{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:39:19Z","timestamp":1791686359285,"version":"4.3.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":63,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["3332024081"],"award-info":[{"award-number":["3332024081"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Post-doctoral Fellowship Program of CPSF under Grant Number","award":["GZC20230312"],"award-info":[{"award-number":["GZC20230312"]}]},{"name":"China Postdoctoral Science Foundation under Grant Number","award":["2024M760264"],"award-info":[{"award-number":["2024M760264"]}]},{"name":"National Institute of Hospital Administration, National Health Commission of China","award":["NIHAYSZX2571"],"award-info":[{"award-number":["NIHAYSZX2571"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-50117-w","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T11:56:19Z","timestamp":1777463779000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["TG-OverLoCK for open-vocabulary detection with text-guided coarse-to-fine refinement"],"prefix":"10.1038","volume":"16","author":[{"given":"Yue","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongqiang","family":"Huo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengjie","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyi","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruijuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"issue":"8","key":"50117_CR1","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"J Zhang","year":"2024","unstructured":"Zhang, J. et al. Vision-language models for vision tasks: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 46 (8), 5625\u20135644 (2024).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"50117_CR2","doi-asserted-by":"publisher","first-page":"8954","DOI":"10.1109\/TPAMI.2024.3413013","volume":"46","author":"C Zhu","year":"2024","unstructured":"Zhu, C. & Chen, L. A survey on open-vocabulary detection and segmentation: Past, present, and future. IEEE Trans. Pattern Anal. Mach. Intell. 46 (12), 8954\u20138975 (2024).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"50117_CR3","doi-asserted-by":"crossref","unstructured":"He, K. et al. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"50117_CR4","doi-asserted-by":"crossref","unstructured":"Huang, G. et al. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4700\u20134708 (2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"50117_CR5","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. A ConvNet for the 2020s. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 11976\u201311986 (2022).","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"50117_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y. et al. Dynamic convolution: Attention over convolution kernels. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 11030\u201311039 (2020).","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"50117_CR7","doi-asserted-by":"crossref","unstructured":"Lou, M. & Yu, Y. OverLoCK an overview-first-look-closely-next ConvNet with context-mixing dynamic kernels. In Proceedings of the Computer Vision and Pattern Recognition Conference, 128\u2013138 (2025).","DOI":"10.1109\/CVPR52734.2025.00021"},{"issue":"5","key":"50117_CR8","doi-asserted-by":"publisher","first-page":"436","DOI":"10.3390\/biomimetics8050436","volume":"8","author":"C Zhang","year":"2023","unstructured":"Zhang, C. et al. Perceiving like a bat: Hierarchical 3D geometric\u2013semantic scene understanding inspired by a biomimetic mechanism. Biomimetics 8 (5), 436 (2023).","journal-title":"Biomimetics"},{"issue":"1","key":"50117_CR9","doi-asserted-by":"publisher","first-page":"2335100","DOI":"10.1080\/08839514.2024.2335100","volume":"38","author":"Z Li","year":"2024","unstructured":"Li, Z. et al. VBNet: A visually-aware biomimetic network for simulating the human eye\u2019s visual system. Appl. Artif. Intell. 38 (1), 2335100 (2024).","journal-title":"Appl. Artif. Intell."},{"key":"50117_CR10","unstructured":"Gu, X. et al. Open-vocabulary object detection via vision and language knowledge distillation. (2021). arXiv preprint arXiv:2104.13921."},{"key":"50117_CR11","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":"50117_CR12","doi-asserted-by":"crossref","unstructured":"Zhou, X. et al. Detecting twenty-thousand classes using image-level supervision. In European Conference on Computer Vision, 350\u2013368 (Springer Nature Switzerland, 2022).","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"50117_CR13","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":"50117_CR14","doi-asserted-by":"crossref","unstructured":"Fu, S. et al. LLMDet: Learning strong open-vocabulary object detectors under the supervision of large language models. (2025). arXiv preprint arXiv:2501.18954.","DOI":"10.1109\/CVPR52734.2025.01396"},{"key":"50117_CR15","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":"50117_CR16","doi-asserted-by":"crossref","unstructured":"Wang, A. et al. Yoloe: Real-time seeing anything. (2025). arXiv preprint arXiv:2503.07465.","DOI":"10.1109\/ICCV51701.2025.02280"},{"key":"50117_CR17","doi-asserted-by":"crossref","unstructured":"Minderer, M. et al. Simple open-vocabulary object detection. In European Conference on Computer Vision, 728\u2013755 (Springer Nature Switzerland, 2022).","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"50117_CR18","unstructured":"Wang, H. et al. Ov-dino: Unified open-vocabulary detection with language-aware selective fusion. (2024). arXiv preprint arXiv:2407.07844."},{"key":"50117_CR19","unstructured":"De Vries, H. et al. Modulating early visual processing by language. Adv. Neural. Inf. Process. Syst. 30. (2017)."},{"key":"50117_CR20","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. In Proceedings of the 38th International Conference on Machine Learning, vol. 139, 8748\u20138763 (PMLR, 2021)."},{"key":"50117_CR21","doi-asserted-by":"crossref","unstructured":"Zhu, J. et al. Transformers without normalization. In Proceedings of the Computer Vision and Pattern Recognition Conference, 14901\u201314911 (2025).","DOI":"10.1109\/CVPR52734.2025.01388"},{"key":"50117_CR22","doi-asserted-by":"crossref","unstructured":"Georgescu, M. I. et al. Multimodal multi-head convolutional attention with various kernel sizes for medical image super-resolution. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2195\u20132205 (2023).","DOI":"10.1109\/WACV56688.2023.00223"},{"key":"50117_CR23","unstructured":"Martins, A. & Astudillo, R. From softmax to sparsemax: A sparse model of attention and multi-label classification. In International Conference on Machine Learning, 1614\u20131623 (PMLR, 2016)."},{"key":"50117_CR24","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P. & Ross, B. Girshick. LVIS: A dataset for large vocabulary instance segmentation. In CVPR, 5356\u20135364 (2019).","DOI":"10.1109\/CVPR.2019.00550"},{"key":"50117_CR25","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\u201312, 2014, Proceedings, Part v 13, 740\u2013755 (Springer, 2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"50117_CR26","doi-asserted-by":"publisher","first-page":"36067","DOI":"10.52202\/068431-2614","volume":"35","author":"H Zhang","year":"2022","unstructured":"Zhang, H. et al. Glipv2: Unifying localization and vision-language understanding. Adv. Neural. Inf. Process. Syst. 35, 36067\u201336080 (2022).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"50117_CR27","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y. & Synnaeve, G. Ishan Misra, and Nicolas Carion. MDETR-modulated detection for end-to-end multi-modal understanding. In ICCV, 1760\u20131770 (2021).","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"50117_CR28","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 Nature Switzerland, 2024).","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"50117_CR29","doi-asserted-by":"publisher","unstructured":"Wang, C. et al. CF-YOLO for small target detection in drone imagery based on YOLOv11 algorithm. Nat. Commun. 16 (1). https:\/\/doi.org\/10.1038\/s41598-025-99634-0 (2025).","DOI":"10.1038\/s41598-025-99634-0"},{"key":"50117_CR30","doi-asserted-by":"publisher","unstructured":"Deng, J. et al. ImageNet: A large-scale hierarchical image database. Proc. IEEE Comput. Vis. Pattern Recognit. 2009, 248\u2013255 .https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"50117_CR31","doi-asserted-by":"crossref","unstructured":"Yue Liu, Y. et al. Vmamba: Visual state space model. Adv. Neural. Inf. Process. Syst. (2024).","DOI":"10.52202\/079017-3273"},{"key":"50117_CR32","doi-asserted-by":"publisher","first-page":"10353","DOI":"10.52202\/068431-0752","volume":"35","author":"Y Rao","year":"2022","unstructured":"Rao, Y. et al. Hornet: Efficient high-order spatial interactions with recursive gated convolutions. Adv. Neural. Inf. Process. Syst. 35, 10353\u201310366 (2022).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"50117_CR33","unstructured":"Shiwei Liu, T. et al. More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity. In International Conference on Learning Representations (2023)."},{"key":"50117_CR34","doi-asserted-by":"crossref","unstructured":"Hassani, A. et al. Neighborhood attention transformer. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6185\u20136194 (2023).","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"50117_CR35","doi-asserted-by":"crossref","unstructured":"Kim, D., Heo, B. & Han, D. Densenets reloaded: Paradigm shift beyond resnets and vits.In European Conference on Computer Vision (2024).","DOI":"10.1007\/978-3-031-72646-0_23"},{"key":"50117_CR36","unstructured":"Li, S. et al. Moganet: Multi-order gated aggregation network. In International Conference on Learning Representations (2023)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50117-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50117-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50117-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T22:41:25Z","timestamp":1782859285000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50117-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,29]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["50117"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-50117-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,29]]},"assertion":[{"value":"3 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 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"}},{"value":"The collection and use of the instruction-aware first-person-view grasping dataset were approved by the appropriate institutional ethics committee. All data used in this study were de-identified and do not contain personally identifiable information.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics statement"}}],"article-number":"19945"}}