{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:55:02Z","timestamp":1760316902729,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031882166"},{"type":"electronic","value":"9783031882173"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-88217-3_24","type":"book-chapter","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T10:23:43Z","timestamp":1748255023000},"page":"314-323","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Modality Fusion Adaptor-Enhanced Vision Transformer for\u00a0Multimodal Action Recognition"],"prefix":"10.1007","author":[{"given":"Xin","family":"Hu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7316-4354","authenticated-orcid":false,"given":"Yunan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yulang","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yihao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Shoude","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2872-388X","authenticated-orcid":false,"given":"Qiguang","family":"Miao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,27]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"24_CR2","unstructured":"Ba, J.L.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Bandi, C., Thomas, U.: Skeleton-based action recognition for human-robot interaction using self-attention mechanism. In: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pp.\u00a01\u20138. IEEE (2021)","DOI":"10.1109\/FG52635.2021.9666948"},{"key":"24_CR4","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"24_CR5","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/s10489-020-01823-z","volume":"51","author":"O Elharrouss","year":"2021","unstructured":"Elharrouss, O., Almaadeed, N., Al-Maadeed, S., Bouridane, A., Beghdadi, A.: A combined multiple action recognition and summarization for surveillance video sequences. Appl. Intell. 51, 690\u2013712 (2021)","journal-title":"Appl. Intell."},{"key":"24_CR6","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"24_CR7","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., Miao, Q., Tian, K., Fan, Y., Xu, X., Li, R., Song, J.: Large-scale gesture recognition with a fusion of RGB-D data based on the C3D model. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 25\u201330. IEEE (2016)","DOI":"10.1109\/ICPR.2016.7899602"},{"key":"24_CR9","unstructured":"Li, Y., et al.: Watching it in dark: a target-aware representation learning framework for high-level vision tasks in low illumination. In: European Conference on Computer Vision (2022)"},{"key":"24_CR10","unstructured":"Loshchilov, I.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Miao, Q., et al.: Multimodal gesture recognition based on the resc3d network. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 3047\u20133055 (2017)","DOI":"10.1109\/ICCVW.2017.360"},{"issue":"1","key":"24_CR12","first-page":"1391906","volume":"2022","author":"F Serpush","year":"2022","unstructured":"Serpush, F., Menhaj, M.B., Masoumi, B., Karasfi, B.: Wearable sensor-based human activity recognition in the smart healthcare system. Comput. Intell. Neurosci. 2022(1), 1391906 (2022)","journal-title":"Comput. Intell. Neurosci."},{"key":"24_CR13","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Advances in Neural Information Processing Systems (2022)"},{"key":"24_CR14","unstructured":"Xu, Y., Cao, H., Mao, K., Chen, Z., Xie, L., Yang, J.: Aligning correlation information for domain adaptation in action recognition. IEEE Trans. Neural Netw. Learn. Syst. (2022)"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Zhou, B., et al.: Decoupling and recoupling spatiotemporal representation for RGB-D-based motion recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20154\u201320163 (2022)","DOI":"10.1109\/CVPR52688.2022.01952"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR 2024 International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-88217-3_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T19:13:32Z","timestamp":1760296412000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88217-3_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031882166","9783031882173"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88217-3_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"27 May 2025","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"}}]}}