{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T21:56:45Z","timestamp":1763416605340,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819530571","type":"print"},{"value":"9789819530588","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"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\/978-981-95-3058-8_17","type":"book-chapter","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T21:52:57Z","timestamp":1763416377000},"page":"195-208","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mask-Guided Visual Text Transformer for\u00a0Radiology Reports Representation Learning"],"prefix":"10.1007","author":[{"given":"Jiazheng","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyan","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"17_CR1","unstructured":"Ba, J., Caruana, R.: Do deep nets really need to be deep? In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"17_CR2","unstructured":"Cai, X., Liu, S., Han, J., Yang, L., Liu, Z., Liu, T.: Chestxraybert: a pretrained language model for chest radiology report summarization. IEEE Trans. Multimedia (2021)"},{"key":"17_CR3","unstructured":"Chen, Y.: Convolutional neural network for sentence classification. Master\u2019s thesis, University of Waterloo (2015)"},{"key":"17_CR4","unstructured":"Chen, Y., et\u00a0al.: Mask-guided vision transformer (MG-VIT) for few-shot learning. arXiv preprint arXiv:2205.09995 (2022)"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Dai, F.Z., Cai, Z.: Glyph-aware embedding of Chinese characters. arXiv preprint arXiv:1709.00028 (2017)","DOI":"10.18653\/v1\/W17-4109"},{"key":"17_CR6","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":"17_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"17_CR8","unstructured":"Elwany, E., Moore, D., Oberoi, G.: Bert goes to law school: quantifying the competitive advantage of access to large legal corpora in contract understanding. arXiv preprint arXiv:1911.00473 (2019)"},{"key":"17_CR9","unstructured":"Hinton, G., Vinyals, O., Dean, J., et\u00a0al.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.025312(7) (2015)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Irvin, J., et al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"issue":"4","key":"17_CR11","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J., et al.: Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234\u20131240 (2020)","journal-title":"Bioinformatics"},{"key":"17_CR12","unstructured":"Li, Y., Zhang, K., Cao, J., Timofte, R., Van\u00a0Gool, L.: LocalViT: bringing locality to vision transformers. arXiv preprint arXiv:2104.05707 (2021)"},{"key":"17_CR13","unstructured":"Liu, P., Qiu, X., Huang, X.:. Recurrent neural network for text classification with multi-task learning. arXiv preprint arXiv:1605.05101 (2016)"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Luo, R., et al.: BioGPT: generative pre-trained transformer for biomedical text generation and mining. arXiv preprint arXiv:2210.10341 (2022)","DOI":"10.1093\/bib\/bbac409"},{"key":"17_CR15","unstructured":"Meng, Y., et al.: Glyph-vectors for Chinese character representations. arXiv preprint arXiv:1901.10125 (2019)"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Rawls, S., Cao, H., Kumar, S., Natarajan, P.: Combining convolutional neural networks and LSTMs for segmentation-free OCR. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 155\u2013160. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.34"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Ryskina, M., Gormley, M.R., Berg-Kirkpatrick, T.: Phonetic and visual priors for decipherment of informal romanization. arXiv preprint arXiv:2005.02517 (2020)","DOI":"10.18653\/v1\/2020.acl-main.737"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Salesky, E., Etter, D., Post, M.: Robust open-vocabulary translation from visual text representations. arXiv preprint arXiv:2104.08211 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.576"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017a)","DOI":"10.1109\/ICCV.2017.74"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017b)","DOI":"10.1109\/ICCV.2017.74"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Smit, A., Jain, S., Rajpurkar, P., Pareek, A., Ng, A.Y., Lungren, M.P.: ChexBert: combining automatic labelers and expert annotations for accurate radiology report labeling using Bert. arXiv preprint arXiv:2004.09167 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Sun, B., Yang, L., Dong, P., Zhang, W., Dong, J., Young, C.: Super characters: a conversion from sentiment classification to image classification. arXiv preprint arXiv:1810.07653 (2018)","DOI":"10.18653\/v1\/W18-6245"},{"key":"17_CR23","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"17_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Yuan, K., Guo, S., Liu, Z., Zhou, A., Yu, F., Wu, W.: Incorporating convolution designs into visual transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 579\u2013588 (2021)","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"17_CR26","unstructured":"Zhang, Z., Zhang, H., Zhao, L., Chen, T., Pfister, T.: Aggregating nested transformers. arXiv preprint arXiv:2105.12723 (2021)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3058-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T21:53:00Z","timestamp":1763416380000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3058-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"ISBN":["9789819530571","9789819530588"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3058-8_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"assertion":[{"value":"18 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","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":"4 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2025.scimeeting.cn\/en\/web\/index\/27434","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}