{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T05:54:02Z","timestamp":1769838842007,"version":"3.49.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031720857","type":"print"},{"value":"9783031720864","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72086-4_28","type":"book-chapter","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T20:34:45Z","timestamp":1727987685000},"page":"295-305","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["GMoD: Graph-Driven Momentum Distillation Framework with\u00a0Active Perception of\u00a0Disease Severity for\u00a0Radiology Report Generation"],"prefix":"10.1007","author":[{"given":"ZhiPeng","family":"Xiang","sequence":"first","affiliation":[]},{"given":"ShaoGuo","family":"Cui","sequence":"additional","affiliation":[]},{"given":"CaoZhi","family":"Shang","sequence":"additional","affiliation":[]},{"given":"Jingfeng","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Liqiang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,4]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"28_CR2","unstructured":"Banerjee, S., Lavie, A.: Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. In: IEEvaluation@ACL (2005)"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T.H., Wan, X.: Generating radiology reports via memory-driven transformer. arXiv preprint arXiv:2010.16056 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: CVPR, (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Demner-Fushman, D., Kohli, M.D., Rosenman, M.B., Shooshan, S.E., Rodriguez, L., Antani, S., Thoma, G.R., McDonald, C.J.: Preparing a collection of radiology examinations for distribution and retrieval. Journal of the American Medical Informatics Association (2016)","DOI":"10.1093\/jamia\/ocv080"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhang, X., Zhang, S.: Kiut: Knowledge-injected u-transformer for radiology report generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Ji, J., Luo, Y., Sun, X., Chen, F., Luo, G., Wu, Y., Gao, Y., Ji, R.: Improving image captioning by leveraging intra-and inter-layer global representation in transformer network. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., Pollard, T.J., Greenbaum, N.R., Lungren, M.P., Deng, C.y., Peng, Y., Lu, Z., Mark, R.G., Berkowitz, S.J., Horng, S.: 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":"28_CR9","doi-asserted-by":"crossref","unstructured":"Li, C., Xu, H., Tian, J., Wang, W., Yan, M., Bi, B., Ye, J., Chen, H., Xu, G., Cao, Z., et\u00a0al.: mplug: Effective and efficient vision-language learning by cross-modal skip-connections. arXiv preprint arXiv:2205.12005 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"28_CR10","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning (2022)"},{"key":"28_CR11","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems (2021)"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Li, M., Cai, W., Verspoor, K., Pan, S., Liang, X., Chang, X.: Cross-modal clinical graph transformer for ophthalmic report generation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.02000"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Li, M., Lin, B., Chen, Z., Lin, H., Liang, X., Chang, X.: Dynamic graph enhanced contrastive learning for chest x-ray report generation. In: CVPR, (2023)","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, B., Cheng, X., Zhu, Z., Li, H., Zou, Y.: Unify, align and refine: Multi-level semantic alignment for radiology report generation. In: CVPR, (2023)","DOI":"10.1109\/ICCV51070.2023.00268"},{"key":"28_CR15","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text summarization branches out (2004)"},{"key":"28_CR16","unstructured":"Liu, F., Ge, S., Zou, Y., Wu, X.: Competence-based multimodal curriculum learning for medical report generation. arXiv preprint arXiv:2206.14579 (2022)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Liu, F., Wu, X., Ge, S., Fan, W., Zou, Y.: Exploring and distilling posterior and prior knowledge for radiology report generation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Liu, F., Yin, C., Wu, X., Ge, S., Zou, Y., Zhang, P., Sun, X.: Contrastive attention for automatic chest x-ray report generation. arXiv preprint arXiv:2106.06965 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"28_CR19","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: Adaptive attention via a visual sentinel for image captioning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Ma, S., Han, Y.: Describing images by feeding lstm with structural words. In: ICME (2016)","DOI":"10.1109\/ICME.2016.7552883"},{"key":"28_CR22","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks. arXiv preprint arXiv:1412.6632 (2014)"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Pan, R., Ran, R., Hu, W., Zhang, W., Qin, Q., Cui, S.: S3-net: A self-supervised dual-stream network for radiology report generation. IEEE Journal of Biomedical and Health Informatics (2023)","DOI":"10.1109\/JBHI.2023.3345932"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Qin, H., Song, Y.: Reinforced cross-modal alignment for radiology report generation. In: ACL (2022)","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Shang, C., Cui, S., Li, T., Wang, X., Li, Y., Jiang, J.: Matnet: Exploiting multi-modal features for radiology report generation. IEEE Signal Processing Letters (2022)","DOI":"10.1109\/LSP.2022.3229844"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Song, Z., Zhou, X.: Exploring explicit and implicit visual relationships for image captioning. In: ICME (2021)","DOI":"10.1109\/ICME51207.2021.9428310"},{"key":"28_CR27","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems (2017)"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: Consensus-based image description evaluation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"28_CR29","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: A neural image caption generator. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Wang, J., Bhalerao, A., He, Y.: Cross-modal prototype driven network for radiology report generation. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Z., Tang, M., Wang, L., Li, X., Zhou, L.: A medical semantic-assisted transformer for radiographic report generation. In: MICCAI (2022)","DOI":"10.1007\/978-3-031-16437-8_63"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Xu, K., Wang, H., Tang, P.: Image captioning with deep lstm based on sequential residual. In: ICME (2017)","DOI":"10.1109\/ICME.2017.8019408"},{"key":"28_CR34","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. In: International conference on machine learning (2015)"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Yang, S., Wu, X., Ge, S., Zheng, Z., Zhou, S.K., Xiao, L.: Radiology report generation with a learned knowledge base and multi-modal alignment. Medical Image Analysis (2023)","DOI":"10.1016\/j.media.2023.102798"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Yang, S., Wu, X., Ge, S., Zhou, S.K., Xiao, L.: Knowledge matters: Chest radiology report generation with general and specific knowledge. Medical image analysis (2022)","DOI":"10.1016\/j.media.2022.102510"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"You, D., Liu, F., Ge, S., Xie, X., Zhang, J., Wu, X.: Aligntransformer: Hierarchical alignment of visual regions and disease tags for medical report generation. In: MICCAI (2021)","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"28_CR38","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sun, X., Luo, Y., Ji, J., Zhou, Y., Wu, Y., Huang, F., Ji, R.: Rstnet: Captioning with adaptive attention on visual and non-visual words. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, X., Xu, Z., Yu, Q., Yuille, A., Xu, D.: When radiology report generation meets knowledge graph. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6989"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72086-4_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T20:38:32Z","timestamp":1727987912000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72086-4_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720857","9783031720864"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72086-4_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"4 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"We declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}