{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T13:10:10Z","timestamp":1746364210725,"version":"3.40.4"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781889"},{"type":"electronic","value":"9783031781896"}],"license":[{"start":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T00:00:00Z","timestamp":1733875200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T00:00:00Z","timestamp":1733875200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78189-6_1","type":"book-chapter","created":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T08:09:41Z","timestamp":1733818181000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mask and\u00a0Compress: Efficient Skeleton-Based Action Recognition in\u00a0Continual Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1989-5779","authenticated-orcid":false,"given":"Matteo","family":"Mosconi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3250-4249","authenticated-orcid":false,"given":"Andriy","family":"Sorokin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1940-7703","authenticated-orcid":false,"given":"Aniello","family":"Panariello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9022-8484","authenticated-orcid":false,"given":"Angelo","family":"Porrello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6751-3407","authenticated-orcid":false,"given":"Jacopo","family":"Bonato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7950-7370","authenticated-orcid":false,"given":"Marco","family":"Cotogni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0865-5891","authenticated-orcid":false,"given":"Luigi","family":"Sabetta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9056-1538","authenticated-orcid":false,"given":"Simone","family":"Calderara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2239-283X","authenticated-orcid":false,"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,11]]},"reference":[{"key":"1_CR1","unstructured":"Arani, E., Sarfraz, F., Zonooz, B.: Learning fast, learning slow: A general continual learning method based on complementary learning system. In: International Conference on Learning Representations (2022)"},{"key":"1_CR2","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEit: BERT pre-training of image transformers. In: International Conference on Learning Representations (2022)"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Bonato, J., Pelosin, F., Sabetta, L., Nicolosi, A.: Mind: Multi-task incremental network distillation. In: Proceedings of the AAAI Conference on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v38i10.28987"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Boschini, M., Bonicelli, L., Buzzega, P., Porrello, A., Calderara, S.: Class-incremental continual learning into the extended der-verse. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)","DOI":"10.1109\/TPAMI.2022.3206549"},{"key":"1_CR5","unstructured":"Buzzega, P., Boschini, M., Porrello, A., Abati, D., Calderara, S.: Dark experience for general continual learning: a strong, simple baseline. Advances in Neural Information Processing Systems (2020)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Castagnolo, G., Spampinato, C., Rundo, F., Giordano, D., Palazzo, S.: A baseline on continual learning methods for video action recognition. arXiv preprint arXiv:2304.10335 (2023)","DOI":"10.1109\/ICIP49359.2023.10222140"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., Hu, W.: Channel-wise topology refinement graph convolution for skeleton-based action recognition. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"1_CR8","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: NIPS Workshop on Deep Learning (2014)"},{"key":"1_CR9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Du, Y., Fu, Y., Wang, L.: Skeleton based action recognition with convolutional neural network. In: Proceedings of the Asian Conference on Computer Vision (2015)","DOI":"10.1109\/ACPR.2015.7486569"},{"key":"1_CR11","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2015)"},{"key":"1_CR12","unstructured":"Duan, H., Wang, J., Chen, K., Lin, D.: Dg-stgcn: dynamic spatial-temporal modeling for skeleton-based action recognition. arXiv preprint arXiv:2210.05895 (2022)"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Duan, H., Wang, J., Chen, K., Lin, D.: Pyskl: Towards good practices for skeleton action recognition. In: ACM International Conference on Multimedia (2022)","DOI":"10.1145\/3503161.3548546"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., Dai, B.: Revisiting skeleton-based action recognition. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"1_CR15","unstructured":"Fan, H., Yu, X., Ding, Y., Yang, Y., Kankanhalli, M.: Pstnet: Point spatio-temporal convolution on point cloud sequences. In: International Conference on Learning Representations (2021)"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez-Aparicio, M.T., Garc\u00eda, R., Brugos, J., Pa\u00f1eda, X.G., Melendi, D., Cabrero, S.: Measuring temporal redundancy in sequences of video requests in a news-on-demand service. Telematics and Informatics (2014)","DOI":"10.1016\/j.tele.2013.10.006"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural computation (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"1_CR19","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (2015)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: A new representation of skeleton sequences for 3d action recognition. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.486"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Kim, T.S., Reiter, A.: Interpretable 3d human action analysis with temporal convolutional networks. IEEE International Conference on Computer Vision and Pattern Recognition Workshops (2017)","DOI":"10.1109\/CVPRW.2017.207"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A.A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et\u00a0al.: Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences (2017)","DOI":"10.1073\/pnas.1611835114"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Kong, Y., Fu, Y.: Human action recognition and prediction: A survey. International Journal of Computer Vision (2022)","DOI":"10.1007\/s11263-022-01594-9"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Kwapisz, J.R., Weiss, G.M., Moore, S.A.: Activity recognition using cell phone accelerometers. ACM SigKDD Explorations Newsletter (2011)","DOI":"10.1145\/1964897.1964918"},{"key":"1_CR25","unstructured":"Li, C., Zhong, Q., Xie, D., Pu, S.: Skeleton-based action recognition with convolutional neural networks. In: IEEE International Conference on Multimedia and Expo Workshops (2017)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Li, T., Ke, Q., Rahmani, H., Ho, R.E., Ding, H., Liu, J.: Else-net: Elastic semantic network for continual action recognition from skeleton data. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01318"},{"key":"1_CR27","unstructured":"Lin, W., Sun, M.T., Poovandran, R., Zhang, Z.: Human activity recognition for video surveillance. In: IEEE international symposium on circuits and systems (ISCAS) (2008)"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: Ntu rgb+ d 120: A large-scale benchmark for 3d human activity understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence (2019)","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Panariello, A., Porrello, A., Calderara, S., Cucchiara, R.: Consistency based self-supervised learning for temporal anomaly localization. In: European Conference on Computer Vision Workshops (2022)","DOI":"10.1007\/978-3-031-25072-9_22"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Park, J., Kang, M., Han, B.: Class-incremental learning for action recognition in videos. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01344"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Qiu, H., Hou, B., Ren, B., Zhang, X.: Spatio-temporal tuples transformer for skeleton-based action recognition. arXiv preprint arXiv:2201.02849 (2022)","DOI":"10.1016\/j.neucom.2022.10.084"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: icarl: Incremental classifier and representation learning. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.587"},{"key":"1_CR33","unstructured":"Riemer, M., Cases, I., Ajemian, R., Liu, M., Rish, I., Tu, Y., , Tesauro, G.: Learning to learn without forgetting by maximizing transfer and minimizing interference. In: International Conference on Learning Representations (2019)"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Robins, A.: Catastrophic forgetting, rehearsal and pseudorehearsal. Connection Science (1995)","DOI":"10.1080\/09540099550039318"},{"key":"1_CR35","unstructured":"Rusu, A.A., Rabinowitz, N.C., Desjardins, G., Soyer, H., Kirkpatrick, J., Kavukcuoglu, K., Pascanu, R., Hadsell, R.: Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)"},{"key":"1_CR36","unstructured":"Sanchez-Caballero, A., Fuentes-Jimenez, D., Losada-Guti\u00e9rrez, C.: Exploiting the convlstm: Human action recognition using raw depth video-based recurrent neural networks. arXiv preprint arXiv:2006.07744 (2020)"},{"key":"1_CR37","unstructured":"Schwarz, J., Czarnecki, W., Luketina, J., Grabska-Barwinska, A., Teh, Y.W., Pascanu, R., Hadsell, R.: Progress & compress: A scalable framework for continual learning. In: International Conference on Machine Learning (2018)"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T., Wang, G.: Ntu rgb+d: A large scale dataset for 3d human activity analysis. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: Finegym: A hierarchical video dataset for fine-grained action understanding. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Decoupled spatial-temporal attention network for skeleton-based action-gesture recognition. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69541-5_3"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Smith, J.S., Karlinsky, L., Gutta, V., Cascante-Bonilla, P., Kim, D., Arbelle, A., Panda, R., Feris, R., Kira, Z.: Coda-prompt: Continual decomposed attention-based prompting for rehearsal-free continual learning. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., Liu, J.: Human action recognition from various data modalities: A review. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"1_CR43","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Advances in Neural Information Processing Systems (2022)"},{"key":"1_CR44","unstructured":"Van\u00a0de Ven, G.M., Tolias, A.S.: Three scenarios for continual learning. arXiv preprint arXiv:1904.07734 (2019)"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Villa, A., Alc\u00e1zar, J.L., Alfarra, M., Alhamoud, K., Hurtado, J., Heilbron, F.C., Soto, A., Ghanem, B.: Pivot: Prompting for video continual learning. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02319"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Lee, C.Y., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J., Pfister, T.: Learning to prompt for continual learning. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Wu, W., Hua, Y., Zheng, C., Wu, S., Chen, C., Lu, A.: Skeletonmae: Spatial-temporal masked autoencoders for self-supervised skeleton action recognition. In: IEEE International Conference on Multimedia and Expo Workshops (2023)","DOI":"10.1109\/ICMEW59549.2023.00045"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Xin, W., Liu, R., Liu, Y., Chen, Y., Yu, W., Miao, Q.: Transformer for skeleton-based action recognition: A review of recent advances. Neurocomputing (2023)","DOI":"10.1016\/j.neucom.2023.03.001"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Yan, H., Liu, Y., Wei, Y., Li, Z., Li, G., Lin, L.: Skeletonmae: graph-based masked autoencoder for skeleton sequence pre-training. In: IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00516"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Yin, J., Han, J., Wang, C., Zhang, B., Zeng, X.: A skeleton-based action recognition system for medical condition detection. In: IEEE Biomedical Circuits and Systems Conference (BioCAS) (2019)","DOI":"10.1109\/BIOCAS.2019.8919127"},{"key":"1_CR52","unstructured":"Zenke, F., Poole, B., Ganguli, S.: Continual learning through synaptic intelligence. In: International Conference on Machine Learning (2017)"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, S., Yang, Y., Xiao, J., Liu, X., Yang, Y., Xie, D., Zhuang, Y.: Fusing geometric features for skeleton-based action recognition using multilayer lstm networks. IEEE Transactions on Multimedia (2018)","DOI":"10.1109\/TMM.2018.2802648"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, Z.: Microsoft kinect sensor and its effect. IEEE MultiMedia (2012)","DOI":"10.1109\/MMUL.2012.24"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78189-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T12:29:50Z","timestamp":1746361790000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78189-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,11]]},"ISBN":["9783031781889","9783031781896"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78189-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,11]]},"assertion":[{"value":"11 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}