{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T01:14:59Z","timestamp":1783559699999,"version":"3.55.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"vor","delay-in-days":59,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Guangzhou Philosophy and Social Sciences \u201c14th Five-Year Plan\u201d Project","award":["No. 2025GZGJ374"],"award-info":[{"award-number":["No. 2025GZGJ374"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-52044-2","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T05:33:54Z","timestamp":1778477634000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MamWorld for open-world object detection with state space modeling and cross-modal fusion"],"prefix":"10.1038","volume":"16","author":[{"given":"Zongqiang","family":"Deng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongfei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,11]]},"reference":[{"key":"52044_CR1","doi-asserted-by":"crossref","unstructured":"Si, S. et al. Pointlmda: Local masked reconstruction and structural prediction for self-supervised domain adaptation on 3d point clouds. Information Fusion 103916 (2025).","DOI":"10.1016\/j.inffus.2025.103916"},{"key":"52044_CR2","doi-asserted-by":"crossref","unstructured":"Liu, Q. et al. Hybrideditdif: Text and exemplar guided image editing with diffusion models. Pattern Recognition 112510 (2025).","DOI":"10.1016\/j.patcog.2025.112510"},{"key":"52044_CR3","doi-asserted-by":"crossref","unstructured":"Minderer, M. et al. Simple open-vocabulary object detection. In European conference on computer vision, 728\u2013755 (Springer, 2022).","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"52044_CR4","doi-asserted-by":"crossref","unstructured":"Joseph, K., Khan, S., Khan, F.\u00a0S. & Balasubramanian, V.\u00a0N. Towards open world object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 5830\u20135840 (2021).","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"52044_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.113674","volume":"166","author":"E Ning","year":"2026","unstructured":"Ning, E., Miao, J., Xie, S., Ma, H. & Ning, X. Occluded person re-identification in multi-scenarios: A synergistic interaction framework with perception-aware optimization. Eng. Appl. Artif. Intell. 166, 113674 (2026).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"52044_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102467","volume":"79","author":"E Ning","year":"2023","unstructured":"Ning, E. et al. Pedestrian re-id based on feature consistency and contrast enhancement. Displays 79, 102467 (2023).","journal-title":"Displays"},{"key":"52044_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102863","volume":"117","author":"E Ning","year":"2025","unstructured":"Ning, E. et al. 3d-guided multi-feature semantic enhancement network for person re-id. Inform. Fusion 117, 102863 (2025).","journal-title":"Inform. Fusion"},{"key":"52044_CR8","doi-asserted-by":"crossref","unstructured":"Ning, E. et al. Disentangling identity from appearance: A semantic-hierarchical multi-level fusion framework for cloth-invariant person re-identification. Information Fusion 104346 (2026).","DOI":"10.1016\/j.inffus.2026.104346"},{"key":"52044_CR9","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","volume":"33","author":"Z Li","year":"2021","unstructured":"Li, Z., Liu, F., Yang, W., Peng, S. & Zhou, J. A survey of convolutional neural networks: Analysis, applications, and prospects. IEEE Trans Neural Netw Learn Syst 33, 6999\u20137019 (2021).","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"52044_CR10","doi-asserted-by":"publisher","first-page":"108374","DOI":"10.1109\/ACCESS.2022.3212767","volume":"10","author":"KT Chitty-Venkata","year":"2022","unstructured":"Chitty-Venkata, K. T., Emani, M., Vishwanath, V. & Somani, A. K. Neural architecture search for transformers: A survey. IEEE Access 10, 108374\u2013108412 (2022).","journal-title":"IEEE Access"},{"key":"52044_CR11","doi-asserted-by":"crossref","unstructured":"Li, S., Singh, H. & Grover, A. Mamba-nd: Selective state space modeling for multi-dimensional data. In European Conference on Computer Vision, 75\u201392 (Springer, 2024).","DOI":"10.1007\/978-3-031-73414-4_5"},{"key":"52044_CR12","unstructured":"Gu, X., Lin, T.-Y., Kuo, W. & Cui, Y. Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)."},{"key":"52044_CR13","doi-asserted-by":"crossref","unstructured":"Li, L.\u00a0H. et al. Grounded language-image pre-training. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 10965\u201310975 (2022).","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"52044_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, A. et al. Ow-detr: Open-world detection transformer. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 9235\u20139244 (2022).","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"52044_CR15","unstructured":"Wang, Z., Li, C., Xu, H. & Zhu, X. Mamba yolo: Ssms-based yolo for object detection. arXiv e-prints arXiv\u20132406 (2024)."},{"key":"52044_CR16","doi-asserted-by":"crossref","unstructured":"Cheng, T. et al. Yolo-world: Real-time open-vocabulary object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 16901\u201316911 (2024).","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"52044_CR17","doi-asserted-by":"crossref","unstructured":"Dong, W. et al. Fusion-mamba for cross-modality object detection. IEEE Transactions on Multimedia (2025).","DOI":"10.1109\/TMM.2025.3599020"},{"key":"52044_CR18","doi-asserted-by":"crossref","unstructured":"Liu, L. et al. Defmamba: Deformable visual state space model. In Proceedings of the Computer Vision and Pattern Recognition Conference, 8838\u20138847 (2025).","DOI":"10.1109\/CVPR52734.2025.00826"},{"key":"52044_CR19","unstructured":"Wang, Z., Li, C., Xu, H. & Zhu, X. Mamba yolo: Ssms-based yolo for object detection. arXiv preprint arXiv:2406.05835 (2024)."},{"key":"52044_CR20","doi-asserted-by":"crossref","unstructured":"Wang, H. et al. Mamba-yolo-world: Marrying yolo-world with mamba for open-vocabulary detection. arXiv preprint arXiv:2409.08513 (2024).","DOI":"10.1109\/ICASSP49660.2025.10888334"},{"key":"52044_CR21","unstructured":"Gu, A. & Dao, T. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)."},{"key":"52044_CR22","unstructured":"Liu, X., Zhang, C. & Zhang, L. Vision mamba: A comprehensive survey and taxonomy. arXiv preprint arXiv:2405.04404 (2024)."},{"key":"52044_CR23","doi-asserted-by":"crossref","unstructured":"Shao, S. et al. Objects365: A large-scale, high-quality dataset for object detection. In Proceedings of the IEEE\/CVF international conference on computer vision, 8430\u20138439 (2019).","DOI":"10.1109\/ICCV.2019.00852"},{"key":"52044_CR24","doi-asserted-by":"crossref","unstructured":"Kamath, A. et al. Mdetr-modulated detection for end-to-end multi-modal understanding. In Proceedings of the IEEE\/CVF international conference on computer vision, 1780\u20131790 (2021).","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"52044_CR25","unstructured":"Gu, X., Lin, T.-Y., Kuo, W. & Cui, Y. Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)."},{"key":"52044_CR26","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y. et al. Microsoft coco: Common objects in context. In Computer vision\u2013ECCV 2014: 13th European conference, zurich, Switzerland, September 6-12, 2014, proceedings, part v 13, 740\u2013755 (Springer, 2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"52044_CR27","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M. et al. The pascal visual object classes challenge: A retrospective. Int. J. Comput. Vision 111, 98\u2013136 (2015).","journal-title":"Int. J. Comput. Vision"},{"key":"52044_CR28","doi-asserted-by":"crossref","unstructured":"Gupta, A. et al. Ow-detr: Open-world detection transformer. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 9235\u20139244 (2022).","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"52044_CR29","doi-asserted-by":"publisher","first-page":"71078","DOI":"10.52202\/075280-3113","volume":"36","author":"C Ma","year":"2023","unstructured":"Ma, C., Jiang, Y., Wen, X., Yuan, Z. & Qi, X. Codet: Co-occurrence guided region-word alignment for open-vocabulary object detection. Adv. Neural. Inf. Process. Syst. 36, 71078\u201371094 (2023).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"52044_CR30","doi-asserted-by":"crossref","unstructured":"Ma, S. et al. Cat: Localization and identification cascade detection transformer for open-world object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 19681\u201319690 (2023).","DOI":"10.1109\/CVPR52729.2023.01885"},{"key":"52044_CR31","doi-asserted-by":"crossref","unstructured":"Zohar, O., Wang, K.-C. & Yeung, S. Prob: Probabilistic objectness for open world object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 11444\u201311453 (2023).","DOI":"10.1109\/CVPR52729.2023.01101"},{"key":"52044_CR32","doi-asserted-by":"crossref","unstructured":"Sun, Z., Li, J. & Mu, Y. Exploring orthogonality in open world object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 17302\u201317312 (2024).","DOI":"10.1109\/CVPR52733.2024.01638"},{"key":"52044_CR33","doi-asserted-by":"crossref","unstructured":"Pham, C., Vu, T. & Nguyen, K. Lp-ovod: Open-vocabulary object detection by linear probing. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 779\u2013788 (2024).","DOI":"10.1109\/WACV57701.2024.00083"},{"key":"52044_CR34","unstructured":"Ma, S. et al. Skdf: A simple knowledge distillation framework for distilling open-vocabulary knowledge to open-world object detector. arXiv preprint arXiv:2312.08653 (2023)."},{"key":"52044_CR35","unstructured":"Liu, L. et al. Yolo-uniow: Efficient universal open-world object detection. arXiv preprint arXiv:2412.20645 (2024)."},{"key":"52044_CR36","doi-asserted-by":"publisher","first-page":"9125","DOI":"10.52202\/068431-0663","volume":"35","author":"L Yao","year":"2022","unstructured":"Yao, L. et al. Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection. Adv. Neural. Inf. Process. Syst. 35, 9125\u20139138 (2022).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"52044_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF international conference on computer vision, 10012\u201310022 (2021).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"52044_CR38","doi-asserted-by":"crossref","unstructured":"Li, L.\u00a0H. et al. Grounded language-image pre-training. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 10965\u201310975 (2022).","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"52044_CR39","doi-asserted-by":"crossref","unstructured":"Liu, S. et al. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In European Conference on Computer Vision, 38\u201355 (Springer, 2024).","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"52044_CR40","doi-asserted-by":"crossref","unstructured":"Kamath, A. et al. Mdetr-modulated detection for end-to-end multi-modal understanding. In Proceedings of the IEEE\/CVF international conference on computer vision, 1780\u20131790 (2021).","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"52044_CR41","doi-asserted-by":"crossref","unstructured":"Zhao, Y. et al. Detrs beat yolos on real-time object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 16965\u201316974 (2024).","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"52044_CR42","doi-asserted-by":"publisher","first-page":"4970","DOI":"10.3390\/electronics12244970","volume":"12","author":"Q Liu","year":"2023","unstructured":"Liu, Q., Liu, Y. & Lin, D. Revolutionizing target detection in intelligent traffic systems: Yolov8-snakevision. Electronics 12, 4970 (2023).","journal-title":"Electronics"},{"key":"52044_CR43","unstructured":"Dong, B., Huang, Z., Yang, G., Zhang, L. & Zuo, W. Mr-gdino: efficient open-world continual object detection. arXiv preprint arXiv:2412.15979 (2024)."},{"key":"52044_CR44","doi-asserted-by":"crossref","unstructured":"Zhong, Y. et al. Regionclip: Region-based language-image pretraining. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 16793\u201316803 (2022).","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"52044_CR45","doi-asserted-by":"crossref","unstructured":"Alhadidi, T., Jaber, A., Jaradat, S., Ashqar, H. & Elhenawy, M. Object detection using oriented window learning vision transformer: Roadway assets recognition. In International Conference on Intelligent Systems, Blockchain, and Communication Technologies, 506\u2013522 (Springer, 2024).","DOI":"10.1007\/978-3-031-82377-0_41"},{"key":"52044_CR46","doi-asserted-by":"publisher","first-page":"19547","DOI":"10.52202\/079017-0617","volume":"37","author":"A Madan","year":"2024","unstructured":"Madan, A., Peri, N., Kong, S. & Ramanan, D. Revisiting few-shot object detection with vision-language models. Adv. Neural. Inf. Process. Syst. 37, 19547\u201319560 (2024).","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52044-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52044-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52044-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:55:07Z","timestamp":1783558507000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52044-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,11]]},"references-count":46,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["52044"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-52044-2","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,11]]},"assertion":[{"value":"22 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 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":"21392"}}