{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T03:14:39Z","timestamp":1774235679312,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Natural Science Foundation of Anhui Province","award":["2208085MF156"],"award-info":[{"award-number":["2208085MF156"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s00371-025-04172-5","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T10:31:36Z","timestamp":1757500296000},"page":"12565-12576","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing generalized zero-shot learning through semantic contrast and feature aggregation"],"prefix":"10.1007","volume":"41","author":[{"given":"Xiyu","family":"Yang","sequence":"first","affiliation":[]},{"given":"Fang","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Mengdao","family":"Xing","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,10]]},"reference":[{"issue":"6","key":"4172_CR1","first-page":"509","volume":"5","author":"M Wang","year":"2023","unstructured":"Wang, M., Meng, M., Liu, J., Wu, J.: Learning adequate alignment and interaction for cross-modal retrieval. Virt. Real. Intell. Hardw. 5(6), 509\u2013522 (2023)","journal-title":"Virt. Real. Intell. Hardw."},{"issue":"6","key":"4172_CR2","first-page":"471","volume":"5","author":"X Tian","year":"2023","unstructured":"Tian, X., Wu, Z., Cao, J., Chen, S., Dong, X.: Ilidviz: An incremental learning-based visual analysis system for network anomaly detection. Virt. Real. Intell. Hardw. 5(6), 471\u2013489 (2023)","journal-title":"Virt. Real. Intell. Hardw."},{"issue":"1","key":"4172_CR3","doi-asserted-by":"publisher","first-page":"2221","DOI":"10.1002\/cav.2221","volume":"35","author":"X Li","year":"2024","unstructured":"Li, X., Lu, J., Zhou, J., Liu, W., Zhang, K.: Multi-temporal scale aggregation refinement graph convolutional network for skeleton-based action recognition. Comput. Anim. Virtual Worlds 35(1), 2221 (2024)","journal-title":"Comput. Anim. Virtual Worlds"},{"issue":"3","key":"4172_CR4","doi-asserted-by":"publisher","first-page":"2268","DOI":"10.1002\/cav.2268","volume":"35","author":"Y Bao","year":"2024","unstructured":"Bao, Y., Liu, X., Qi, Y., Liu, R., Li, H.: Adaptive information fusion network for multi-modal personality recognition. Comput. Anim. Virtual Worlds 35(3), 2268 (2024)","journal-title":"Comput. Anim. Virtual Worlds"},{"issue":"3","key":"4172_CR5","doi-asserted-by":"publisher","first-page":"2248","DOI":"10.1002\/cav.2248","volume":"35","author":"W Zhao","year":"2024","unstructured":"Zhao, W., Zhu, J., Huang, J., Li, P., Sheng, B.: Gan-based multi-decomposition photo cartoonization. Comput. Anim. Virtual Worlds 35(3), 2248 (2024)","journal-title":"Comput. Anim. Virtual Worlds"},{"issue":"4","key":"4172_CR6","doi-asserted-by":"publisher","first-page":"1083","DOI":"10.1109\/TMI.2022.3223683","volume":"42","author":"R Liu","year":"2022","unstructured":"Liu, R., Wang, T., Li, H., Zhang, P., Li, J., Yang, X., Shen, D., Sheng, B.: Tmm-nets: Transferred multi-to mono-modal generation for lupus retinopathy diagnosis. IEEE Trans. Med. Imaging 42(4), 1083\u20131094 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"9","key":"4172_CR7","doi-asserted-by":"publisher","first-page":"5334","DOI":"10.1109\/TVCG.2024.3447351","volume":"31","author":"X Hu","year":"2024","unstructured":"Hu, X., Yang, C., Fang, F., Huang, J., Li, P., ShengB, B., Lee, T.-Y.: Msembgan: Multi-stitch embroidery synthesis via region-aware texture generation. IEEE Trans. Visual Comput. Graph. 31(9), 5334\u20135347 (2024)","journal-title":"IEEE Trans. Visual Comput. Graph."},{"key":"4172_CR8","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"4172_CR9","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1016\/j.neunet.2022.01.007","volume":"148","author":"Q Li","year":"2022","unstructured":"Li, Q., Hou, M., Lai, H., Yang, M.: Cross-modal distribution alignment embedding network for generalized zero-shot learning. Neural Netw. 148, 176\u2013182 (2022). https:\/\/doi.org\/10.1016\/j.neunet.2022.01.007","journal-title":"Neural Netw."},{"key":"4172_CR10","doi-asserted-by":"publisher","unstructured":"Jiang, H., Wang, R., Shan, S., Chen, X.: Transferable contrastive network for generalized zero-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9765\u20139774 (2019). https:\/\/doi.org\/10.48550\/arXiv.1908.05832","DOI":"10.48550\/arXiv.1908.05832"},{"key":"4172_CR11","doi-asserted-by":"publisher","unstructured":"Xian, Y., Sharma, S., Schiele, B., Akata, Z.: f-vaegan-d2: A feature generating framework for any-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10275\u201310284 (2019). https:\/\/doi.org\/10.48550\/arXiv.1903.10132","DOI":"10.48550\/arXiv.1903.10132"},{"key":"4172_CR12","doi-asserted-by":"publisher","unstructured":"Narayan, S., Gupta, A., Khan, F.S., Snoek, C.G., Shao, L.: Latent embedding feedback and discriminative features for zero-shot classification. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXII 16, pp. 479\u2013495 (2020). https:\/\/doi.org\/10.48550\/arXiv.2003.07833","DOI":"10.48550\/arXiv.2003.07833"},{"key":"4172_CR13","doi-asserted-by":"publisher","first-page":"4526","DOI":"10.1109\/TMM.2021.3119854","volume":"24","author":"S Deng","year":"2021","unstructured":"Deng, S., Xiang, G., Gao, Q., Xia, W., Gao, X.: Zero-shot learning based on quality-verifying adversarial network. IEEE Trans. Multim. 24, 4526\u20134537 (2021). https:\/\/doi.org\/10.1109\/TMM.2021.3119854","journal-title":"IEEE Trans. Multim."},{"issue":"9","key":"4172_CR14","doi-asserted-by":"publisher","first-page":"3087","DOI":"10.1007\/s00371-022-02539-6","volume":"38","author":"J Guan","year":"2022","unstructured":"Guan, J., Meng, M., Liang, T., Liu, J., Wu, J.: Dual-level contrastive learning network for generalized zero-shot learning. Vis. Comput. 38(9), 3087\u20133095 (2022). https:\/\/doi.org\/10.1007\/s00371-022-02539-6","journal-title":"Vis. Comput."},{"key":"4172_CR15","doi-asserted-by":"publisher","unstructured":"Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3174\u20133183 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.473","DOI":"10.1109\/CVPR.2017.473"},{"issue":"4","key":"4172_CR16","doi-asserted-by":"publisher","first-page":"4051","DOI":"10.1109\/TPAMI.2022.3191696","volume":"45","author":"F Pourpanah","year":"2022","unstructured":"Pourpanah, F., Abdar, M., Luo, Y., Zhou, X., Wang, R., Lim, C.P., Wang, X.-Z., Wu, Q.J.: A review of generalized zero-shot learning methods. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4051\u20134070 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2022.3191696","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4172_CR17","doi-asserted-by":"publisher","unstructured":"Xian, Y., Lorenz, T., Schiele, B., Akata, Z.: Feature generating networks for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5542\u20135551 (2018). https:\/\/doi.org\/10.48550\/arXiv.1712.00981","DOI":"10.48550\/arXiv.1712.00981"},{"key":"4172_CR18","doi-asserted-by":"publisher","unstructured":"Li, J., Jing, M., Lu, K., Ding, Z., Zhu, L., Huang, Z.: Leveraging the invariant side of generative zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7402\u20137411 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00758","DOI":"10.1109\/CVPR.2019.00758"},{"key":"4172_CR19","doi-asserted-by":"publisher","unstructured":"Verma, V.K., Arora, G., Mishra, A., Rai, P.: Generalized zero-shot learning via synthesized examples. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4281\u20134289 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00450","DOI":"10.1109\/CVPR.2018.00450"},{"key":"4172_CR20","doi-asserted-by":"publisher","unstructured":"Schonfeld, E., Ebrahimi, S., Sinha, S., Darrell, T., Akata, Z.: Generalized zero-and few-shot learning via aligned variational autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8247\u20138255 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00844","DOI":"10.1109\/CVPR.2019.00844"},{"key":"4172_CR21","doi-asserted-by":"publisher","unstructured":"Ma, P., Hu, X.: A variational autoencoder with deep embedding model for generalized zero-shot learning. In: Proceedings of the AAAI Conference on Artificial Intelligence 34, 11733\u201311740 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6844","DOI":"10.1609\/aaai.v34i07.6844"},{"key":"4172_CR22","doi-asserted-by":"publisher","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, pp. 951\u2013958 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206594","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"4172_CR23","doi-asserted-by":"publisher","unstructured":"Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for attribute-based classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 819\u2013826 (2013). https:\/\/doi.org\/10.1109\/CVPR.2013.111","DOI":"10.1109\/CVPR.2013.111"},{"key":"4172_CR24","unstructured":"Dinu, G., Lazaridou, A., Baroni, M.: Improving zero-shot learning by mitigating the hubness problem. arXiv preprint arXiv:1412.6568 (2014)"},{"key":"4172_CR25","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Ranzato, M., Mikolov, T. (2013): Devise: A deep visual-semantic embedding model. Advances in neural information processing systems 26"},{"key":"4172_CR26","doi-asserted-by":"publisher","unstructured":"Dinh, L., Krueger, D., Bengio, Y.: Nice: Non-linear independent components estimation. arXiv preprint arXiv:1410.8516 (2014) https:\/\/doi.org\/10.48550\/arXiv.1410.8516","DOI":"10.48550\/arXiv.1410.8516"},{"key":"4172_CR27","doi-asserted-by":"publisher","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real nvp. arXiv preprint arXiv:1605.08803 (2016) https:\/\/doi.org\/10.48550\/arXiv.1605.08803","DOI":"10.48550\/arXiv.1605.08803"},{"key":"4172_CR28","doi-asserted-by":"publisher","unstructured":"Shen, Y., Qin, J., Huang, L., Liu, L., Zhu, F., Shao, L.: Invertible zero-shot recognition flows. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVI 16, pp. 614\u2013631 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_36","DOI":"10.1007\/978-3-030-58517-4_36"},{"key":"4172_CR29","doi-asserted-by":"crossref","unstructured":"Han, Z., Fu, Z., Chen, S., Yang, J.: Contrastive embedding for generalized zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2371\u20132381 (2021)","DOI":"10.1109\/CVPR46437.2021.00240"},{"key":"4172_CR30","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607 (2020)"},{"key":"4172_CR31","doi-asserted-by":"publisher","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018) https:\/\/doi.org\/10.48550\/arXiv.1807.03748","DOI":"10.48550\/arXiv.1807.03748"},{"key":"4172_CR32","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., Krishnan, D.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661\u201318673 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4172_CR33","doi-asserted-by":"publisher","first-page":"2710","DOI":"10.1609\/aaai.v35i3.16375","volume":"35","author":"C Wang","year":"2021","unstructured":"Wang, C., Chen, X., Min, S., Sun, X., Li, H.: Task-independent knowledge makes for transferable representations for generalized zero-shot learning. In: Proceedings of the AAAI Conference on Artificial Intelligence 35, 2710\u20132718 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i3.16375","journal-title":"In: Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"4172_CR34","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. Advances in neural information processing systems 28 (2015)"},{"key":"4172_CR35","unstructured":"Kingma, D.P.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"4172_CR36","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199\u20131208 (2018)","DOI":"10.1109\/CVPR.2018.00131"},{"issue":"9","key":"4172_CR37","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.1109\/TPAMI.2018.2857768","volume":"41","author":"Y Xian","year":"2018","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning\u2014a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2251\u20132265 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2018.2857768","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4172_CR38","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"4172_CR39","doi-asserted-by":"publisher","unstructured":"Nilsback, M.-E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing, pp. 722\u2013729 (2008). https:\/\/doi.org\/10.1109\/ICVGIP.2008.47","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"4172_CR40","unstructured":"Romera-Paredes, B., Torr, P.: An embarrassingly simple approach to zero-shot learning. In: International Conference on Machine Learning, pp. 2152\u20132161 (2015)"},{"key":"4172_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Y., Guo, J., Cai, D., He, X.: Attribute attention for semantic disambiguation in zero-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6698\u20136707 (2019)","DOI":"10.1109\/ICCV.2019.00680"},{"key":"4172_CR42","doi-asserted-by":"crossref","unstructured":"Min, S., Yao, H., Xie, H., Wang, C., Zha, Z.-J., Zhang, Y.: Domain-aware visual bias eliminating for generalized zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12664\u201312673 (2020)","DOI":"10.1109\/CVPR42600.2020.01268"},{"key":"4172_CR43","doi-asserted-by":"crossref","unstructured":"Yu, Y., Ji, Z., Han, J., Zhang, Z.: Episode-based prototype generating network for zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14035\u201314044 (2020)","DOI":"10.1109\/CVPR42600.2020.01405"},{"key":"4172_CR44","doi-asserted-by":"crossref","unstructured":"Chen, S., Wang, W., Xia, B., Peng, Q., You, X., Zheng, F., Shao, L.: Free: Feature refinement for generalized zero-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 122\u2013131 (2021)","DOI":"10.1109\/ICCV48922.2021.00019"},{"key":"4172_CR45","doi-asserted-by":"publisher","unstructured":"Kim, J., Shim, K., Shim, B.: Semantic feature extraction for generalized zero-shot learning. In: Proceedings of the AAAI Conference on Artificial Intelligence 36, 1166\u20131173 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i1.20002","DOI":"10.1609\/aaai.v36i1.20002"},{"key":"4172_CR46","unstructured":"Chou, Y.-Y., Lin, H.-T., Liu, T.-L.: Adaptive and generative zero-shot learning. In: International Conference on Learning Representations (2020)"},{"key":"4172_CR47","doi-asserted-by":"crossref","unstructured":"Chen, Z., Luo, Y., Qiu, R., Wang, S., Huang, Z., Li, J., Zhang, Z.: Semantics disentangling for generalized zero-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8712\u20138720 (2021)","DOI":"10.1109\/ICCV48922.2021.00859"},{"key":"4172_CR48","doi-asserted-by":"crossref","unstructured":"Li, K., Min, M.R., Fu, Y.: Rethinking zero-shot learning: A conditional visual classification perspective. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3583\u20133592 (2019)","DOI":"10.1109\/ICCV.2019.00368"},{"key":"4172_CR49","doi-asserted-by":"publisher","unstructured":"Yang, F.-E., Lee, Y.-H., Lin, C.-C., Wang, Y.-C.F.: Semantics-guided intra-category knowledge transfer for generalized zero-shot learning. Int. J. Comput. Vision 131(6), 1331\u20131345 (2023). https:\/\/doi.org\/10.1007\/s11263-023-01767-0","DOI":"10.1007\/s11263-023-01767-0"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04172-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04172-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04172-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:16:12Z","timestamp":1763644572000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04172-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,10]]},"references-count":49,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["4172"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04172-5","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,10]]},"assertion":[{"value":"5 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2025","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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}