{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:24:56Z","timestamp":1757629496181,"version":"3.44.0"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032045454","type":"print"},{"value":"9783032045461","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T00:00:00Z","timestamp":1757548800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T00:00:00Z","timestamp":1757548800000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-04546-1_27","type":"book-chapter","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T14:53:48Z","timestamp":1757516028000},"page":"327-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Long-Term Motion Feature Learning via\u00a0Frequency-Based Key Frame Guidance for\u00a0Action Recognition"],"prefix":"10.1007","author":[{"given":"Yuchen","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Shougang","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Xingjian","family":"Gu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"27_CR1","unstructured":"Chen, Y., Kalantidis, Y., Li, J., Yan, S., Feng, J.: \u00c2 2-nets: double attention networks. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"27_CR2","unstructured":"Erdogan, E., Aksoy, E.E., Sariel, S.: Real-time manipulation action recognition with a factorized graph sequence encoder. arXiv preprint arXiv:2503.12034 (2025)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Fan, L., Huang, W., Gan, C., Ermon, S., Gong, B., Huang, J.: End-to-end learning of motion representation for video understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6016\u20136025 (2018)","DOI":"10.1109\/CVPR.2018.00630"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Goyal, R., et\u00a0al.: The \u201csomething-something\u201d video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 5842\u20135850. IEEE (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: a large video database for human motion recognition. In: 2011 International Conference on Computer Vision, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"27_CR6","first-page":"79399","volume":"36","author":"D Lee","year":"2023","unstructured":"Lee, D., Lee, J., Choi, J.: Cast: cross-attention in space and time for video action recognition. Adv. Neural. Inf. Process. Syst. 36, 79399\u201379425 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Lee, M., Lee, S., Son, S., Park, G., Kwak, N.: Motion feature network: Fixed motion filter for action recognition. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 387\u2013403 (2018)","DOI":"10.1007\/978-3-030-01249-6_24"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., Sridhar, D., Liang, H., Wong, A.: Spot the difference! temporal coarse to fine to finer difference spotting for action recognition in videos. In: 2024 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136. IEEE (2024)","DOI":"10.1109\/ICME57554.2024.10687820"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Liu, X., Yuan, G., Bing, R., Cai, Z., Fu, S., Yu, Y.: When skeleton meets motion: adaptive multimodal graph representation fusion for action recognition. In: 2024 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136. IEEE (2024)","DOI":"10.1109\/ICME57554.2024.10688272"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Teinet: towards an efficient architecture for video recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11669\u201311676 (2020)","DOI":"10.1609\/aaai.v34i07.6836"},{"issue":"3","key":"27_CR11","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1109\/TCSVT.2022.3207518","volume":"33","author":"X Sheng","year":"2022","unstructured":"Sheng, X., Li, K., Shen, Z., Xiao, G.: A progressive difference method for capturing visual tempos on action recognition. IEEE Trans. Circuits Syst. Video Technol. 33(3), 977\u2013987 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"27_CR12","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"27_CR13","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":"27_CR14","doi-asserted-by":"crossref","unstructured":"Stroud, J., Ross, D., Sun, C., Deng, J., Sukthankar, R.: D3d: distilled 3d networks for video action recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 625\u2013634 (2020)","DOI":"10.1109\/WACV45572.2020.9093274"},{"key":"27_CR15","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":"27_CR16","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vision 103, 60\u201379 (2013)","journal-title":"Int. J. Comput. Vision"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: Tdn: temporal difference networks for efficient action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1895\u20131904 (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"27_CR18","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"},{"issue":"3","key":"27_CR19","first-page":"3347","volume":"45","author":"M Wang","year":"2022","unstructured":"Wang, M., Xing, J., Su, J., Chen, J., Liu, Y.: Learning spatiotemporal and motion features in a unified 2d network for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3347\u20133362 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"27_CR20","doi-asserted-by":"publisher","first-page":"368","DOI":"10.3390\/e24030368","volume":"24","author":"Q Yang","year":"2022","unstructured":"Yang, Q., Lu, T., Zhou, H.: A spatio-temporal motion network for action recognition based on spatial attention. Entropy 24(3), 368 (2022)","journal-title":"Entropy"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Zheng, Q., Zheng, P., Luo, W., Lu, W.: A fast and tunable privacy-preserving action recognition framework over compressed video. In: 2024 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136. IEEE (2024)","DOI":"10.1109\/ICME57554.2024.10687883"},{"key":"27_CR22","unstructured":"Zhu, Y., et al.: A comprehensive study of deep video action recognition. arXiv preprint arXiv:2012.06567 (2020)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04546-1_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T14:53:54Z","timestamp":1757516034000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04546-1_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,11]]},"ISBN":["9783032045454","9783032045461"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04546-1_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,11]]},"assertion":[{"value":"11 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}