{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:25:31Z","timestamp":1757629531054,"version":"3.44.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032045454","type":"print"},{"value":"9783032045461","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T00:00:00Z","timestamp":1757548800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T00:00:00Z","timestamp":1757548800000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-04546-1_51","type":"book-chapter","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T14:53:37Z","timestamp":1757516017000},"page":"630-642","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HeteroCap: Hierarchical Visual-Semantic Fusion with\u00a0Heterogeneous Graphs for\u00a0Image Captioning"],"prefix":"10.1007","author":[{"given":"Yuxi","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohua","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"51_CR1","unstructured":"A survey on heterogeneous graph embedding: methods, techniques, applications and sources (2021)"},{"key":"51_CR2","doi-asserted-by":"crossref","unstructured":"Multi-modal graph contrastive encoding for neural machine translation. Artif. Intell. 323, 103986 (2023)","DOI":"10.1016\/j.artint.2023.103986"},{"key":"51_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"51_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"51_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Y., Yang, X., Li, J.: Captioning transformer with scene graph guiding. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 2538\u20132542 (2021)","DOI":"10.1109\/ICIP42928.2021.9506193"},{"key":"51_CR6","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"51_CR7","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Bojar, O., et al. (eds.) Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 376\u2013380, Baltimore, Maryland, USA. Association for Computational Linguistics (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"51_CR8","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"51_CR9","unstructured":"Gao, C., Zhang, J., Xing, J.: Dynamic graph attention for cross-modal alignment. In: ICCV (2023)"},{"key":"51_CR10","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 (CVPR), pp. 770\u2013778. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"51_CR11","first-page":"4132","volume":"34","author":"H Hong","year":"2020","unstructured":"Hong, H., et al.: An attention-based graph neural network for heterogeneous structural learning. Proc. AAAI Conf. Artif. Intell. 34, 4132\u20134139 (2020)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"51_CR12","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.-Y.: Attention on attention for image captioning. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4633\u20134642 (2019D)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"51_CR13","doi-asserted-by":"publisher","first-page":"120698","DOI":"10.1016\/j.eswa.2023.120698","volume":"231","author":"J Jia","year":"2023","unstructured":"Jia, J., et al.: Image captioning based on scene graphs: a survey. Expert Syst. Appl. 231, 120698 (2023)","journal-title":"Expert Syst. Appl."},{"key":"51_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Pan, Y., Yao, T., Mei, T.: Comprehending and ordering semantics for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17990\u201317999 (2022)","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"51_CR15","unstructured":"Lin, C.-Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381, Barcelona, Spain. Association for Computational Linguistics (2004)"},{"key":"51_CR16","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10968\u201310977 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"51_CR17","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. ACL \u201902, pp. 311\u2013318, USA. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"issue":"2","key":"51_CR18","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1109\/TNNLS.2020.2979270","volume":"32","author":"G Ren","year":"2021","unstructured":"Ren, G., et al.: Scene graph generation with hierarchical context. IEEE Trans. Neural Netw. Learn. Syst. 32(2), 909\u2013915 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"51_CR19","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the 28th Conference on Neural Information Processing Systems (NeurIPS), pp. 91\u201399 (2015)"},{"key":"51_CR20","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: Cider: consensus-based image description evaluation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"51_CR21","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"51_CR22","doi-asserted-by":"crossref","unstructured":"Yang, X., Gao, C., Zhang, H., Cai, J.: Hierarchical scene graph encoder-decoder for image paragraph captioning. In: Proceedings of the 28th ACM International Conference on Multimedia, MM \u201920, pp. 4181\u20134189, New York, NY, USA. Association for Computing Machinery (2020)","DOI":"10.1145\/3394171.3413859"},{"key":"51_CR23","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10677\u201310686 (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"51_CR24","doi-asserted-by":"crossref","unstructured":"Zeng, P., Zhu, J., Song, J., Gao, L.: Progressive tree-structured prototype network for end-to-end image captioning. In: Proceedings of the 30th ACM International Conference on Multimedia, MM \u201922, pp. 5210\u20135218, New York, NY, USA. Association for Computing Machinery (2022)","DOI":"10.1145\/3503161.3548024"},{"key":"51_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sun, X., Luo, Y., Li, B., Zhang, Z.: RSTNET: captioning with adaptive attention on visual and non-visual words. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15465\u201315474. IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"51_CR26","doi-asserted-by":"publisher","first-page":"102210","DOI":"10.1016\/j.displa.2022.102210","volume":"74","author":"S Zhao","year":"2022","unstructured":"Zhao, S., Li, L., Peng, H.: Aligned visual semantic scene graph for image captioning. Displays 74, 102210 (2022)","journal-title":"Displays"},{"key":"51_CR27","doi-asserted-by":"publisher","first-page":"191603","DOI":"10.1109\/ACCESS.2024.3518777","volume":"12","author":"Y Zhao","year":"2024","unstructured":"Zhao, Y., Liu, H., Duan, H.: HGNN-GAMS: heterogeneous graph neural networks for graph attribute mining and semantic fusion. IEEE Access 12, 191603\u2013191611 (2024)","journal-title":"IEEE Access"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04546-1_51","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T14:53:48Z","timestamp":1757516028000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04546-1_51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,11]]},"ISBN":["9783032045454","9783032045461"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04546-1_51","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,11]]},"assertion":[{"value":"11 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}