{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T11:34:13Z","timestamp":1773747253709,"version":"3.50.1"},"reference-count":41,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biomimetics"],"abstract":"<jats:p>Monocular 3D human\u2013object interaction (HOI) reconstruction requires jointly recovering articulated human geometry, object pose, and physically plausible contact from a single RGB image. While recent token-based methods commonly employ dense self-attention to capture global dependencies, isotropic all-to-all mixing tends to entangle spatial-geometric cues (e.g., contact locality) with channel-wise semantic cues (e.g., action\/affordance), and provides limited control for representing directional and asymmetric physical influence between humans and objects. This paper presents HOIMamba, a state-space sequence modeling framework that reformulates HOI reconstruction as bidirectional, multi-scale interaction state inference. Instead of relying on symmetric correlation aggregation, HOIMamba uses structured state evolution to propagate interaction evidence. We introduce a multi-scale state-space module (MSSM) to capture interaction dependencies spanning local contact details and global body\u2013object coordination. Building on MSSM, we propose a spatial-channel grouped SSM (SCSSM) block that factorizes interaction modeling into a spatial pathway for geometric\/contact dependencies and a channel pathway for semantic\/functional correlations, followed by gated fusion. HOIMamba further performs explicit bidirectional propagation between human and object states to better reflect asymmetric reciprocity in physical interactions. We evaluate HOIMamba on two public benchmarks, BEHAVE and InterCap, using Chamfer distance for human\/object meshes and contact precision\/recall induced by reconstructed geometry. HOIMamba achieves consistent improvements over representative prior methods. On the BEHAVE dataset, it reduces human Chamfer distance by 8.6% and improves contact recall by 13.5% compared to the strongest Transformer-based baseline, with similar gains observed on the InterCap dataset. Ablation studies on BEHAVE verify the contributions of state-space modeling, multi-scale inference, spatial-channel factorization, and bidirectional interaction reasoning.<\/jats:p>","DOI":"10.3390\/biomimetics11030214","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T10:21:41Z","timestamp":1773742901000},"page":"214","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HOIMamba: Bidirectional State-Space Modeling for Monocular 3D Human\u2013Object Interaction Reconstruction"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9619-5030","authenticated-orcid":false,"given":"Jinsong","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science, Big Data and Software, Fuzhou University, Fuzhou 350108, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqin","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science, Big Data and Software, Fuzhou University, Fuzhou 350108, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Catalfamo, A., Celesti, A., Fazio, M., Saif, A.S., Lin, Y.S., Silva, E.F., and Villari, M. (2025). An Approach to Enable Human\u20133D Object Interaction Through Voice Commands in an Immersive Virtual Environment. Big Data Cogn. Comput., 9.","DOI":"10.3390\/bdcc9070188"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wang, T., Lu, T., Fang, W., and Zhang, Y. (2022). Human\u2013Object Interaction Detection with Ratio-Transformer. Symmetry, 14.","DOI":"10.3390\/sym14081666"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Peng, W., Li, C., Tang, K., Liu, X., and Fang, M. (2022). HOME: 3D Human\u2013Object Mesh Topology-Enhanced Interaction Recognition in Images. Mathematics, 10.","DOI":"10.3390\/math10162841"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"130709","DOI":"10.1016\/j.neucom.2025.130709","article-title":"Simple yet effective: An explicit query-based relation learner for human-object-interaction detection","volume":"649","author":"Luo","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Alhaji, B., Beecken, J., Ehlers, R., Gertheiss, J., Merz, F., M\u00fcller, J.P., Prilla, M., Rausch, A., Reinhardt, A., and Reinhardt, D. (2020). Engineering human\u2013machine teams for trusted collaboration. Big Data Cogn. Comput., 4.","DOI":"10.3390\/bdcc4040035"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Peng, B., and Chen, B. (2025). Bayesian prototypical pruning for transformers in human\u2013robot collaboration. Mathematics, 13.","DOI":"10.3390\/math13091411"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez-Rodicio, E., Dondrup, C., Sevilla-Salcedo, J., Castro-Gonz\u00e1lez, \u00c1., and Salichs, M.A. (2025). Predicting and Synchronising Co-Speech Gestures for Enhancing Human\u2013Robot Interactions Using Deep Learning Models. Biomimetics, 10.","DOI":"10.3390\/biomimetics10120835"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"126243","DOI":"10.1016\/j.neucom.2023.126243","article-title":"From detection to understanding: A survey on representation learning for human-object interaction","volume":"543","author":"Luo","year":"2023","journal-title":"Neurocomputing"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"130882","DOI":"10.1016\/j.neucom.2025.130882","article-title":"Exploring interaction concepts for human\u2013object-interaction detection via global- and local-scale enhancing","volume":"651","author":"Luo","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhang, J.Y., Pepose, S., Joo, H., Ramanan, D., Malik, J., and Kanazawa, A. (2020, January 23\u201328). Perceiving 3d human-object spatial arrangements from a single image in the wild. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58610-2_3"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Xie, X., Bhatnagar, B.L., and Pons-Moll, G. (2022, January 23\u201327). Chore: Contact, human and object reconstruction from a single rgb image. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20086-1_8"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Nam, H., Jung, D.S., Moon, G., and Lee, K.M. (2024, January 16\u201322). Joint reconstruction of 3d human and object via contact-based refinement transformer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.00973"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, Q., Ma, S., Ye, M., Zhan, Y., and Li, D. (2025, January 11\u201315). End-to-End HOI Reconstruction Transformer with Graph-based Encoding. Proceedings of the IEEE Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.02580"},{"key":"ref_14","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref_15","unstructured":"Gu, A., Goel, K., and R\u00e9, C. (2021). Efficiently modeling long sequences with structured state spaces. arXiv."},{"key":"ref_16","unstructured":"Gu, A., and Dao, T. (2024, January 7\u20139). Mamba: Linear-time sequence modeling with selective state spaces. Proceedings of the First Conference on Language Modeling, Philadelphia, PA, USA."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B.L., Xie, X., Petrov, I.A., Sminchisescu, C., Theobalt, C., and Pons-Moll, G. (2022, January 18\u201324). Behave: Dataset and method for tracking human object interactions. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Huang, Y., Taheri, O., Black, M.J., and Tzionas, D. (2022, January 27\u201330). InterCap: Joint markerless 3D tracking of humans and objects in interaction. Proceedings of the DAGM German Conference on Pattern Recognition, Konstanz, Germany.","DOI":"10.1007\/978-3-031-16788-1_18"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A.A., Tzionas, D., and Black, M.J. (2019, January 15\u201320). Expressive body capture: 3d hands, face, and body from a single image. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Omran, M., Lassner, C., Pons-Moll, G., Gehler, P., and Schiele, B. (2018, January 5\u20138). Neural body fitting: Unifying deep learning and model based human pose and shape estimation. Proceedings of the 2018 International Conference on 3D Vision (3DV), Verona, Italy.","DOI":"10.1109\/3DV.2018.00062"},{"key":"ref_21","unstructured":"Yang, Y., Dong, L., Wang, W., Zhong, Z., and Sun, X. (2025). Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., and Black, M.J. (2023). SMPL: A skinned multi-person linear model. Seminal Graphics Papers: Pushing the Boundaries, Volume 2, ACM.","DOI":"10.1145\/3596711.3596800"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., and Malik, J. (2018, January 18\u201323). End-to-end recovery of human shape and pose. Proceedings of the IEEE Conference Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00744"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., and Daniilidis, K. (2018, January 18\u201323). Learning to estimate 3D human pose and shape from a single color image. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00055"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., and Liu, Z. (2021, January 10\u201317). Mesh graphormer. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., and Liu, Z. (2021, January 10\u201317). End-to-end human pose and mesh reconstruction with transformers. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Montreal, QC, Canada.","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Krishnan, R., Shalit, U., and Sontag, D. (2017, January 4\u20139). Structured inference networks for nonlinear state space models. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","DOI":"10.1609\/aaai.v31i1.10779"},{"key":"ref_28","unstructured":"Dao, T., and Gu, A. (2024). Transformers are ssms: Generalized models and efficient algorithms through structured state space duality. arXiv."},{"key":"ref_29","unstructured":"Lieber, O., Lenz, B., Bata, H., Cohen, G., Osin, J., Dalmedigos, I., Safahi, E., Meirom, S., Belinkov, Y., and Shalev-Shwartz, S. (2024). Jamba: A hybrid transformer-mamba language model. arXiv."},{"key":"ref_30","unstructured":"Waleffe, R., Byeon, W., Riach, D., Norick, B., Korthikanti, V., Dao, T., Gu, A., Hatamizadeh, A., Singh, S., and Narayanan, D. (2024). An empirical study of mamba-based language models. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1109\/TNNLS.2025.3610435","article-title":"Vision mamba: A comprehensive survey and taxonomy","volume":"37","author":"Liu","year":"2026","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhu, Y., Wang, D., Zhang, L., Chen, T., Wang, Z., and Ye, Z. (2024). A survey on visual mamba. Appl. Sci., 14.","DOI":"10.3390\/app14135683"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., and Kautz, J. (2025, January 10\u201317). Mambavision: A hybrid mamba-transformer vision backbone. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"ref_34","first-page":"81489","article-title":"Voxel mamba: Group-free state space models for point cloud based 3d object detection","volume":"37","author":"Zhang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Jin, X., Su, H., Liu, K., Ma, C., Wu, W., Hui, F., and Yan, J. (2025, January 10\u201317). UniMamba: Unified spatial-channel representation learning with group-efficient mamba for LiDAR-based 3D object detection. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.00139"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TMI.2025.3589797","article-title":"Segmamba-v2: Long-range sequential modeling mamba for general 3d medical image segmentation","volume":"45","author":"Xing","year":"2026","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"112701","DOI":"10.1016\/j.patcog.2025.112701","article-title":"A comprehensive analysis of Mamba for 3D volumetric medical image segmentation","volume":"173","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"21357","DOI":"10.1038\/s41598-025-06462-3","article-title":"CDA-mamba: Cross-directional attention mamba for enhanced 3D medical image segmentation","volume":"15","author":"Xu","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_39","unstructured":"Zhang, Z., Liu, A., Chen, Q., Chen, F., Reid, I., Hartley, R., Zhuang, B., and Tang, H. (2024). Infinimotion: Mamba boosts memory in transformer for arbitrary long motion generation. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"7079","DOI":"10.1109\/TIP.2025.3624601","article-title":"Text-controlled motion mamba: Text-instructed temporal grounding of human motion","volume":"34","author":"Wang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"ref_41","unstructured":"Jordan, K., Jin, Y., Boza, V., Jiacheng, Y., Cesista, F., Newhouse, L., and Bernstein, J. (2026, March 10). Muon: An Optimizer for Hidden Layers in Neural Networks. Available online: https:\/\/kellerjordan.github.io\/posts\/muon\/."}],"container-title":["Biomimetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-7673\/11\/3\/214\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T10:50:12Z","timestamp":1773744612000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-7673\/11\/3\/214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":41,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["biomimetics11030214"],"URL":"https:\/\/doi.org\/10.3390\/biomimetics11030214","relation":{},"ISSN":["2313-7673"],"issn-type":[{"value":"2313-7673","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]}}}