{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T03:51:32Z","timestamp":1779940292986,"version":"3.53.1"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:00:00Z","timestamp":1742601600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:00:00Z","timestamp":1742601600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"The Natural Science Foundation of Hebei Provience","award":["F2022511001"],"award-info":[{"award-number":["F2022511001"]}]},{"name":"The Natural Science Foundation of Hebei Provience","award":["F2022511001"],"award-info":[{"award-number":["F2022511001"]}]},{"name":"The Natural Science Foundation of Hebei Provience","award":["F2022511001"],"award-info":[{"award-number":["F2022511001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s00371-025-03850-8","type":"journal-article","created":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T07:23:29Z","timestamp":1742714609000},"page":"7983-7995","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhanced fine-grained relearning for skeleton-based action recognition"],"prefix":"10.1007","volume":"41","author":[{"given":"Zhenghao","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junfen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bojun","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,22]]},"reference":[{"issue":"3","key":"3850_CR1","doi-asserted-by":"publisher","first-page":"3200","DOI":"10.1109\/tpami.2022.3183112","volume":"45","author":"Z Sun","year":"2022","unstructured":"Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., Liu, J.: Human action recognition from various data modalities: a review. IEEE Trans. Patter. Anal. Mach. Intell. 45(3), 3200\u20133225 (2022). https:\/\/doi.org\/10.1109\/tpami.2022.3183112","journal-title":"IEEE Trans. Patter. Anal. Mach. Intell."},{"key":"3850_CR2","doi-asserted-by":"publisher","first-page":"2482","DOI":"10.1109\/tcsvt.2018.2867286","volume":"29","author":"N Xu","year":"2019","unstructured":"Xu, N., Liu, A.-A., Wong, Y., Zhang, Y., Nie, W., Su, Y., Kankanhalli, M.S.: Dual-stream recurrent neural network for video captioning. IEEE Trans. Circuits Syst. Video Technol. 29, 2482\u20132493 (2019). https:\/\/doi.org\/10.1109\/tcsvt.2018.2867286","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3850_CR3","doi-asserted-by":"publisher","unstructured":"Zhao, R., Ali, H., Smagt, P.: Two-stream rnn\/cnn for action recognition in 3d videos. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2017) https:\/\/doi.org\/10.1109\/iros.2017.8206288","DOI":"10.1109\/iros.2017.8206288"},{"key":"3850_CR4","doi-asserted-by":"publisher","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017) https:\/\/doi.org\/10.1109\/cvpr.2017.502","DOI":"10.1109\/cvpr.2017.502"},{"key":"3850_CR5","doi-asserted-by":"publisher","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: 2015 IEEE International Conference on Computer Vision (ICCV) (2015) https:\/\/doi.org\/10.1109\/iccv.2015.510","DOI":"10.1109\/iccv.2015.510"},{"key":"3850_CR6","volume-title":"Temporal segment networks: towards good practices for deep action recognition","author":"L Wang","year":"2016","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. Springer, Cham (2016)"},{"key":"3850_CR7","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. arXiv (Cornell University) 27, 568\u2013576 (2014)"},{"key":"3850_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01446-y","author":"P Weinzaepfel","year":"2021","unstructured":"Weinzaepfel, P., Rogez, G.: Mimetics: towards understanding human actions out of context. Int. J. Comput. Vision (2021). https:\/\/doi.org\/10.1007\/s11263-021-01446-y","journal-title":"Int. J. Comput. Vision"},{"key":"3850_CR9","doi-asserted-by":"publisher","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 p. 32, (2018) https:\/\/doi.org\/10.1609\/aaai.v32i1.12328","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"3850_CR10","doi-asserted-by":"publisher","unstructured":"Ren, B., Liu, M., Ding, R., Liu, H.: A survey on 3d skeleton-based action recognition using learning method (2020) https:\/\/doi.org\/10.48550\/arxiv.2002.05907","DOI":"10.48550\/arxiv.2002.05907"},{"key":"3850_CR11","doi-asserted-by":"crossref","unstructured":"Duhme, M., Memmesheimer, R., Paulus, D.: Fusion-gcn: Multimodal action recognition using graph convolutional networks. arXiv (Cornell University) (2021)","DOI":"10.1007\/978-3-030-92659-5_17"},{"key":"3850_CR12","doi-asserted-by":"publisher","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 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00298","DOI":"10.1109\/CVPR52688.2022.00298"},{"issue":"4\u20135","key":"3850_CR13","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1080\/10447318.2018.1543081","volume":"35","author":"A Kamel","year":"2019","unstructured":"Kamel, A., Liu, B., Li, P., Sheng, B.: An investigation of 3d human pose estimation for learning tai chi: A human factor perspective. Int. J. Hum.-Comput. Interact. 35(4\u20135), 427\u2013439 (2019)","journal-title":"Int. J. Hum.-Comput. Interact."},{"key":"3850_CR14","doi-asserted-by":"publisher","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast Networks for Video Recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00630","DOI":"10.1109\/ICCV.2019.00630"},{"key":"3850_CR15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01232","author":"D Ghadiyaram","year":"2019","unstructured":"Ghadiyaram, D., Tran, D., Mahajan, D.: Large-scale weakly-supervised pre-training for video action recognition. Comput. Vision Pattern Recognit. (2019). https:\/\/doi.org\/10.1109\/cvpr.2019.01232","journal-title":"Comput. Vision Pattern Recognit."},{"key":"3850_CR16","doi-asserted-by":"publisher","unstructured":"Liu, Z., Zhang, H., Chen, Z., Wang, Z., Ouyang, W.: Disentangling and unifying graph convolutions for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00022","DOI":"10.1109\/cvpr42600.2020.00022"},{"key":"3850_CR17","doi-asserted-by":"publisher","first-page":"4405","DOI":"10.1007\/s11042-015-3177-1","volume":"76","author":"C Chen","year":"2015","unstructured":"Chen, C., Jafari, R., Kehtarnavaz, N.: A survey of depth and inertial sensor fusion for human action recognition. Multimed. Tools Appl. 76, 4405\u20134425 (2015). https:\/\/doi.org\/10.1007\/s11042-015-3177-1","journal-title":"Multimed. Tools Appl."},{"issue":"5","key":"3850_CR18","doi-asserted-by":"publisher","first-page":"2774","DOI":"10.1109\/TSMC.2019.2916896","volume":"51","author":"K Aouaidjia","year":"2019","unstructured":"Aouaidjia, K., Sheng, B., Li, P., Kim, J., Feng, D.D.: Efficient body motion quantification and similarity evaluation using 3-d joints skeleton coordinates. IEEE Trans. Syst. Man, Cyber.: Syst. 51(5), 2774\u20132788 (2019)","journal-title":"IEEE Trans. Syst. Man, Cyber.: Syst."},{"key":"3850_CR19","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1049\/cit2.12014","volume":"6","author":"Y Xing","year":"2021","unstructured":"Xing, Y., Zhu, J.: Deep learning-based action recognition with 3d skeleton: A survey. CAAI Trans. Intell. Technol. 6, 80\u201392 (2021). https:\/\/doi.org\/10.1049\/cit2.12014","journal-title":"CAAI Trans. Intell. Technol."},{"issue":"3","key":"3850_CR20","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.1007\/s10044-023-01156-w","volume":"26","author":"Q Cheng","year":"2023","unstructured":"Cheng, Q., Cheng, J., Ren, Z., Zhang, Q., Liu, J.: Multi-scale spatial-temporal convolutional neural network for skeleton-based action recognition. Pattern Anal. Appl. 26(3), 1303\u20131315 (2023)","journal-title":"Pattern Anal. Appl."},{"key":"3850_CR21","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, S., Chen, X., Zhang, Y., Wang, Y., Tian, Q.: Actional-structural graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3595\u20133603 (2019)","DOI":"10.1109\/CVPR.2019.00371"},{"issue":"5","key":"3850_CR22","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TCSVT.2020.3015051","volume":"31","author":"Y-F Song","year":"2020","unstructured":"Song, Y.-F., Zhang, Z., Shan, C., Wang, L.: Richly activated graph convolutional network for robust skeleton-based action recognition. IEEE Trans. Circuits Syst. Video Technol. 31(5), 1915\u20131925 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3850_CR23","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12026\u201312035 (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"3850_CR24","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Skeleton-based action recognition with directed graph neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7912\u20137921 (2019)","DOI":"10.1109\/CVPR.2019.00810"},{"key":"3850_CR25","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/TIP.2021.3129117","volume":"31","author":"H Yang","year":"2021","unstructured":"Yang, H., Yan, D., Zhang, L., Sun, Y., Li, D., Maybank, S.J.: Feedback graph convolutional network for skeleton-based action recognition. IEEE Trans. Image Process 31, 164\u2013175 (2021)","journal-title":"IEEE Trans. Image Process"},{"key":"3850_CR26","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 183\u2013192 (2020)","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"3850_CR27","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1109\/TMM.2023.3271811","volume":"26","author":"J Liu","year":"2023","unstructured":"Liu, J., Wang, X., Wang, C., Gao, Y., Liu, M.: Temporal decoupling graph convolutional network for skeleton-based gesture recognition. IEEE Trans. Multimed. 26, 811\u2013823 (2023)","journal-title":"IEEE Trans. Multimed."},{"key":"3850_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Yan, X., Cheng, Z.-Q., Yan, Y., Dai, Q., Hua, X.-S.: Blockgcn: Redefine topology awareness for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2049\u20132058 (2024)","DOI":"10.1109\/CVPR52733.2024.00200"},{"key":"3850_CR29","doi-asserted-by":"crossref","unstructured":"Xie, J., Meng, Y., Zhao, Y., Nguyen, A., Yang, X., Zheng, Y.: Dynamic semantic-based spatial graph convolution network for skeleton-based human action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 6225\u20136233 (2024)","DOI":"10.1609\/aaai.v38i6.28440"},{"key":"3850_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Q., Wang, Y.: Learning discriminative representations for skeleton based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10608\u201310617 (2023)","DOI":"10.1109\/CVPR52729.2023.01022"},{"key":"3850_CR31","doi-asserted-by":"publisher","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. arXiv (Cornell University) (2019) https:\/\/doi.org\/10.1109\/cvpr.2019.01230","DOI":"10.1109\/cvpr.2019.01230"},{"key":"3850_CR32","doi-asserted-by":"publisher","unstructured":"Li, C., Zhong, Q., Xie, D., Pu, S.: Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation (2018) https:\/\/doi.org\/10.24963\/ijcai.2018\/109","DOI":"10.24963\/ijcai.2018\/109"},{"key":"3850_CR33","doi-asserted-by":"publisher","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., L\u00c3, T.: Tam: Temporal adaptive module for video recognition. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021) https:\/\/doi.org\/10.1109\/iccv48922.2021.01345","DOI":"10.1109\/iccv48922.2021.01345"},{"key":"3850_CR34","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.1109\/tpami.2017.2769085","volume":"40","author":"H Bilen","year":"2018","unstructured":"Bilen, H., Fernando, B., Gavves, E., Vedaldi, A.: Action recognition with dynamic image networks. IEEE Trans. Pattern Anal. Mach. Intell. 40, 2799\u20132813 (2018). https:\/\/doi.org\/10.1109\/tpami.2017.2769085","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3850_CR35","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/tpami.2018.2868668","volume":"41","author":"L Wang","year":"2019","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Gool, L.V.: Temporal segment networks for action recognition in videos. IEEE Trans. Pattern Anal. Mach. Intell. 41, 2740\u20132755 (2019). https:\/\/doi.org\/10.1109\/tpami.2018.2868668","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3850_CR36","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition (2009). https:\/\/doi.org\/10.1109\/cvpr.2009.5206848","DOI":"10.1109\/cvpr.2009.5206848"},{"key":"3850_CR37","doi-asserted-by":"publisher","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks. In: proceedings of the IEEE International Conference on Computer Vision (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.590","DOI":"10.1109\/ICCV.2017.590"},{"key":"3850_CR38","doi-asserted-by":"publisher","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A Closer Look at Spatiotemporal Convolutions for Action Recognition. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00675","DOI":"10.1109\/CVPR.2018.00675"},{"key":"3850_CR39","doi-asserted-by":"publisher","unstructured":"Feichtenhofer, C.: X3d: Expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00028","DOI":"10.1109\/cvpr42600.2020.00028"},{"key":"3850_CR40","doi-asserted-by":"publisher","first-page":"1250","DOI":"10.1109\/tcsvt.2021.3077512","volume":"32","author":"H Wu","year":"2021","unstructured":"Wu, H., Ma, X., Li, Y.: Spatiotemporal multimodal learning with 3d cnns for video action recognition. IEEE Trans. Circuits Syst. Video Technol. 32, 1250\u20131261 (2021). https:\/\/doi.org\/10.1109\/tcsvt.2021.3077512","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3850_CR41","doi-asserted-by":"publisher","first-page":"83791","DOI":"10.1109\/access.2020.2991891","volume":"8","author":"B Fu","year":"2020","unstructured":"Fu, B., Damer, N., Kirchbuchner, F., Kuijper, A.: Sensing technology for human activity recognition: a comprehensive survey. IEEE Access 8, 83791\u201383820 (2020). https:\/\/doi.org\/10.1109\/access.2020.2991891","journal-title":"IEEE Access"},{"key":"3850_CR42","unstructured":"Huang, X., Zhou, H., Feng, B., Wang, X., Liu, W., Wang, J., Feng, H., Han, J., Ding, E., Wang, J.: Graph contrastive learning for skeleton-based action recognition. arXiv (Cornell University) (2023). https:\/\/doi.org\/10.48550\/arxiv.2301.10900"},{"key":"3850_CR43","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1007\/s00371-021-02229-9","volume":"38","author":"S Zeghoud","year":"2022","unstructured":"Zeghoud, S., Ali, S.G., Ertugrul, E., Kamel, A., Sheng, B., Li, P., Chi, X., Kim, J., Mao, L.: Real-time spatial normalization for dynamic gesture classification. Visual Comput. 38, 1345\u20131357 (2022)","journal-title":"Visual Comput."},{"key":"3850_CR44","doi-asserted-by":"publisher","first-page":"2963","DOI":"10.1109\/TIP.2021.3056895","volume":"30","author":"C Bian","year":"2021","unstructured":"Bian, C., Feng, W., Wan, L., Wang, S.: Structural knowledge distillation for efficient skeleton-based action recognition. IEEE Trans. Image Process. 30, 2963\u20132976 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"3850_CR45","doi-asserted-by":"publisher","first-page":"1918","DOI":"10.1109\/LSP.2022.3204190","volume":"29","author":"C Liu","year":"2022","unstructured":"Liu, C., Zhao, X., Li, Z., Yan, Z., Du, C.: A novel two-stage knowledge distillation framework for skeleton-based action prediction. IEEE Sig. Process. Lett. 29, 1918\u20131922 (2022)","journal-title":"IEEE Sig. Process. Lett."},{"key":"3850_CR46","doi-asserted-by":"crossref","unstructured":"Liu, C., Jiang, Y., Du, C., Li, Z.: Enhancing action recognition from low-quality skeleton data via part-level knowledge distillation. Sig. Process. 221, 109486 (2024)","DOI":"10.1016\/j.sigpro.2024.109486"},{"key":"3850_CR47","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.1109\/TIP.2024.3364056","volume":"33","author":"Y Chen","year":"2024","unstructured":"Chen, Y., Jiang, R., Zheng, Y., Sheng, B., Yang, Z.-X., Wu, E.: Dual branch multi-level semantic learning for few-shot segmentation. IEEE Trans. Image Process. 33, 1432\u20131447 (2024)","journal-title":"IEEE Trans. Image Process."},{"key":"3850_CR48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.787","author":"C Feichtenhofer","year":"2017","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal multiplier networks for video action recognition. Comput. Vision Pattern Recognit. (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.787","journal-title":"Comput. Vision Pattern Recognit."},{"key":"3850_CR49","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: Temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"3850_CR50","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: Eca-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"3850_CR51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2858826","author":"T-Y Lin","year":"2018","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. (2018). https:\/\/doi.org\/10.1109\/tpami.2018.2858826","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3850_CR52","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"3850_CR53","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2616\u20132625 (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"3850_CR54","doi-asserted-by":"publisher","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: A large video database for human motion recognition. In: 2011 International Conference on Computer Vision (2011) https:\/\/doi.org\/10.1109\/iccv.2011.6126543","DOI":"10.1109\/iccv.2011.6126543"},{"key":"3850_CR55","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"3850_CR56","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2916873","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M.L., Wang, G., Duan, L.-Y., Kot Chichung, A.: Ntu rgb+d 120: a large-scale benchmark for 3d human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. (2019). https:\/\/doi.org\/10.1109\/tpami.2019.2916873","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03850-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03850-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03850-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T08:22:23Z","timestamp":1757146943000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03850-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,22]]},"references-count":56,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["3850"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03850-8","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,22]]},"assertion":[{"value":"17 February 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}