{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:40:57Z","timestamp":1776530457902,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556755","type":"print"},{"value":"9789819556762","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\/978-981-95-5676-2_14","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:32:25Z","timestamp":1768249945000},"page":"203-217","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Cross-modal Feature Enhancement and\u00a0Contrastive Alignment for\u00a0Micro-gesture Recognition"],"prefix":"10.1007","author":[{"given":"Tuyun","family":"Shang","sequence":"first","affiliation":[]},{"given":"Yanbin","family":"Hao","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Pei","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Li","sequence":"additional","affiliation":[]},{"given":"Huixia","family":"Ben","sequence":"additional","affiliation":[]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset (2018)","DOI":"10.1109\/CVPR.2017.502"},{"key":"14_CR2","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1007\/s11263-023-01761-6","volume":"131","author":"H Chen","year":"2023","unstructured":"Chen, H., Shi, H., Liu, X., et al.: SMG: a micro-gesture dataset towards spontaneous body gestures for emotional stress state analysis. Int. J. Comput. Vision 131, 1346\u20131366 (2023)","journal-title":"Int. J. Comput. Vision"},{"key":"14_CR3","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: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 180\u2013189 (2020)","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"14_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.123061","volume":"244","author":"Q Cheng","year":"2024","unstructured":"Cheng, Q., Cheng, J., Liu, Z., Ren, Z., Liu, J.: A dense-sparse complementary network for human action recognition based on RGB and skeleton modalities. Expert Syst. Appl. 244, 123061 (2024)","journal-title":"Expert Syst. Appl."},{"key":"14_CR5","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2969\u20132978 (June 2022)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. arXiv preprint arXiv:1812.03982 (2018)","DOI":"10.1109\/ICCV.2019.00630"},{"issue":"7","key":"14_CR7","doi-asserted-by":"publisher","first-page":"6238","DOI":"10.1109\/TCSVT.2024.3358415","volume":"34","author":"D Guo","year":"2024","unstructured":"Guo, D., Li, K., Hu, B., Zhang, Y., Wang, M.: Benchmarking micro-action recognition: dataset, methods, and applications. IEEE Trans. Circuits Syst. Video Technol. 34(7), 6238\u20136252 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"10","key":"14_CR8","doi-asserted-by":"publisher","first-page":"7120","DOI":"10.1109\/TCSVT.2022.3169842","volume":"32","author":"Y Hao","year":"2022","unstructured":"Hao, Y., et al.: Attention in attention: modeling context correlation for efficient video classification. IEEE Trans. Circuits Syst. Video Technol. 32(10), 7120\u20137132 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Hao, Y., Zhang, H., Ngo, C.W., He, X.: Group contextualization for video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 928\u2013938 (2022)","DOI":"10.1109\/CVPR52688.2022.00100"},{"issue":"12","key":"14_CR10","doi-asserted-by":"publisher","first-page":"5820","DOI":"10.1007\/s11263-024-02154-z","volume":"132","author":"Y Hao","year":"2024","unstructured":"Hao, Y., Zhou, D., Wang, Z., Ngo, C.W., Wang, M.: PosMLP-video: spatial and temporal relative position encoding for efficient video recognition. Int. J. Comput. Vision 132(12), 5820\u20135840 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"14_CR11","unstructured":"Huang, H., Guo, X., Peng, W., Xia, Z.: Micro-gesture classification based on ensemble hypergraph-convolution transformer. In: MiGA@ IJCAI (2023)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, H., Zheng, W., Zong, Y., Xu, X., Jiang, X., Xue, Y.: Geometric magnification-based attention graph convolutional network for skeleton-based micro-gesture recognition. In: 2023 IEEE International Conference on Image Processing (ICIP), pp. 3404\u20133408 (2023)","DOI":"10.1109\/ICIP49359.2023.10222125"},{"key":"14_CR13","unstructured":"Khor, H., See, J., Phan, R.C., Lin, W.: Enriched long-term recurrent convolutional network for facial micro-expression recognition. CoRR abs\/1805.08417 (2018)"},{"key":"14_CR14","unstructured":"Li, K., Guo, D., Chen, G., Peng, X., Wang, M.: Joint skeletal and semantic embedding loss for micro-gesture classification (2023)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: Temporal shift module for efficient video understanding (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Liu, M., Bian, S., Zhou, B., Lukowicz, P.: iKAN: Global incremental learning with KAN for human activity recognition across heterogeneous datasets (2024)","DOI":"10.1145\/3675095.3676618"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Liu, X., Shi, H., Chen, H., Yu, Z., Li, X., Zhaoz?, G.: iMiGUE: An identity-free video dataset for micro-gesture understanding and emotion analysis (2021)","DOI":"10.1109\/CVPR46437.2021.01049"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., Hu, H.: Video swin transformer (2021)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"14_CR19","unstructured":"Liu, Z., et al.: KAN: Kolmogorov-Arnold networks. arXiv preprint arXiv:2404.19756 (2025)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, H., Chen, Z., Wang, Z., Ouyang, W.: Disentangling and unifying graph convolutions for skeleton-based action recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"14_CR21","unstructured":"Pan, J., Lin, Z., Zhu, X., Shao, J., Li, H.: ST-adapter: Parameter-efficient image-to-video transfer learning. arXiv preprint arXiv:2206.13559 (2022)"},{"key":"14_CR22","unstructured":"Patapati, S., Srinivasan, T., Adiraju, A.: CLIP-MG: guiding semantic attention with skeletal pose features and RGB data for micro-gesture recognition on the iMiGUE dataset (2025)"},{"key":"14_CR23","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"14_CR25","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 (ICCV), pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. arXiv preprint arXiv:1711.11248 (2017)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Gool, L.V.: Temporal segment networks: Towards good practices for deep action recognition. arXiv preprint arXiv:1608.00859 (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Wang, S., Guo, D., Zhou, W.g., Zha, Z.j., Wang, M.: Connectionist temporal fusion for sign language translation. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 1483\u20131491 (2018)","DOI":"10.1145\/3240508.3240671"},{"key":"14_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1007\/978-3-030-58607-2_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Wang","year":"2020","unstructured":"Wang, S., Yue, J., Liu, J., Tian, Q., Wang, M.: Large-scale few-shot learning via multi-modal knowledge discovery. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 718\u2013734. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_42"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Y., See, J., Phan, R.C., Oh, Y.: Efficient spatio-temporal local binary patterns for spontaneous facial micro-expression recognition. PLoS One 10(5), e0124674 (2015)","DOI":"10.1371\/journal.pone.0124674"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. CoRR abs\/1801.07455 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Yu, B.X., Liu, Y., Zhang, X., Zhong, S.h., Chan, K.C.: MMNet: a model-based multimodal network for human action recognition in RGB-D videos. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3522\u20133538 (2023)","DOI":"10.1109\/TPAMI.2022.3177813"},{"key":"14_CR33","unstructured":"Zhang, B., et al.: VideoLLaMA 3: Frontier multimodal foundation models for image and video understanding (2025)"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hao, Y., Ngo, C.W.: Token shift transformer for video classification. In: Proceedings of the 29th ACM International Conference on Multimedia (MM \u201921), pp. 917\u2013925. ACM (2021)","DOI":"10.1145\/3474085.3475272"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. arXiv preprint arXiv:1711.08496 (2018)","DOI":"10.1007\/978-3-030-01246-5_49"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5676-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:32:30Z","timestamp":1768249950000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5676-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556755","9789819556762"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5676-2_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}