{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T22:58:16Z","timestamp":1781218696144,"version":"3.54.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"content-version":"vor","delay-in-days":53,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Natural Science Basic Research Plan in Shaanxi Province of China"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-49105-x","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T07:27:57Z","timestamp":1776670077000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic knowledge enhanced 3D human\u2013object interaction learning"],"prefix":"10.1038","volume":"16","author":[{"given":"Xuyang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiyue","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaopeng","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingbin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichuan","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiapeng","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Getao","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"49105_CR1","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/s10956-012-9405-9","volume":"22","author":"K-H Cheng","year":"2013","unstructured":"Cheng, K.-H. & Tsai, C.-C. Affordances of augmented reality in science learning: Suggestions for future research. J. Sci. Educ. Technol. 22, 449\u2013462 (2013).","journal-title":"J. Sci. Educ. Technol."},{"key":"49105_CR2","doi-asserted-by":"publisher","first-page":"107954","DOI":"10.1016\/j.knosys.2021.107954","volume":"239","author":"IF del Amo","year":"2022","unstructured":"del Amo, I. F., Erkoyuncu, J. A., Farsi, M. & Ariansyah, D. Hybrid recommendations and dynamic authoring for AR knowledge capture and re-use in diagnosis applications. Knowl.-Based Syst. 239, 107954 (2022).","journal-title":"Knowl.-Based Syst."},{"key":"49105_CR3","doi-asserted-by":"crossref","unstructured":"Zare, M., Kebria, P. M., Khosravi, A. & Nahavandi, S. Algorithms, recent developments, and challenges. In IEEE Transactions on Cybernetics, A Survey of Imitation Learning (2024).","DOI":"10.1109\/TCYB.2024.3395626"},{"key":"49105_CR4","doi-asserted-by":"crossref","unstructured":"Hu, Y. et al. Fusion dynamical systems with machine learning in imitation learning: A comprehensive overview. Inf. Fusion 102379 (2024).","DOI":"10.1016\/j.inffus.2024.102379"},{"key":"49105_CR5","doi-asserted-by":"crossref","unstructured":"Ren, L., Dong, J., Liu, S., Zhang, L. & Wang, L. Embodied intelligence toward future smart manufacturing in the era of AI foundation model. In IEEE\/ASME Transactions on Mechatronics (2024).","DOI":"10.1109\/TMECH.2024.3456250"},{"key":"49105_CR6","doi-asserted-by":"crossref","unstructured":"Liu, H., Guo, D. & Cangelosi, A. A synergy of morphology, action, perception and learning. ACM Comput. Surv. Embodied Intell. (2025).","DOI":"10.1145\/3717059"},{"key":"49105_CR7","doi-asserted-by":"crossref","unstructured":"Dai, Y. & Wang, J. Co-evolving embodied intelligence with design for artificial intelligence architecture. Nat. Rev. Electr. Eng. 1\u20132 (2025).","DOI":"10.1038\/s44287-025-00146-w"},{"key":"49105_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dwivedi, S.\u00a0K., Black, M.\u00a0J. & Tzionas, D. Detecting human-object contact in images. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17100\u201317110 (2023).","DOI":"10.1109\/CVPR52729.2023.01640"},{"key":"49105_CR9","doi-asserted-by":"crossref","unstructured":"Tripathi, S. et al. Deco: Dense estimation of 3D human-scene contact in the wild. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 8001\u20138013 (2023).","DOI":"10.1109\/ICCV51070.2023.00735"},{"key":"49105_CR10","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y. & Tao, D. Learning affordance grounding from exocentric images. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2252\u20132261 (2022).","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"49105_CR11","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y. & Tao, D. Leverage interactive affinity for affordance learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 6809\u20136819 (2023).","DOI":"10.1109\/CVPR52729.2023.00658"},{"key":"49105_CR12","doi-asserted-by":"crossref","unstructured":"Petrov, I.\u00a0A., Marin, R., Chibane, J. & Pons-Moll, G. Object pop-up: Can we infer 3D objects and their poses from human interactions alone? In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4726\u20134736 (2023).","DOI":"10.1109\/CVPR52729.2023.00458"},{"key":"49105_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y.-L. et al. Detailed 2D-3D joint representation for human-object interaction. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10166\u201310175 (2020).","DOI":"10.1109\/CVPR42600.2020.01018"},{"key":"49105_CR14","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhai, W., Luo, H., Cao, Y. & Zha, Z.-J. Lemon: Learning 3D human-object interaction relation from 2D images. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16284\u201316295 (2024).","DOI":"10.1109\/CVPR52733.2024.01541"},{"key":"49105_CR15","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P. & He, K. Detecting and recognizing human-object interactions. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8359\u20138367 (2018).","DOI":"10.1109\/CVPR.2018.00872"},{"key":"49105_CR16","doi-asserted-by":"crossref","unstructured":"Chao, Y.-W., Liu, Y., Liu, X., Zeng, H. & Deng, J. Learning to detect human-object interactions. In IEEE Winter Conference on Applications of Computer Vision. 381\u2013389 (2018).","DOI":"10.1109\/WACV.2018.00048"},{"key":"49105_CR17","doi-asserted-by":"crossref","unstructured":"Tamura, M., Ohashi, H. & Yoshinaga, T. Qpic: Query-based pairwise human-object interaction detection with image-wide contextual information. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10410\u201310419 (2021).","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"49105_CR18","doi-asserted-by":"crossref","unstructured":"Kim, B., Lee, J., Kang, J., Kim, E.-S. & Kim, H.\u00a0J. Hotr: End-to-end human-object interaction detection with transformers. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 74\u201383 (2021).","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"49105_CR19","doi-asserted-by":"crossref","unstructured":"Qi, S., Wang, W., Jia, B., Shen, J. & Zhu, S.-C. Learning human-object interactions by graph parsing neural networks. In Proceedings of the European Conference on Computer Vision. 401\u2013417 (2018).","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"49105_CR20","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1016\/j.neucom.2022.08.008","volume":"509","author":"Q Li","year":"2022","unstructured":"Li, Q., Xie, X., Zhang, C., Zhang, J. & Shi, G. Detecting human-object interactions in videos by modeling the trajectory of objects and human skeleton. Neurocomputing 509, 234\u2013243 (2022).","journal-title":"Neurocomputing"},{"key":"49105_CR21","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Feichtenhofer, C. & Grauman, K. Grounded human-object interaction hotspots from video. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 8688\u20138697 (2019).","DOI":"10.1109\/ICCV.2019.00878"},{"key":"49105_CR22","doi-asserted-by":"publisher","first-page":"2472","DOI":"10.1007\/s11263-022-01642-4","volume":"130","author":"W Zhai","year":"2022","unstructured":"Zhai, W., Luo, H., Zhang, J., Cao, Y. & Tao, D. One-shot object affordance detection in the wild. Int. J. Comput. Vis. 130, 2472\u20132500 (2022).","journal-title":"Int. J. Comput. Vis."},{"key":"49105_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G. & Black, M. J. Smpl: A skinned multi-person linear model. ACM Trans. Graph. (TOG) 34, 1\u201316 (2015).","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"49105_CR24","doi-asserted-by":"crossref","unstructured":"Pavlakos, G. et al. Expressive body capture: 3D hands, face, and body from a single image. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10975\u201310985 (2019).","DOI":"10.1109\/CVPR.2019.01123"},{"key":"49105_CR25","unstructured":"Romero, J., Tzionas, D. & Black, M.\u00a0J. Embodied hands: Modeling and capturing hands and bodies together. arXiv preprint arXiv:2201.02610 (2022)."},{"key":"49105_CR26","doi-asserted-by":"crossref","unstructured":"Huang, C.-H.\u00a0P. et al. Capturing and inferring dense full-body human-scene contact. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13274\u201313285 (2022).","DOI":"10.1109\/CVPR52688.2022.01292"},{"key":"49105_CR27","doi-asserted-by":"crossref","unstructured":"Deng, S., Xu, X., Wu, C., Chen, K. & Jia, K. 3D affordancenet: A benchmark for visual object affordance understanding. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1778\u20131787 (2021).","DOI":"10.1109\/CVPR46437.2021.00182"},{"key":"49105_CR28","doi-asserted-by":"crossref","unstructured":"Han, S. & Joo, H. Chorus: Learning canonicalized 3d human-object spatial relations from unbounded synthesized images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 15835\u201315846 (2023).","DOI":"10.1109\/ICCV51070.2023.01451"},{"key":"49105_CR29","doi-asserted-by":"crossref","unstructured":"Yang, Y. et al. Grounding 3D object affordance from 2D interactions in images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 10905\u201310915 (2023).","DOI":"10.1109\/ICCV51070.2023.01001"},{"key":"49105_CR30","doi-asserted-by":"crossref","unstructured":"Bui, D.\u00a0C., Le, T.\u00a0V. & Ngo, B.\u00a0H. C2t-net: Channel-aware cross-fused transformer-style networks for pedestrian attribute recognition. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 351\u2013358 (2024).","DOI":"10.1109\/WACVW60836.2024.00043"},{"key":"49105_CR31","doi-asserted-by":"publisher","first-page":"111486","DOI":"10.1016\/j.patcog.2025.111486","volume":"164","author":"DC Bui","year":"2025","unstructured":"Bui, D. C., Le, T. V., Ngo, B. H. & Choi, T. J. Clear: Cross-transformers with pre-trained language model for person attribute recognition and retrieval. Pattern Recognit. 164, 111486 (2025).","journal-title":"Pattern Recognit."},{"key":"49105_CR32","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J. et al. Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43, 3349\u20133364 (2020).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"49105_CR33","first-page":"1","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang, Y. et al. Dynamic graph cnn for learning on point clouds. ACM Trans. Graph. (TOG) 38, 1\u201312 (2019).","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"49105_CR34","unstructured":"Team, Q. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"49105_CR35","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. 8748\u20138763 (2021)."},{"key":"49105_CR36","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Doll\u00e1r, P. Focal loss for dense object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2980\u20132988 (2017).","DOI":"10.1109\/ICCV.2017.324"},{"key":"49105_CR37","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N. & Ahmadi, S.-A. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 Fourth International Conference on 3D Vision (3DV). 565\u2013571 (2016).","DOI":"10.1109\/3DV.2016.79"},{"key":"49105_CR38","doi-asserted-by":"publisher","first-page":"8494","DOI":"10.1109\/TPAMI.2022.3232797","volume":"45","author":"Y Li","year":"2022","unstructured":"Li, Y. et al. Hake: A knowledge engine foundation for human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 45, 8494\u20138506 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"49105_CR39","unstructured":"Gupta, S. & Malik, J. Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)."},{"key":"49105_CR40","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition. 248\u2013255 (2009).","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-49105-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-49105-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-49105-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T22:28:53Z","timestamp":1781216933000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-49105-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["49105"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-49105-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"18215"}}