{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T17:27:48Z","timestamp":1764350868460},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T00:00:00Z","timestamp":1694822400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T00:00:00Z","timestamp":1694822400000},"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":["SIViP"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s11760-023-02766-x","type":"journal-article","created":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T05:02:00Z","timestamp":1694840520000},"page":"399-406","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Leveraging cross-resolution attention for effective extreme low-resolution video action recognition"],"prefix":"10.1007","volume":"18","author":[{"given":"Oguzhan","family":"Oguz","sequence":"first","affiliation":[]},{"given":"Nazli","family":"Ikizler-Cinbis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,16]]},"reference":[{"key":"2766_CR1","doi-asserted-by":"crossref","unstructured":"Bai, Y., Zou, Q., Chen, X., et al.: Extreme low-resolution action recognition with confident spatial-temporal attention transfer. Int. J. Comput. Vis. 1\u201316 (2023)","DOI":"10.1007\/s11263-023-01771-4"},{"key":"2766_CR2","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":"2766_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Wu, J., Konrad, J., et al.: Semi-coupled two-stream fusion convnets for action recognition at extremely low resolutions. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, pp. 139\u2013147 (2017)","DOI":"10.1109\/WACV.2017.23"},{"key":"2766_CR4","doi-asserted-by":"crossref","unstructured":"Crasto, N., Weinzaepfel, P., Alahari, K., Schmid, C.: Mars: motion-augmented RGB stream for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7882\u20137891 (2019)","DOI":"10.1109\/CVPR.2019.00807"},{"key":"2766_CR5","doi-asserted-by":"crossref","unstructured":"Dai, R., Das, S., Br\u00e9mond, F.: Learning an augmented RGB representation with cross-modal knowledge distillation for action detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13053\u201313064 (2021)","DOI":"10.1109\/ICCV48922.2021.01281"},{"key":"2766_CR6","doi-asserted-by":"crossref","unstructured":"Dave, I.R., Chen, C., Shah, M.: Spact: Self-supervised privacy preservation for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20164\u201320173 (2022)","DOI":"10.1109\/CVPR52688.2022.01953"},{"key":"2766_CR7","doi-asserted-by":"crossref","unstructured":"Demir, U., Rawat, Y.S., Shah, M.: Tinyvirat: low-resolution video action recognition. In: 2020 25th International Conference on Pattern Recognition (ICPR), IEEE, pp. 7387\u20137394 (2021)","DOI":"10.1109\/ICPR48806.2021.9412541"},{"key":"2766_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., et al.: 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":"2766_CR9","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531 (2015)"},{"issue":"6","key":"2766_CR10","doi-asserted-by":"publisher","first-page":"670","DOI":"10.3390\/mi12060670","volume":"12","author":"M Hou","year":"2021","unstructured":"Hou, M., Liu, S., Zhou, J., et al.: Extreme low-resolution activity recognition using a super-resolution-oriented generative adversarial network. Micromachines 12(6), 670 (2021)","journal-title":"Micromachines"},{"key":"2766_CR11","doi-asserted-by":"publisher","unstructured":"Huang, Z., Wang, X., Wei, Y., et al.: Ccnet: Criss-cross attention for semantic segmentation. In: IEEE Transactions on Pattern Analysis and Machine Intelligence p. 1 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2020.3007032","DOI":"10.1109\/TPAMI.2020.3007032"},{"key":"2766_CR12","doi-asserted-by":"crossref","unstructured":"Kim, H., Jain, M., Lee, J.T., et al.: 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":"2766_CR13","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., et al.: Hmdb: a large video database for human motion recognition. In: 2011 International conference on computer vision, IEEE, pp. 2556\u20132563 (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"2766_CR14","doi-asserted-by":"crossref","unstructured":"Liu, T., Lam, K.-M., Kong, J.: Distilling privileged knowledge for anomalous event detection from weakly labeled videos. In: IEEE Transactions on Neural Networks and Learning Systems, IEEE (2023)","DOI":"10.1109\/TNNLS.2023.3263966"},{"key":"2766_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., et al.: Video swin transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2766_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., et al.: Tam: Temporal adaptive module for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13708\u201313718 (2021)","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"2766_CR17","first-page":"37865","volume":"35","author":"C Ma","year":"2022","unstructured":"Ma, C., Guo, Q., Jiang, Y., et al.: Rethinking resolution in the context of efficient video recognition. Adv. Neural Inf. Process. Syst. 35, 37865\u201337877 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2766_CR18","doi-asserted-by":"crossref","unstructured":"Purwanto, D., Renanda Adhi Pramono, R., Chen, Y.T., et al.: Extreme low resolution action recognition with spatial-temporal multi-head self-attention and knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, (2019)","DOI":"10.1109\/ICCVW.2019.00125"},{"issue":"8","key":"2766_CR19","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., et al.: Three-stream network with bidirectional self-attention for action recognition in extreme low resolution videos. IEEE Signal Process. Lett. 26(8), 1187\u20131191 (2019)","journal-title":"IEEE Signal Process. Lett."},{"key":"2766_CR20","doi-asserted-by":"publisher","first-page":"12019","DOI":"10.1109\/ACCESS.2021.3050514","volume":"9","author":"P Russo","year":"2021","unstructured":"Russo, P., Ticca, S., Alati, E., et al.: Learning to see through a few pixels: Multi streams network for extreme low-resolution action recognition. IEEE Access 9, 12019\u201312026 (2021)","journal-title":"IEEE Access"},{"key":"2766_CR21","doi-asserted-by":"crossref","unstructured":"Ryoo, M., Kim, K., Yang, H.: Extreme low resolution activity recognition with multi-siamese embedding learning. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12299"},{"key":"2766_CR22","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Rothrock, B., Fleming, C., et al.: Privacy-preserving human activity recognition from extreme low resolution. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11233"},{"key":"2766_CR23","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., et al.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"2766_CR24","doi-asserted-by":"crossref","unstructured":"Shaikh, A.H., Meshram, B.: Security issues in cloud computing. In: Intelligent Computing and Networking. Springer, pp. 63\u201377 (2021)","DOI":"10.1007\/978-981-15-7421-4_6"},{"key":"2766_CR25","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":"2766_CR26","doi-asserted-by":"crossref","unstructured":"Xu, M., Sharghi, A., Chen, X., et al.: Fully-coupled two-stream spatiotemporal networks for extremely low resolution action recognition. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, pp. 1607\u20131615 (2018)","DOI":"10.1109\/WACV.2018.00178"},{"key":"2766_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, K., Gool, L.V., Timofte, R.: Deep unfolding network for image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3217\u20133226 (2020)","DOI":"10.1109\/CVPR42600.2020.00328"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-023-02766-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-023-02766-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-023-02766-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T15:41:09Z","timestamp":1706197269000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-023-02766-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,16]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["2766"],"URL":"https:\/\/doi.org\/10.1007\/s11760-023-02766-x","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,16]]},"assertion":[{"value":"28 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This declaration is not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}