{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T23:49:10Z","timestamp":1782863350569,"version":"3.54.5"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s00138-026-01829-6","type":"journal-article","created":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T13:50:51Z","timestamp":1778853051000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robonavguard: lightweight deformable obstacle segmentation and 3D visual grounding for indoor robot navigation"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0931-8985","authenticated-orcid":false,"given":"Zehan","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2018-6730","authenticated-orcid":false,"given":"Yaoyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henghua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,15]]},"reference":[{"key":"1829_CR1","doi-asserted-by":"crossref","unstructured":"Huang, X., Sanket, K., Ayyad, A., Naeini, F.B., Makris, D., Zweir, Y.: A neuromorphic dataset for object segmentation in indoor cluttered environment. arXiv preprint arXiv:2302.06301 (2023)","DOI":"10.1038\/s41597-024-02920-1"},{"key":"1829_CR2","doi-asserted-by":"crossref","unstructured":"Rafique, A.A., Jalal, A., Kim, K.: Statistical multi-objects segmentation for indoor\/outdoor scene detection and classification via depth images. In: 2020 17th International Bhurban Conference on Applied Sciences and Technology (IBCAST), pp. 271\u2013276 (2020). IEEE","DOI":"10.1109\/IBCAST47879.2020.9044576"},{"key":"1829_CR3","unstructured":"Proen\u00e7a, P.F., Simoes, P.: Taco: Trash annotations in context for litter detection. arXiv preprint arXiv:2003.06975 (2020)"},{"key":"1829_CR4","unstructured":"Keipour, A., Mousaei, M., Bandari, M., Schaal, S., Scherer, S.: Detection and physical interaction with deformable linear objects. arXiv preprint arXiv:2205.08041 (2022)"},{"key":"1829_CR5","doi-asserted-by":"crossref","unstructured":"Tan, Z., Yang, W., Zhang, Z.: Dos dataset: A novel indoor deformable object segmentation dataset for sweeping robots. In: International Conference on Neural Information Processing, pp. 352\u2013366 (2023). Springer","DOI":"10.1007\/978-981-99-8070-3_27"},{"key":"1829_CR6","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1829_CR7","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","volume":"129","author":"C Yu","year":"2021","unstructured":"Yu, C., Gao, C., Wang, J., Yu, G., Shen, C., Sang, N.: Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation. Int. J. Comput. Vision 129, 3051\u20133068 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"1829_CR8","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"1829_CR9","unstructured":"Wadekar, S.N., Chaurasia, A.: Mobilevitv3: Mobile-friendly vision transformer with simple and effective fusion of local, global and input features. arXiv preprint arXiv:2209.15159 (2022)"},{"key":"1829_CR10","unstructured":"Wang, P., Yang, A., Men, R., Lin, J., Bai, S., Li, Z., Ma, J., Zhou, C., Zhou, J., Yang, H.: Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: International Conference on Machine Learning, pp. 23318\u201323340 (2022). PMLR"},{"key":"1829_CR11","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Li, C., Yang, J., Su, H., Zhu, J., et al.: Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"1829_CR12","doi-asserted-by":"crossref","unstructured":"Yan, B., Jiang, Y., Wu, J., Wang, D., Luo, P., Yuan, Z., Lu, H.: Universal instance perception as object discovery and retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15325\u201315336 (2023)","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"1829_CR13","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: Scanrefer: 3d object localization in rgb-d scans using natural language. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XX, pp. 202\u2013221 (2020). Springer","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"1829_CR14","doi-asserted-by":"crossref","unstructured":"Wu, Y., Cheng, X., Zhang, R., Cheng, Z., Zhang, J.: Eda: Explicit text-decoupling and dense alignment for 3d visual grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19231\u201319242 (2023)","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"1829_CR15","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: Scannet: Richly-annotated 3d reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"1829_CR16","unstructured":"Couprie, C., Farabet, C., Najman, L., LeCun, Y.: Indoor semantic segmentation using depth information. arXiv preprint arXiv:1301.3572 (2013)"},{"key":"1829_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755 (2014). Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1829_CR18","doi-asserted-by":"crossref","unstructured":"Huang, S., Chen, Y., Jia, J., Wang, L.: Multi-view transformer for 3d visual grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15524\u201315533 (2022)","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"1829_CR19","doi-asserted-by":"crossref","unstructured":"Tan, Z., Yang, W., Wang, Z.: Reimagining 3d visual grounding: Instance segmentation and transformers for fragmented point cloud scenarios. In: Proceedings of the 5th ACM International Conference on Multimedia in Asia, pp. 1\u20137 (2023)","DOI":"10.1145\/3595916.3626405"},{"key":"1829_CR20","doi-asserted-by":"crossref","unstructured":"Hess, W., Kohler, D., Rapp, H., Andor, D.: Real-time loop closure in 2d lidar slam. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 1271\u20131278 (2016). IEEE","DOI":"10.1109\/ICRA.2016.7487258"},{"key":"1829_CR21","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"1829_CR22","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1829_CR23","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: Vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594 (2021). PMLR"},{"key":"1829_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1829_CR25","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1829_CR26","doi-asserted-by":"crossref","unstructured":"Sun, Z., Yu, H., Song, X., Liu, R., Yang, Y., Zhou, D.: Mobilebert: a compact task-agnostic bert for resource-limited devices. arXiv preprint arXiv:2004.02984 (2020)","DOI":"10.18653\/v1\/2020.acl-main.195"},{"issue":"11","key":"1829_CR27","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/34.888718","volume":"22","author":"Z Zhang","year":"2000","unstructured":"Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1330\u20131334 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1829_CR28","doi-asserted-by":"publisher","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.544","DOI":"10.1109\/CVPR.2017.544"},{"key":"1829_CR29","doi-asserted-by":"crossref","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, pp. 248\u2013255 (2009). Ieee","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1829_CR30","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6399\u20136408 (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"1829_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1829_CR32","doi-asserted-by":"crossref","unstructured":"Yu, W., Luo, M., Zhou, P., Si, C., Zhou, Y., Wang, X., Feng, J., Yan, S.: Metaformer is actually what you need for vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10819\u201310829 (2022)","DOI":"10.1109\/CVPR52688.2022.01055"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01829-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-026-01829-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01829-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T22:54:11Z","timestamp":1782860051000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-026-01829-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,15]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["1829"],"URL":"https:\/\/doi.org\/10.1007\/s00138-026-01829-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7809650\/v1","asserted-by":"object"}]},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,15]]},"assertion":[{"value":"8 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2026","order":4,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"69"}}