{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:57:13Z","timestamp":1781161033872,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819200672","type":"print"},{"value":"9789819200689","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-92-0068-9_36","type":"book-chapter","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:08:32Z","timestamp":1781158112000},"page":"528-543","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Dynamic Key Frames Based Temporal Segmentation for Activity Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7943-8621","authenticated-orcid":false,"given":"Vo Hoai","family":"Viet","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1401-471X","authenticated-orcid":false,"given":"Mach Vinh","family":"Phat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6626-7699","authenticated-orcid":false,"given":"Tran Nguyen Dang","family":"Tam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"36_CR1","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. J. 28, 976\u2013990 (2010)","journal-title":"Image Vis. Comput. J."},{"key":"36_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1922649.1922653","volume":"43","author":"JK Aggarwal","year":"2011","unstructured":"Aggarwal, J.K., Ryoo, M.S.: Human activity analysis: a review. ACM Comput. Surv. 43, 1\u201343 (2011)","journal-title":"ACM Comput. Surv."},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos \u201cin the Wild\u201d. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Reddy, K.K., Shah, M.: Recognizing 50 human action categoriesof web videos. Mach. Vis. Appl. (MVAP) (2012)","DOI":"10.1007\/s00138-012-0450-4"},{"key":"36_CR6","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":"36_CR7","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: IEEE\/CVF International Conference on Computer Vision (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Ciptadi, A., Goodwin, M.S., Rehg, J.M.: Movement pattern histogram for action recognition and retrieval. In: European Conference on Computer Vision, pp. 695\u2013710 (2014)","DOI":"10.1007\/978-3-319-10605-2_45"},{"key":"36_CR9","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"36_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"36_CR11","doi-asserted-by":"publisher","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision\u2013ECCV: 16th European Conference, Glasgow, UK, August 23\u201328, Proceedings, Part II 16, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24","DOI":"10.1007\/978-3-030-58536-5_24"},{"issue":"1","key":"36_CR12","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/s11063-018-9932-3","volume":"50","author":"H Hu","year":"2018","unstructured":"Hu, H., Liao, Z., Xiao, X.: Action recognition using multiple pooling strategies of CNN features. Neural Process. Lett. 50(1), 379\u2013396 (2018). https:\/\/doi.org\/10.1007\/s11063-018-9932-3","journal-title":"Neural Process. Lett."},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"issue":"7","key":"36_CR14","doi-asserted-by":"publisher","first-page":"1810","DOI":"10.1016\/j.patcog.2012.10.004","volume":"46","author":"L Liu","year":"2013","unstructured":"Liu, L., Shao, L., Rockett, P.: Boosted key-frame selection and correlated pyramidal motion-feature representation for human action recognition. Pattern Recogn. 46(7), 1810\u20131818 (2013)","journal-title":"Pattern Recogn."},{"key":"36_CR15","doi-asserted-by":"publisher","first-page":"3343","DOI":"10.1016\/j.patcog.2014.04.018","volume":"47","author":"G Guo","year":"2014","unstructured":"Guo, G., Lai, A.: A survey on still image based human action recognition. Pattern Recogn. 47, 3343\u20133361 (2014)","journal-title":"Pattern Recogn."},{"key":"36_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1007\/978-3-319-10599-4_35","volume-title":"Computer Vision \u2013 ECCV 2014","author":"D Potapov","year":"2014","unstructured":"Potapov, D., Douze, M., Harchaoui, Z., Schmid, C.: Category-specific video summarization. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 540\u2013555. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_35"},{"issue":"5","key":"36_CR17","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/S0923-5965(00)00011-4","volume":"16","author":"I Koprinska","year":"2001","unstructured":"Koprinska, I., Carrato, S.: Temporal video segmentation: a survey. Sig. Process. Image Commun. 16(5), 477\u2013500 (2001)","journal-title":"Sig. Process. Image Commun."},{"issue":"4","key":"36_CR18","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.cviu.2009.03.011","volume":"114","author":"AF Smeaton","year":"2010","unstructured":"Smeaton, A.F., Over, P., Doherty, A.R.: Video shot boundary detection: seven years of trecvid activity. Comput. Vis. Image Underst. 114(4), 411\u2013418 (2010)","journal-title":"Comput. Vis. Image Underst."},{"key":"36_CR19","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"36_CR20","unstructured":"Weisstein, E.W.: F-distribution. Wolfram Research, Inc. (2002)"},{"key":"36_CR21","unstructured":"Tan, H., Lei, J., Wolf, T., Bansal, M.: VIMPAC: video pre-training via masked token prediction and contrastive learning. arXiv preprint arXiv:2106.11250 (2021)"},{"key":"36_CR22","unstructured":"Zhao, Z., Huang, B., Xing, S., Wu, G., Qiao, Y., Wang, L.: Asymmetric masked distillation for pre-training small foundation models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18 516\u201318 526 (2024)"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training. In: NeurIPS (2022)","DOI":"10.52202\/068431-0732"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: VideoMAE V2: scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14 549\u201314 560 (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"36_CR25","doi-asserted-by":"crossref","unstructured":"Ranasinghe, K., Naseer, M., Khan, S., Khan, F.S., Ryoo, M.S.: Self-supervised video transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2874\u20132884 (2022)","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"36_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108273","volume":"122","author":"GM Elahi","year":"2022","unstructured":"Elahi, G.M., Yang, Y.H.: Online learnable keyframe extraction in videos and its application with semantic word vector in action recognition. Pattern Recogn. 122, 108273 (2022)","journal-title":"Pattern Recogn."},{"key":"36_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108797","volume":"130","author":"W Dong","year":"2022","unstructured":"Dong, W., Zhang, Z., Song, C., Tan, T.: Identifying the key frames: an attention-aware sampling method for action recognition. Pattern Recogn. 130, 108797 (2022)","journal-title":"Pattern Recogn."},{"key":"36_CR28","doi-asserted-by":"crossref","unstructured":"Ke, X., Chang, B., Wu, H., Xu, F., Zhong, S.: Towards practical and efficient long video summary. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 1770\u20131774 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746911"},{"key":"36_CR29","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, L.: ZeroI2V: zero-cost adaptation of pre-trained transformers from image to video. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV (2024)","DOI":"10.1007\/978-3-031-73010-8_25"},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Afham, M., Shukla, S.N., Poursaeed, O., Zhang, P., Shah, A., Lim, S.: Revisiting kernel temporal segmentation as an adaptive tokenizer for long-form video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1189\u20131194 (2024)","DOI":"10.1109\/ICCVW60793.2023.00128"},{"key":"36_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124183","volume":"252","author":"Z Yang","year":"2024","unstructured":"Yang, Z., An, G., Zheng, Z., Cao, S., Wang, F.: EPK-CLIP: external and priori knowledge CLIP for action recognition. Expert Syst. Appl. 252, 124183 (2024)","journal-title":"Expert Syst. Appl."},{"key":"36_CR32","volume":"255","author":"B Wang","year":"2024","unstructured":"Wang, B., Chang, F., Liu, C., Wang, W., Ma, R.: An efficient motion visual learning method for video action recognition. Expert Syst. Appl. 255, 124183 (2024)","journal-title":"Expert Syst. Appl."},{"key":"36_CR33","doi-asserted-by":"publisher","first-page":"32705","DOI":"10.1007\/s11042-024-20484-5","volume":"84","author":"AK AlShami","year":"2025","unstructured":"AlShami, A.K., Rabinowitz, R., Lam, K., et al.: SMART-vision: survey of modern action recognition techniques in vision. Multimed Tools Appl. 84, 32705\u201332776 (2025)","journal-title":"Multimed Tools Appl."},{"key":"36_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.126255","volume":"268","author":"S Chen","year":"2025","unstructured":"Chen, S., Wang, X., Sun, Y., Yang, K.: STAN: spatio-temporal analysis network for efficient video action recognition. Expert Syst. Appl. 268, 126255 (2025)","journal-title":"Expert Syst. Appl."},{"key":"36_CR35","unstructured":"Support Vector Classification. https:\/\/scikit-learn.org\/stable\/api\/sklearn.svm.html. Accessed 18 Feb 2025"}],"container-title":["Communications in Computer and Information Science","Recent Challenges in Intelligent information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-0068-9_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:08:40Z","timestamp":1781158120000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-0068-9_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819200672","9789819200689"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-0068-9_36","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaohsiung","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 April 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}