{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:50:27Z","timestamp":1767340227817,"version":"3.37.3"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"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":["Vis Comput"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s00371-023-02850-w","type":"journal-article","created":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T07:02:55Z","timestamp":1682406175000},"page":"1311-1325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["AMNet: a new RGB-D instance segmentation network based on attention and multi-modality"],"prefix":"10.1007","volume":"40","author":[{"given":"Mingyang","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2212-7187","authenticated-orcid":false,"given":"Lihua","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Yuting","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Xiaoling","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Jianhua","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Sulan","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,25]]},"reference":[{"key":"2850_CR1","doi-asserted-by":"crossref","unstructured":"Romera-Paredes, B., Torr, P.H.S.: Recurrent instance segmentation. In: European Conference on Computer Vision. Springer (2016)","DOI":"10.1007\/978-3-319-46466-4_19"},{"key":"2850_CR2","doi-asserted-by":"publisher","first-page":"e11373","DOI":"10.1002\/aps3.11373","volume":"8","author":"J Champ","year":"2020","unstructured":"Champ, J., et al.: Instance segmentation for the fine detection of crop and weed plants by precision agricultural robots. Appl. Plant Sci. 8, e11373 (2020)","journal-title":"Appl. Plant Sci."},{"key":"2850_CR3","doi-asserted-by":"publisher","first-page":"154435","DOI":"10.1109\/ACCESS.2021.3128536","volume":"9","author":"P Zhao","year":"2021","unstructured":"Zhao, P., et al.: Accurate fine-grained layout analysis for the historical Tibetan document based on the instance segmentation. IEEE Access 9, 154435\u2013154447 (2021)","journal-title":"IEEE Access"},{"key":"2850_CR4","doi-asserted-by":"publisher","first-page":"1759","DOI":"10.1007\/s00371-021-02103-8","volume":"38","author":"HT Li","year":"2022","unstructured":"Li, H.T., Todd, Z., Bielski, N., et al.: 3D lidar point-cloud projection operator and transfer machine learning for effective road surface features detection and segmentation. Vis. Comput. 38, 1759\u20131774 (2022)","journal-title":"Vis. Comput."},{"key":"2850_CR5","doi-asserted-by":"crossref","unstructured":"Ma, D., Gausemeier, J., Fan, X., Grafe, M.: Virtual reality & augmented reality in industry. Springer (2011)","DOI":"10.1007\/978-3-642-17376-9"},{"key":"2850_CR6","doi-asserted-by":"publisher","first-page":"989","DOI":"10.1007\/s00371-019-01713-7","volume":"36","author":"S Lamba","year":"2020","unstructured":"Lamba, S., Nain, N.: Segmentation of crowd flow by trajectory clustering in active contours. Vis. Comput. 36, 989\u20131000 (2020)","journal-title":"Vis. Comput."},{"key":"2850_CR7","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s00371-021-02315-y","volume":"39","author":"X Qian","year":"2023","unstructured":"Qian, X., Quan, H., Wu, M.: PRNet: polar regression network for medical image segmentation. Vis. Comput. 39, 87\u201398 (2023)","journal-title":"Vis. Comput."},{"key":"2850_CR8","unstructured":"Couprie, C., Farabet, C., Najman, L., LeCun, Y.: Indoor semantic segmentation using depth information. In: 1st International Conference on Learning Representations. ICLR (2013)"},{"key":"2850_CR9","doi-asserted-by":"crossref","unstructured":"Hazirbas, C., Ma, L., Domokos, C., Cremers, D.: Fusenet: Incorporating depth into semantic segmentation via fusion-based cnn architecture. In: Asian Conference on Computer Vision. Springer (2016)","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"2850_CR10","first-page":"1561","volume":"35","author":"XD Zhang","year":"2020","unstructured":"Zhang, X.D., Wang, Y.T., Fan, Z.G., et al.: RGB-D multi-class instance segmentation based on double pyramid feature fusion model. Control Decis. 35, 1561\u20131568 (2020). ((in Chinese))","journal-title":"Control Decis."},{"key":"2850_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.472"},{"key":"2850_CR12","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"2850_CR13","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 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2850_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"2850_CR15","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"2850_CR16","doi-asserted-by":"crossref","unstructured":"Fang, H.-S., Sun, J., Wang, R., Gou, M., Li, Y.-L., Lu, C.: Instaboost: Boosting instance segmentation via probability map guided copy-pasting. Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00077"},{"key":"2850_CR17","doi-asserted-by":"crossref","unstructured":"Bai, M., Urtasun, R.: Deep watershed transform for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.305"},{"key":"2850_CR18","doi-asserted-by":"crossref","unstructured":"Liu, S., Jia, J., Fidler, S., Urtasun, R.: SGN: Sequential grouping networks for instance segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.378"},{"key":"2850_CR19","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: Yolact: Real-time instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00925"},{"key":"2850_CR20","doi-asserted-by":"crossref","unstructured":"Wang, X., Kong, T., Shen, C., Jiang, Y., Li, L.: Solo: Segmenting objects by locations. In: European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"2850_CR21","first-page":"17721","volume":"33","author":"X Wang","year":"2020","unstructured":"Wang, X., Zhang, R., Kong, T., Li, L., Shen, C.: Solov2: Dynamic and fast instance segmentation. Adv. Neural Inf. Process. Syst. 33, 17721\u201317732 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2850_CR22","doi-asserted-by":"crossref","unstructured":"Neubeck, A., Van Gool, L.: Efficient non-maximum suppression. In: 18th International Conference on Pattern Recognition (ICPR\u201906). IEEE (2006)","DOI":"10.1109\/ICPR.2006.479"},{"key":"2850_CR23","unstructured":"Fang, Y., Yang, S., Wang, X., Li, Y., Fang, C., Shan, Y., Feng, B., Liu, W.: Queryinst: parallelly supervised mask query for instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)"},{"key":"2850_CR24","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 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2850_CR25","unstructured":"Jiang, J., Zheng, L., Luo, F., Zhang, Z.: Rednet: Residual encoder-decoder network for indoor RGB-D semantic segmentation. arXiv preprint arXiv:1806.01054 (2018)"},{"key":"2850_CR26","unstructured":"Park, S.-J., Hong, K.-S., Lee, S.: Rdfnet: RGB-D multi-level residual feature fusion for indoor semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (2017)"},{"key":"2850_CR27","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1109\/MIS.2020.2999462","volume":"36","author":"W Zhou","year":"2020","unstructured":"Zhou, W., Yuan, J., Lei, J., Luo, T.: TSNet: three-stream self-attention network for RGB-D indoor semantic segmentation. IEEE Intell. Syst. 36, 73\u201378 (2020)","journal-title":"IEEE Intell. Syst."},{"key":"2850_CR28","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 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2850_CR29","doi-asserted-by":"crossref","unstructured":"Gupta, S., Girshick, R., Arbelaez, P., Malik, J.: Learning rich features from RGB-D images for object detection and segmentation. In: European Conference on Computer Vision. Springer (2014)","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"2850_CR30","doi-asserted-by":"publisher","unstructured":"Shao, L., Tian, Y., Bohg, J.: ClusterNet: 3D Instance Segmentation in RGB-D Images. https:\/\/doi.org\/10.48550\/arXiv.1807.08894 (2018)","DOI":"10.48550\/arXiv.1807.08894"},{"key":"2850_CR31","doi-asserted-by":"crossref","unstructured":"\u00d6rnek, E. et al.: SupeRGB-D: Zero-shot Instance Segmentation in Cluttered Indoor Environments. arXiv preprint arXiv:2212.11922 (2022)","DOI":"10.1109\/LRA.2023.3271527"},{"key":"2850_CR32","doi-asserted-by":"publisher","unstructured":"Xiang, Y., et al. : Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation. https:\/\/doi.org\/10.48550\/arXiv.2007.15157, (2020)","DOI":"10.48550\/arXiv.2007.15157"},{"key":"2850_CR33","doi-asserted-by":"publisher","unstructured":"Xie, C., et al.: Unseen Object Instance Segmentation for Robotic Environments. https:\/\/doi.org\/10.48550\/arXiv.2007.08073 (2020)","DOI":"10.48550\/arXiv.2007.08073"},{"key":"2850_CR34","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2850_CR35","doi-asserted-by":"crossref","unstructured":"Hu, X., Yang, K., Fei, L., Wang, K.: Acnet: Attention based network to exploit complementary features for rgbd semantic segmentation. In: 2019 IEEE International Conference on Image Processing (ICIP). IEEE (2019)","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"2850_CR36","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1109\/TMRB.2020.3009527","volume":"2","author":"W Shi","year":"2020","unstructured":"Shi, W., Zhu, D., Zhang, G., Xu, J., Wang, X., Chen, L., Li, J., Zhang, X.: Multilevel cross-aware RGBD indoor semantic segmentation for bionic binocular robot. IEEE Trans. Med. Robot. Bionics 2, 382\u2013390 (2020)","journal-title":"IEEE Trans. Med. Robot. Bionics"},{"key":"2850_CR37","unstructured":"Li, H., Xiong, P., An, J., Wang, L.: Pyramid attention network for semantic segmentation. arXiv preprint arXiv:1805.10180 (2018)"},{"key":"2850_CR38","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Learning a discriminative feature network for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00199"},{"key":"2850_CR39","unstructured":"Deng, L., Yang, M., Li, T., He, Y., Wang, C.: RFBNet: deep multimodal networks with residual fusion blocks for RGB-D semantic segmentation. arXiv preprint arXiv:1907.00135 (2019)"},{"key":"2850_CR40","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. ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2850_CR41","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: European Conference on Computer Vision. Springer (2012)","DOI":"10.1007\/978-3-642-33715-4_54"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02850-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-02850-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02850-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T04:05:17Z","timestamp":1729310717000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-02850-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,25]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["2850"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-02850-w","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2023,4,25]]},"assertion":[{"value":"13 March 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2023","order":2,"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"}}]}}