2020). Temporal pyramid network for action recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 591\u2013600).","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"1771_CR67","unstructured":"Yi, P., Wang, Z., Jiang, K., Jiang, J., Lu, T., & Ma, J. (2020). A progressive fusion generative adversarial network for realistic and consistent video super-resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(5), 2264\u20132280."},{"key":"1771_CR68","unstructured":"Zagoruyko, S., & Komodakis, N. (2016). Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. In Proceedings of the international conference on learning representations (ICLR)."},{"issue":"1","key":"1771_CR69","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1109\/TIP.2011.2162423","volume":"21","author":"WWW Zou","year":"2012","unstructured":"Zou, W. W. W., & Yuen, P. C. (2012). Very low resolution face recognition problem. IEEE Transactions on Image Processing, 21(1), 327\u2013340.","journal-title":"IEEE Transactions on Image Processing"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01771-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01771-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01771-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T05:15:26Z","timestamp":1681794926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01771-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,8]]},"references-count":69,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["1771"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01771-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,8]]},"assertion":[{"value":"7 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 March 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}