{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T17:16:03Z","timestamp":1778001363707,"version":"3.51.4"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62076153"],"award-info":[{"award-number":["No. 62076153"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.62176144"],"award-info":[{"award-number":["No.62176144"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the major fundamental research project of Shandong, China","award":["No. ZR2019ZD03"],"award-info":[{"award-number":["No. ZR2019ZD03"]}]},{"name":"the Taishan Scholar Project of Shandong, China","award":["No. ts20190924"],"award-info":[{"award-number":["No. ts20190924"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s00530-023-01222-7","type":"journal-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T02:02:13Z","timestamp":1705629733000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Locally controllable network based on visual\u2013linguistic relation alignment for text-to-image generation"],"prefix":"10.1007","volume":"30","author":[{"given":"Zaike","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaxiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongmei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boqun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,19]]},"reference":[{"key":"1222_CR1","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"1222_CR2","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"1222_CR3","doi-asserted-by":"crossref","unstructured":"Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang, X., He, X.:Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"1222_CR4","doi-asserted-by":"crossref","unstructured":"Ji, Z., Wang, H., Han, J., Pang, Y.: Saliency-guided attention network for image-sentence matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5754\u20135763 (2019)","DOI":"10.1109\/ICCV.2019.00585"},{"key":"1222_CR5","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"1222_CR6","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.1109\/TIP.2020.3026728","volume":"30","author":"H Tan","year":"2020","unstructured":"Tan, H., Liu, X., Liu, M., Yin, B., Li, X.: Kt-gan: Knowledge-transfer generative adversarial network for text-to-image synthesis. IEEE Trans. Image Process. 30, 1275\u20131290 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"1222_CR7","doi-asserted-by":"crossref","unstructured":"Dong, H., Yu, S., Wu, C., Guo, Y.: Semantic image synthesis via adversarial learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5706\u20135714 (2017)","DOI":"10.1109\/ICCV.2017.608"},{"key":"1222_CR8","first-page":"22020","volume":"33","author":"B Li","year":"2020","unstructured":"Li, B., Qi, X., Torr, P., Lukasiewicz, T.: Lightweight generative adversarial networks for text-guided image manipulation. Adv. Neural. Inf. Process. Syst. 33, 22020\u201322031 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1222_CR9","first-page":"42","volume":"31","author":"S Nam","year":"2018","unstructured":"Nam, S., Kim, Y., Kim, S.J.: Text-adaptive generative adversarial networks: manipulating images with natural language. Adv. Neural. Inf. Process. Syst. Neural Inf Process Syst 31, 42\u201351 (2018)","journal-title":"Adv. Neural. Inf. Process. Syst. Neural Inf Process Syst"},{"key":"1222_CR10","doi-asserted-by":"crossref","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.H.: Manigan: Text-guided image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7880\u20137889 (2020)","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"1222_CR11","first-page":"1104","volume-title":"Dynamic\u00a0Modality\u00a0Interaction Modeling\u00a0for\u00a0Image-Text\u00a0Retrieval","author":"L Qu","year":"2021","unstructured":"Qu, L., Liu, M., Wu, J., Gao, Z., Nie, L.: Dynamic\u00a0Modality\u00a0Interaction Modeling\u00a0for\u00a0Image-Text\u00a0Retrieval, pp. 1104\u20131113. Springer (2021)"},{"key":"1222_CR12","doi-asserted-by":"crossref","unstructured":"Lee, K.-H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"1222_CR13","first-page":"1047","volume-title":"Context-Aware\u00a0Multi-view Summarization\u00a0Network\u00a0for\u00a0Image-Text\u00a0Matching","author":"L Qu","year":"2020","unstructured":"Qu, L., Liu, M., Cao, D., Nie, L., Tian, Q.: Context-Aware\u00a0Multi-view Summarization\u00a0Network\u00a0for\u00a0Image-Text\u00a0Matching, pp. 1047\u20131055. Springer (2020)"},{"key":"1222_CR14","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yang, H., Qian, X., Ma, L., Lu, J., Li, B., Fan, X.: Position focused attention network for image-text matching. arXiv preprint arXiv:1907.09748 (2019)","DOI":"10.24963\/ijcai.2019\/526"},{"issue":"1","key":"1222_CR15","doi-asserted-by":"publisher","first-page":"2108","DOI":"10.1080\/09540091.2022.2098926","volume":"34","author":"H Huan","year":"2022","unstructured":"Huan, H., Guo, Z., Cai, T., He, Z.: A text classification method based on a convolutional and bidirectional long short-term memory model. Connect. Sci. 34(1), 2108\u20132124 (2022)","journal-title":"Connect. Sci."},{"key":"1222_CR16","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1222_CR17","first-page":"5098","volume":"32","author":"B Li","year":"2019","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.: Controllable text-to-image generation. Adv. Neural. Inf. Process. Syst. 32, 5098 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1222_CR18","doi-asserted-by":"crossref","unstructured":"Liu, C., Mao, Z., Zhang, T., Xie, H., Wang, B., Zhang, Y.: Graph structured network for image-text matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10921\u201310930 (2020)","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"1222_CR19","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltechucsd birds-200\u20132011 dataset (2011)"},{"key":"1222_CR20","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollar, 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, 13th edn., pp. 740\u2013755. Springer (2014)","edition":"13"},{"key":"1222_CR21","first-page":"42","volume":"29","author":"T Salimans","year":"2016","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. Adv. Neural. Inf. Process. Syst. Neural Inf Process Syst 29, 42 (2016)","journal-title":"Adv. Neural. Inf. Process. Syst. Neural Inf Process Syst"},{"key":"1222_CR22","unstructured":"Alec, R., Jong, W.K., Chris, H., Aditya, R., Gabriel, G., Sandhini, A., Girish, S., Amanda, A., Pamela, M., Jack, C., Gretchen, K., Ilya, S.: Learning transferable visual models from natural language supervision. arXiv:2103.00020 [cs] (2021)"},{"key":"1222_CR23","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01222-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-023-01222-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01222-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T06:15:28Z","timestamp":1707891328000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-023-01222-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,19]]},"references-count":23,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["1222"],"URL":"https:\/\/doi.org\/10.1007\/s00530-023-01222-7","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,19]]},"assertion":[{"value":"26 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2024","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 that there are no conflicts of interest regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"34"}}