{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:10:05Z","timestamp":1757617805882,"version":"3.44.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T00:00:00Z","timestamp":1744243200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T00:00:00Z","timestamp":1744243200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62203192"],"award-info":[{"award-number":["62203192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s00371-025-03897-7","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T01:09:00Z","timestamp":1744247340000},"page":"8761-8773","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GPT-ZSS: a unified zero-shot segmentation framework leveraging GPT-generated semantic embeddings and relationship alignment"],"prefix":"10.1007","volume":"41","author":[{"given":"Dan","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlong","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,10]]},"reference":[{"issue":"5","key":"3897_CR1","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.3390\/electronics12051199","volume":"12","author":"Y Yu","year":"2023","unstructured":"Yu, Y., Wang, C., Fu, Q., et al.: Techniques and challenges of image segmentation: a review. Electronics 12(5), 1199 (2023). https:\/\/doi.org\/10.3390\/electronics12051199","journal-title":"Electronics"},{"issue":"2","key":"3897_CR2","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1109\/TVCG.2018.2869326","volume":"26","author":"B Sheng","year":"2018","unstructured":"Sheng, B., Li, P., Jin, Y.X., et al.: Intrinsic image decomposition with step and drift shading separation. IEEE Trans. Visual Comput. Graphics 26(2), 1332\u20131346 (2018). https:\/\/doi.org\/10.1109\/TVCG.2018.2869326","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"issue":"2","key":"3897_CR3","doi-asserted-by":"publisher","first-page":"224","DOI":"10.54097\/rfa5x119","volume":"9","author":"C Zhang","year":"2024","unstructured":"Zhang, C., Lu, W., Wu, J., et al.: SegNet network architecture for deep learning image segmentation and its integrated applications and prospects. Acad. J. Sci. Technol. 9(2), 224\u2013229 (2024)","journal-title":"Acad. J. Sci. Technol."},{"key":"3897_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03570-5","author":"SG Ali","year":"2024","unstructured":"Ali, S.G., Wang, X., Li, P., et al.: EGDNet: an efficient glomerular detection network for multiple anomalous pathological feature in glomerulonephritis. The Vis. Comput. (2024). https:\/\/doi.org\/10.1007\/s00371-024-03570-5","journal-title":"The Vis. Comput."},{"key":"3897_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03139-8","author":"J Li","year":"2024","unstructured":"Li, J., Guan, Z., Wang, J., et al.: Integrated image-based deep learning and language models for primary diabetes care. Nat. Med. (2024). https:\/\/doi.org\/10.1038\/s41591-024-03139-8","journal-title":"Nat. Med."},{"key":"3897_CR6","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Huang, Z., Zhang, R., et al.: Zept: Zero-shot pan-tumor segmentation via query-disentangling and self-prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11386\u201311397 (2024).","DOI":"10.1109\/CVPR52733.2024.01082"},{"key":"3897_CR7","doi-asserted-by":"publisher","first-page":"8874","DOI":"10.1109\/TMM.2024.3383276","volume":"52","author":"C Wen","year":"2024","unstructured":"Wen, C., Huang, H., Ma, Y., et al.: Dual-guided frequency prototype network for few-shot semantic segmentation. IEEE Trans. Multimedia 52, 8874\u20138888 (2024)","journal-title":"IEEE Trans. Multimedia"},{"issue":"10","key":"3897_CR8","doi-asserted-by":"publisher","first-page":"12562","DOI":"10.1109\/TPAMI.2023.3285009","volume":"45","author":"S Sun","year":"2023","unstructured":"Sun, S., Zhi, S., Liao, Q., et al.: Unbiased scene graph generation via two-stage causal modeling. IEEE Trans. Pattern Anal. Mach. Intell. 45(10), 12562\u201312580 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"3897_CR9","doi-asserted-by":"publisher","first-page":"3216","DOI":"10.1109\/TVCG.2018.2866090","volume":"25","author":"B Sheng","year":"2018","unstructured":"Sheng, B., Li, P., Gao, C., et al.: Deep neural representation guided face sketch synthesis. IEEE Trans. Visual Comput. Graphics 25(12), 3216\u20133230 (2018). https:\/\/doi.org\/10.1109\/TVCG.2018.2866090","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"3897_CR10","first-page":"1","volume":"52","author":"J Fang","year":"2024","unstructured":"Fang, J., Yang, G., Han, A., et al.: Zero-shot learning via categorization-relevant disentanglement and discriminative samples synthesis. The Vis. Comput. 52, 1\u201313 (2024)","journal-title":"The Vis. Comput."},{"key":"3897_CR11","first-page":"2589","volume":"36","author":"B Blumenstiel","year":"2024","unstructured":"Blumenstiel, B., Jakubik, J., K\u00fchne, H., et al.: What a mess: Multi-domain evaluation of zero-shot semantic segmentation. Adv. Neural. Inf. Process. Syst. 36, 2589 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"3897_CR12","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., et al.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3897_CR13","doi-asserted-by":"crossref","unstructured":"He, S., Ding, H., Jiang, W.: Primitive generation and semantic-related alignment for universal zero-shot segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11238\u201311247 (2023).","DOI":"10.1109\/CVPR52729.2023.01081"},{"key":"3897_CR14","first-page":"5689","volume":"32","author":"M Bucher","year":"2019","unstructured":"Bucher, M., Vu, T.H., Cord, M., et al.: Zero-shot semantic segmentation. Adv. Neural. Inf. Process. Syst. 32, 5689 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3897_CR15","doi-asserted-by":"crossref","unstructured":"He, S., Ding, H., Jiang, W.: Semantic-promoted debiasing and background disambiguation for zero-shot instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19498\u201319507 (2023)","DOI":"10.1109\/CVPR52729.2023.01868"},{"key":"3897_CR16","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Wu, J., Qin, Y., et al.: Zero-shot instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 2593\u20132602 (2021)","DOI":"10.1109\/CVPR46437.2021.00262"},{"key":"3897_CR17","doi-asserted-by":"publisher","unstructured":"Demirel, B., Gokberk Cinbis, R., Ikizler-Cinbis, N.: Attributes2classname: A discriminative model for attribute-based unsupervised zero-shot learning. In: Proceedings of the IEEE international conference on computer vision, pp. 1232\u20131241 (2017). https:\/\/doi.org\/10.48550\/arXiv.1705.01734","DOI":"10.48550\/arXiv.1705.01734"},{"key":"3897_CR18","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.neunet.2023.08.023","volume":"167","author":"H Zhang","year":"2023","unstructured":"Zhang, H., Meng, X., Cao, W., et al.: Graph embedding-based multi-label Zero-shot Learning. Neural Netw. 167, 129\u2013140 (2023). https:\/\/doi.org\/10.1016\/j.neunet.2023.08.023","journal-title":"Neural Netw."},{"key":"3897_CR19","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp. 951\u2013958 (2009).","DOI":"10.1109\/CVPR.2009.5206594"},{"issue":"7","key":"3897_CR20","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1109\/TPAMI.2012.256","volume":"35","author":"WJ Scheirer","year":"2012","unstructured":"Scheirer, W.J., de Rezende, R.A., Sapkota, A., et al.: Toward open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1757\u20131772 (2012). https:\/\/doi.org\/10.1109\/TPAMI.2012.256","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3897_CR21","doi-asserted-by":"publisher","unstructured":"Zhao, S., Gao, C., Shao, Y., et al.: Gtnet: Generative transfer network for zero-shot object detection. In: Proceedings of the AAAI conference on artificial intelligence, 34(07): 12967\u201312974 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6996","DOI":"10.1609\/aaai.v34i07.6996"},{"key":"3897_CR22","first-page":"1","volume":"5","author":"J Fang","year":"2024","unstructured":"Fang, J., Yang, G., Han, A., et al.: Zero-shot learning via categorization-relevant disentanglement and discriminative samples synthesis. The Vis. Comput. 5, 1\u201313 (2024)","journal-title":"The Vis. Comput."},{"key":"3897_CR23","doi-asserted-by":"publisher","unstructured":"Zhou, Z., Lei, Y., Zhang, B., et al.: Zegclip: towards adapting clip for zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11175\u201311185 (2023). https:\/\/doi.org\/10.48550\/arXiv.221 2.03588","DOI":"10.48550\/arXiv"},{"key":"3897_CR24","doi-asserted-by":"publisher","unstructured":"Chen, J., Deguchi, D., Zhang, C., et al.: Generalizable Semantic Vision Query Generation for Zero-shot Panoptic and Semantic Segmentation. arxiv preprint, (2024). https:\/\/doi.org\/10.48550\/arXiv.2402.13697","DOI":"10.48550\/arXiv.2402.13697"},{"key":"3897_CR25","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G. S., et al.: Decoupling zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11583\u201311592 (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"3897_CR26","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1007\/s11280-017-0468-7","volume":"21","author":"A Krishnan","year":"2018","unstructured":"Krishnan, A., et al.: Leveraging semantic resources in diversified query expansion. World Wide Web 21, 1041\u20131067 (2018)","journal-title":"World Wide Web"},{"key":"3897_CR27","first-page":"69","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 69 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3897_CR28","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1016\/j.neucom.2021.05.090","volume":"456","author":"W Li","year":"2021","unstructured":"Li, W., Li, J., Li, J., et al.: A lightweight multi-scale channel attention network for image super-resolution. Neurocomputing 456, 327\u2013337 (2021). https:\/\/doi.org\/10.1016\/j.neucom.2021.05.090","journal-title":"Neurocomputing"},{"key":"3897_CR29","unstructured":"Li, Y., Swersky, K., Zemel, R.: Generative moment matching networks. In: International conference on machine learning. PMLR, pp. 1718\u20131727 (2015)"},{"key":"3897_CR30","doi-asserted-by":"crossref","unstructured":"Ren, Y., Luo, Y., Zhu, J.: Improving Generative Moment Matching Networks with Distribution Partition. In: Proceedings of the AAAI Conference on Artificial Intelligence. 35(11): 9403\u20139410 (2021)","DOI":"10.1609\/aaai.v35i11.17133"},{"key":"3897_CR31","doi-asserted-by":"crossref","unstructured":"Xian, Y., Choudhury, S., He, Y., et al.: Semantic projection network for zero-and few-label semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8256\u20138265 (2019)","DOI":"10.1109\/CVPR.2019.00845"},{"key":"3897_CR32","doi-asserted-by":"publisher","unstructured":"Gu, Z., Zhou, S., Niu, L., et al.: Context-aware feature generation for zero-shot semantic segmentation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1921\u20131929 (2020). https:\/\/doi.org\/10.1145\/3394171.3413593","DOI":"10.1145\/3394171.3413593"},{"key":"3897_CR33","doi-asserted-by":"publisher","unstructured":"Cheng, J., Nandi, S., Natarajan, P., et al.: Sign: Spatial-information incorporated generative network for generalized zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9556\u20139566 (2021). https:\/\/doi.org\/10.48550\/arXiv.2108.12517","DOI":"10.48550\/arXiv.2108.12517"},{"key":"3897_CR34","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., et al.: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. In: European Conference on Computer Vision. Cham: Springer Nature Switzerland, pp. 736\u2013753 (2022)","DOI":"10.1007\/978-3-031-19818-2_42"},{"issue":"4","key":"3897_CR35","first-page":"4051","volume":"45","author":"F Pourpanah","year":"2022","unstructured":"Pourpanah, F., Abdar, M., Luo, Y., et al.: A review of generalized zero-shot learning methods. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4051\u20134070 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"3897_CR36","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1016\/S2213-8587(24)00154-2","volume":"12","author":"B Sheng","year":"2024","unstructured":"Sheng, B., Pushpanathan, K., Guan, Z., et al.: Artificial intelligence for diabetes care: current and future prospects. Lancet Diabetes Endocrinol. 12(8), 569\u2013595 (2024). https:\/\/doi.org\/10.1016\/S2213-8587(24)00154-2","journal-title":"Lancet Diabetes Endocrinol."},{"key":"3897_CR37","doi-asserted-by":"publisher","unstructured":"Gu, Z., Zhou, S., Niu, L., et al.: Context-aware feature generation for zero-shot semantic segmentation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1921\u20131929 (2020). https:\/\/doi.org\/10.1145\/3394171.3413593.","DOI":"10.1145\/3394171.3413593"},{"key":"3897_CR38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3295772","author":"A Gupta","year":"2023","unstructured":"Gupta, A., Narayan, S., Khan, S., et al.: Generative multi-label zero-shot learning. IEEE Trans. Pattern Anal. Mach. Intell. (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3295772","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3897_CR39","unstructured":"Ni, M., Zhang, Y., Feng, K., et al.: Ref-diff: zero-shot referring image segmentation with generative models. arxiv preprint (2023)"},{"key":"3897_CR40","first-page":"35631","volume":"36","author":"S Jiao","year":"2023","unstructured":"Jiao, S., Wei, Y., Wang, Y., et al.: Learning mask-aware clip representations for zero-shot segmentation. Adv. Neural. Inf. Process. Syst. 36, 35631\u201335653 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"3","key":"3897_CR41","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1109\/TCSVT.2022.3208071","volume":"33","author":"GS Xie","year":"2022","unstructured":"Xie, G.S., Zhang, Z., Xiong, H., et al.: Towards zero-shot learning: a brief review and an attention-based embedding network. IEEE Trans. Circuits Syst. Video Technol. 33(3), 1181\u20131197 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2022.3208071","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3897_CR42","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G. S., et al.: Decoupling zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11583\u201311592 (2022)","DOI":"10.1109\/CVPR52688.2022.01129"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03897-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03897-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03897-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T10:51:01Z","timestamp":1757155861000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03897-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,10]]},"references-count":42,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["3897"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03897-7","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2025,4,10]]},"assertion":[{"value":"18 March 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2025","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}