{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T07:11:02Z","timestamp":1774681862184,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698905","type":"print"},{"value":"9789819698912","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\/978-981-96-9891-2_39","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T05:46:43Z","timestamp":1753422403000},"page":"467-479","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid CNN-Transformer Network for Fine-Grained Tongue Multi-Attribute Classification with Tongue Group Attribute Mask Training in Traditional Chinese Medicine Diagnosis"],"prefix":"10.1007","author":[{"given":"Jiawen","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feixiang","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fufeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinlei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linqiang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Rong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongrong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"39_CR1","unstructured":"BioHit: In: http:\/\/github.com\/BioHit\/TongueImageDataset (2014)"},{"key":"39_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2024.102953","volume":"87","author":"Q Chen","year":"2025","unstructured":"Chen, Q., et al.: A mixed-scale dynamic attention transformer for pediatric pneumonia diagnosis. Displays 87, 102953 (2025)","journal-title":"Displays"},{"key":"39_CR3","unstructured":"Cosmin Duta, I., Liu, L., Zhu, F., Shao, L.: Pyramidal convolution: rethinking convolutional neural networks for visual recognition. arXiv e-prints pp. arXiv\u20132006 (2020)"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. pp. 248\u2013255. Ieee (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"39_CR5","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":"39_CR6","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, pp. 770\u2013778(2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"39_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102110","volume":"118","author":"Y Hu","year":"2021","unstructured":"Hu, Y., et al.: Fully channel regional attention network for disease-location recognition with tongue images. Artif. Intell. Med. 118, 102110 (2021)","journal-title":"Artif. Intell. Med."},{"key":"39_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Lanchantin, J., Wang, T., Ordonez, V., Qi, Y.: General multi-label image classification with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16478\u201316488 (2021)","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"39_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1472-6882-12-127","volume":"12","author":"F Li","year":"2012","unstructured":"Li, F., Zhao, C., Xia, Z., Wang, Y., Zhou, X., Li, G.Z.: Computer-assisted lip di- agnosis on traditional chinese medicine using multi-class support vector machines. BMC Complement. Altern. Med. 12, 1\u201313 (2012)","journal-title":"BMC Complement. Altern. Med."},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Li, W., Cao, Z., Feng, J., Zhou, J., Lu, J.: Label2label: A language modeling framework for multi-attribute learning. In: European Conference on Computer Vision, pp. 562\u2013579. Springer (2022)","DOI":"10.1007\/978-3-031-19775-8_33"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Li, X., Yang, D., Wang, Y., Yang, S., Qi, L., Li, F., Gan, Z., Zhang, W.: Automatic tongue image segmentation for real-time remote diagnosis. In: 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 409\u2013414. IEEE (2019)","DOI":"10.1109\/BIBM47256.2019.8982947"},{"key":"39_CR14","unstructured":"Liu, S., Zhang, L., Yang, X., Su, H., Zhu, J.: Query2label: A simple transformer way to multi-label classification. arXiv preprint arXiv:2107.10834 (2021)"},{"issue":"2","key":"39_CR15","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1007\/s11263-024-02204-6","volume":"133","author":"Y Liu","year":"2025","unstructured":"Liu, Y., Wang, X., Zhu, M., Cao, Y., Huang, T., Shen, C.: Masked channel modeling for bootstrapping visual pre-training. Int. J. Comput. Vision 133(2), 760\u2013780 (2025)","journal-title":"Int. J. Comput. Vision"},{"issue":"3","key":"39_CR16","doi-asserted-by":"publisher","first-page":"653","DOI":"10.3390\/diagnostics12030653","volume":"12","author":"J Ni","year":"2022","unstructured":"Ni, J., Yan, Z., Jiang, J.: Tonguecaps: an improved capsule network model for multi-classification of tongue color. Diagnostics 12(3), 653 (2022)","journal-title":"Diagnostics"},{"key":"39_CR17","unstructured":"PolyU\/HIT: In: http:\/\/www.comp.polyu.edu.hk\/biometrics"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Ridnik, T., et al.: Asymmetric loss for multi-label classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 82\u201391(2021)","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Ridnik, T., Lawen, H., Noy, A., Ben Baruch, E., Sharir, G., Friedman, I.: Tresnet: High performance GPU-dedicated architecture. In: proceedings of the IEEE\/CVF winter conference on applications of computer vision. pp. 1400\u20131409 (2021)","DOI":"10.1109\/WACV48630.2021.00144"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Schick, T., Sch\u00fctze, H.: Exploiting cloze questions for few shot text classification and natural language inference. arXiv preprint arXiv:2001.07676 (2020)","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"39_CR21","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 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, Y., Mao, J., Huang, Z., Huang, C., Xu, W.: CNN-RNN: A uni- fied framework for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2285\u20132294 (2016)","DOI":"10.1109\/CVPR.2016.251"},{"key":"39_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jep.2021.114905","volume":"285","author":"X Wang","year":"2022","unstructured":"Wang, X., et al.: Constructing tongue coating recognition model using deep transfer learning to assist syndrome diagnosis and its potential in noninvasive ethnopharmacological evaluation. J. Ethnopharmacol. 285, 114905 (2022)","journal-title":"J. Ethnopharmacol."},{"issue":"16","key":"39_CR24","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6262","volume":"33","author":"H Weng","year":"2021","unstructured":"Weng, H., Li, L., Lei, H., Luo, Z., Li, C., Li, S.: A weakly supervised tooth-mark and crack detection method in tongue image. Concurr. Comput.: Pract. Exper. 33(16), e6262 (2021)","journal-title":"Concurr. Comput.: Pract. Exper."},{"issue":"22","key":"39_CR25","doi-asserted-by":"publisher","first-page":"4286","DOI":"10.3390\/math10224286","volume":"10","author":"B Yan","year":"2022","unstructured":"Yan, B., Zhang, S., Yang, Z., Su, H., Zheng, H.: Tongue segmentation and color classification using deep convolutional neural networks. Mathematics 10(22), 4286 (2022)","journal-title":"Mathematics"},{"key":"39_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102772","volume":"86","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Luo, L., Dou, Q., Heng, P.A.: Triplet attention and dual-pool contrastive learning for clinic-driven multi-label medical image classification. Med. Image Anal. 86, 102772 (2023)","journal-title":"Med. Image Anal."},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, F., Li, H., Ouyang, W., Yu, N., Wang, X.: Learning spatial regularization with image-level supervisions for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5513\u20135522 (2017)","DOI":"10.1109\/CVPR.2017.219"},{"key":"39_CR28","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"}],"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\/978-981-96-9891-2_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:04:42Z","timestamp":1774677882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9891-2_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698905","9789819698912"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9891-2_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":"26 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"}}]}}