{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T13:12:52Z","timestamp":1783948372461,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819697939","type":"print"},{"value":"9789819697946","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-9794-6_39","type":"book-chapter","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T06:12:59Z","timestamp":1752473579000},"page":"467-478","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VAMP: Visual Attribute-Guided Multi-dimensional Perception for Nasal Endoscopy Report Generation"],"prefix":"10.1007","author":[{"given":"Xinpan","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianuo","family":"Ju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liujie","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changhong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingzhu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaomin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenguang","family":"Gan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Lee, S., Liu, M., Kim, H., et al.: CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images. European Radiology, pp. 1\u201313 (2025)","DOI":"10.1007\/s00330-024-11339-6"},{"key":"39_CR2","unstructured":"Pelka, O., Kl\u00edmek, R., M\u00fcller, H., et al.: Overview of the ImageCLEFmed 2021 concept & caption prediction task. In: Proceedings of the CLEF 2021 Conference and Labs of the Evaluation Forum \u2013 Working Notes, pp. 21\u201324 (2021)"},{"issue":"1","key":"39_CR3","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.1038\/s41598-023-31223-5","volume":"13","author":"A Selivanov","year":"2023","unstructured":"Selivanov, A., Belousov, A., Nikolenko, S.I., et al.: Medical image captioning via generative pretrained transformers. Sci. Rep. 13(1), 4171 (2023)","journal-title":"Sci. Rep."},{"issue":"1","key":"39_CR4","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1186\/s12880-022-00827-0","volume":"22","author":"T Huang","year":"2022","unstructured":"Huang, T., Liu, W., Luo, D., et al.: Deep transfer learning to quantify pleural effusion severity in chest X-rays. BMC Med. Imag. 22(1), 100 (2022)","journal-title":"BMC Med. Imag."},{"key":"39_CR5","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.patrec.2023.12.022","volume":"178","author":"Z Zeng","year":"2024","unstructured":"Zeng, Z., Zhang, Y., Chen, J., et al.: Pyramid hybrid pooling quantization for efficient fine-grained image retrieval. Pattern Recogn. Lett. 178, 106\u2013114 (2024)","journal-title":"Pattern Recogn. Lett."},{"issue":"8","key":"39_CR6","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1109\/JAS.2022.105734","volume":"9","author":"Y Ming","year":"2022","unstructured":"Ming, Y., Zhao, Q., Wang, D., et al.: Visuals to text: a comprehensive review on automatic image captioning. IEEE\/CAA J. Automatica Sinica 9(8), 1339\u20131365 (2022)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"issue":"10","key":"39_CR7","doi-asserted-by":"publisher","first-page":"5719","DOI":"10.1007\/s00034-022-02050-2","volume":"41","author":"KR Suresh","year":"2022","unstructured":"Suresh, K.R., Jarapala, A., Sudeep, P.V.: Image captioning encoder\u2013decoder models using CNN-RNN architectures: a comparative study. Circ. Syst. Signal Process. 41(10), 5719\u20135742 (2022)","journal-title":"Circ. Syst. Signal Process."},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Luo, J., Zhang, Y., Xu, X., et al.: Semantic-conditional diffusion networks for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Hu, X., Wang, L., Xu, Y., et al.: Scaling up vision-language pre-training for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"39_CR10","unstructured":"Yang, A., Pan, J., Lin, J., et al.: Chinese CLIP: Contrastive vision-language pretraining in Chinese. arXiv preprint, arXiv:2211.01335 (2022)"},{"key":"39_CR11","doi-asserted-by":"publisher","first-page":"23716","DOI":"10.52202\/068431-1723","volume":"35","author":"J-B Alayrac","year":"2022","unstructured":"Alayrac, J.-B., Donahue, J., Luc, P., et al.: Flamingo: A visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"39_CR12","unstructured":"Xu, X., Li, Z., Chen, L., et al.: A survey on knowledge distillation of large language models. arXiv preprint, arXiv:2402.13116 (2024)"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Li, J., Su, T., Zhao, B., et al.: Ultrasound report generation with cross-modality feature alignment via unsupervised guidance. IEEE Trans. Med. Imag. (2024)","DOI":"10.1109\/TMI.2024.3424978"},{"key":"39_CR14","unstructured":"Chen, Z., Shen, Y., Song, Y., et al.: Cross-modal memory networks for radiology report generation. arXiv preprint, arXiv:2204.13258 (2022)"},{"key":"39_CR15","unstructured":"Lee, M., Min, J., Lee, W., et al.: Structured language generation model for robust structure prediction. arXiv preprint, arXiv:2402.08971 (2024)"},{"key":"39_CR16","unstructured":"Yu, J., Li, X., Koh, J. Y., et al.: Vector-quantized image modeling with improved VQGAN. arXiv preprint, arXiv:2110.04627 (2021)"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Xu, P., Shao, W., Zhang, K., et al.: LVLM-eHub: A comprehensive evaluation benchmark for large vision-language models. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3507000"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Pavlopoulos, J., Kougia, V., Androutsopoulos, I.: A survey on biomedical image captioning. In: Proceedings of the Second Workshop on Shortcomings in Vision and Language, pp. 26\u201336 (2019)","DOI":"10.18653\/v1\/W19-1803"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Johnson, A.E.W., Pollard, T.J., Greenbaum, N.R., et al.: MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv preprint, arXiv:1901.07042 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"39_CR20","unstructured":"Hu, Y., Zhang, L., Wang, Y., et al.: PromptCap: Prompt-guided task-aware image captioning. arXiv preprint, arXiv:2211.09699 (2022)"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Ramos, R., Wei, X., Jin, H., et al.: SmallCap: Lightweight image captioning prompted with retrieval augmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20432\u201320441 (2023)","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"39_CR22","first-page":"12910","volume":"34","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Wang, X., Xu, Z., et al.: When radiology report generation meets knowledge graph. Proc. AAAI Conf. Artif. Intell. 34, 12910\u201312917 (2020)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Qin, H., Song, Y.: Reinforced cross-modal alignment for radiology report generation. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 448\u2013458 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"39_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103377","volume":"99","author":"W Lang","year":"2025","unstructured":"Lang, W., Liu, Z., Zhang, Y.: DACG: dual attention and context guidance model for radiology report generation. Med. Image Anal. 99, 103377 (2025)","journal-title":"Med. Image Anal."},{"key":"39_CR25","doi-asserted-by":"crossref","unstructured":"Tanida, T., Matsumoto, Y., Lee, H., et al.: Interactive and explainable region-guided radiology report generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Lai, H., Zhao, W., Wang, J., et al.: Carzero: cross-attention alignment for radiology zero-shot classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01059"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9794-6_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T12:44:46Z","timestamp":1783946686000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9794-6_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819697939","9789819697946"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9794-6_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"15 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}