{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T03:55:11Z","timestamp":1779940511889,"version":"3.53.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726392","type":"print"},{"value":"9783031726408","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-72640-8_25","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"447-462","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by\u00a0Disentangled Variational Autoencoders"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9091-8036","authenticated-orcid":false,"given":"Sheng-Wei","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8214-3226","authenticated-orcid":false,"given":"Zi-Xiang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0557-8106","authenticated-orcid":false,"given":"Wei-Jie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6707-8589","authenticated-orcid":false,"given":"Yi-Hsin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8989-501X","authenticated-orcid":false,"given":"Chih-Yuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2408-4603","authenticated-orcid":false,"given":"Jane Yung-jen","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Atzmon, Y., Chechik, G.: Adaptive confidence smoothing for generalized zero-shot learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01194"},{"key":"25_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-642-39593-2_1","volume-title":"Statistical Language and Speech Processing","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y.: Deep learning of representations: looking forward. In: Dediu, A.-H., Mart\u00edn-Vide, C., Mitkov, R., Truthe, B. (eds.) Statistical Language and Speech Processing, pp. 1\u201337. Springer Berlin Heidelberg, Berlin, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-39593-2_1"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Semantics disentangling for generalized zero-shot learning. In: ICCV (2021)","DOI":"10.36227\/techrxiv.13683919.v1"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, K., Zhang, Y., He, X., Chen, W., Cheng, J., Lu, H.: Skeleton-based action recognition with shift graph convolutional network. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"25_CR5","unstructured":"Chunhui, L., Yueyu, H., Yanghao, L., Sijie, S., Jiaying, L.: PKU-MMD: a large scale benchmark for continuous multi-modal human action understanding. arXiv preprint arXiv:1703.07475 (2017)"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Fu, H., Li, C., Liu, X., Gao, J., Celikyilmaz, A., Carin, L.: Cyclical annealing schedule: a simple approach to mitigating KL vanishing. arXiv preprint arXiv:1903.10145 (2019)","DOI":"10.18653\/v1\/N19-1021"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Gupta, P., Sharma, D., Sarvadevabhatla, R.K.: Syntactically guided generative embeddings for zero-shot skeleton action recognition. In: ICIP (2021)","DOI":"10.1109\/ICIP42928.2021.9506179"},{"key":"25_CR8","unstructured":"Higgins, I., et al.: beta-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (2016)"},{"key":"25_CR9","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"issue":"4","key":"25_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925975","volume":"35","author":"D Holden","year":"2016","unstructured":"Holden, D., Saito, J., Komura, T.: A deep learning framework for character motion synthesis and editing. ACM Trans. Graph. (TOG) 35(4), 1\u201311 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR11","doi-asserted-by":"publisher","unstructured":"Honnibal, M., Montani, I., Van\u00a0Landeghem, S., Boyd, A.: spaCy: industrial-strength Natural Language Processing in Python (2020). https:\/\/doi.org\/10.5281\/zenodo.1212303","DOI":"10.5281\/zenodo.1212303"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Hubert\u00a0Tsai, Y.H., Huang, L.K., Salakhutdinov, R.: Learning robust visual-semantic embeddings. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.386"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Keselman, L., Iselin\u00a0Woodfill, J., Grunnet-Jepsen, A., Bhowmik, A.: Intel RealSense stereoscopic depth cameras. In: CVPRW (2017)","DOI":"10.1109\/CVPRW.2017.167"},{"key":"25_CR14","unstructured":"Kingma, D.P., Welling, M.: Auto-Encoding Variational Bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"issue":"1\u20133","key":"25_CR15","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/BF01589116","volume":"45","author":"DC Liu","year":"1989","unstructured":"Liu, D.C., Nocedal, J.: On the limited memory BFGS method for large scale optimization. Math. Program. 45(1\u20133), 503\u2013528 (1989)","journal-title":"Math. Program."},{"issue":"10","key":"25_CR16","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu, J., et al.: NTU RGB+D 120: a large-scale benchmark for 3D human activity understanding. TPAMI 42(10), 2684\u20132701 (2019)","journal-title":"TPAMI"},{"key":"25_CR17","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: SciKit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"25_CR18","first-page":"4051","volume":"45","author":"F Pourpanah","year":"2022","unstructured":"Pourpanah, F., et al.: A review of generalized zero-shot learning methods. TPAMI 45(4), 4051\u20134070 (2022)","journal-title":"TPAMI"},{"key":"25_CR19","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Schonfeld, E., Ebrahimi, S., Sinha, S., Darrell, T., Akata, Z.: Generalized zero-and few-shot learning via aligned variational autoencoders. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00844"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+D: a large scale dataset for 3D human activity analysis. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Wray, M., Larlus, D., Csurka, G., Damen, D.: Fine-grained action retrieval through multiple parts-of-speech embeddings. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00054"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI. vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"25_CR26","unstructured":"Yuan, Y., et al.: HRFormer: high-resolution vision transformer for dense prediction. In: NeurIPS (2021)"},{"issue":"2","key":"25_CR27","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MMUL.2012.24","volume":"19","author":"Z Zhang","year":"2012","unstructured":"Zhang, Z.: Microsoft Kinect sensor and its effect. IEEE Multimedia 19(2), 4\u201310 (2012)","journal-title":"IEEE Multimedia"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Qiang, W., Rao, A., Lin, N., Su, B., Wang, J.: Zero-shot skeleton-based action recognition via mutual information estimation and maximization. In: ACM MM (2023)","DOI":"10.1145\/3581783.3611888"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72640-8_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:50:28Z","timestamp":1730109028000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72640-8_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031726392","9783031726408"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72640-8_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","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":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}