{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:28:20Z","timestamp":1743042500752,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723520"},{"type":"electronic","value":"9783031723537"}],"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\/978-3-031-72353-7_24","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T15:04:02Z","timestamp":1726499042000},"page":"328-342","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-modal Multi-scale State Space Model for\u00a0Medical Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Qishen","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minjie","family":"Bian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxuan","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huahu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"24_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105049","volume":"85","author":"Z Chen","year":"2023","unstructured":"Chen, Z., Zou, B., Dai, Y., Zhu, C., Kong, G., Zhang, W.: Medical visual question answering with symmetric interaction attention and cross-modal gating. Biomed. Signal Process. Control 85, 105049 (2023)","journal-title":"Biomed. Signal Process. Control"},{"key":"24_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103018","volume":"91","author":"Z Chen","year":"2024","unstructured":"Chen, Z., et al.: Mapping medical image-text to a joint space via masked modeling. Med. Image Anal. 91, 103018 (2024)","journal-title":"Med. Image Anal."},{"key":"24_CR3","doi-asserted-by":"publisher","unstructured":"Gong, H., Chen, G., Liu, S., Yu, Y., Li, G.: Cross-modal self-attention with multi-task pre-training for medical visual question answering. In: Proceedings of the 2021 International Conference on Multimedia Retrieval, pp. 456\u2013460 (2021). https:\/\/doi.org\/10.1145\/3460426.3463584","DOI":"10.1145\/3460426.3463584"},{"issue":"11","key":"24_CR4","doi-asserted-by":"publisher","first-page":"3332","DOI":"10.1109\/TMI.2022.3185008","volume":"41","author":"H Gong","year":"2022","unstructured":"Gong, H., Chen, G., Mao, M., Li, Z., Li, G.: VQAMix: conditional triplet mixup for medical visual question answering. IEEE Trans. Med. Imaging 41(11), 3332\u20133343 (2022). https:\/\/doi.org\/10.1109\/TMI.2022.3185008","journal-title":"IEEE Trans. Med. Imaging"},{"key":"24_CR5","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"24_CR6","unstructured":"Gu, A., Goel, K., Re, C.: Efficiently modeling long sequences with structured state spaces. In: International Conference on Learning Representations (2021)"},{"key":"24_CR7","unstructured":"Gu, A., et al.: Combining recurrent, convolutional, and continuous-time models with linear state space layers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 572\u2013585 (2021)"},{"key":"24_CR8","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: International Conference on Machine Learning, pp. 1321\u20131330. PMLR (2017)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"He, X., et al.: Pan-Mamba: effective pan-sharpening with state space model. arXiv preprint arXiv:2402.12192 (2024)","DOI":"10.1016\/j.inffus.2024.102779"},{"key":"24_CR10","doi-asserted-by":"publisher","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"24_CR11","doi-asserted-by":"publisher","unstructured":"Khare, Y., Bagal, V., Mathew, M., Devi, A., Priyakumar, U.D., Jawahar, C.: MmBERT: multimodal BERT pretraining for improved medical VQA. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1033\u20131036. IEEE (2021). https:\/\/doi.org\/10.1109\/ISBI48211.2021.9434063","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"24_CR12","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"issue":"1","key":"24_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., Gayen, S., Ben Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data 5(1), 1\u201310 (2018)","journal-title":"Sci. Data"},{"key":"24_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-87196-3_20","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"B Liu","year":"2021","unstructured":"Liu, B., Zhan, L.-M., Wu, X.-M.: Contrastive pre-training and\u00a0representation distillation for\u00a0medical visual question answering based on\u00a0radiology images. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 210\u2013220. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_20"},{"key":"24_CR15","doi-asserted-by":"publisher","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: SLAKE: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1650\u20131654. IEEE (2021). https:\/\/doi.org\/10.1109\/ISBI48211.2021.9434010","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Parameter-efficient transfer learning for medical visual question answering. IEEE Trans. Emerging Top. Comput. Intell. (2023)","DOI":"10.1109\/TETCI.2023.3311333"},{"key":"24_CR17","unstructured":"Liu, Y., et al.: VMamba: visual state space model. arXiv preprint arXiv:2401.10166 (2024)"},{"key":"24_CR18","doi-asserted-by":"publisher","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"24_CR19","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"24_CR20","unstructured":"Ma, J., Li, F., Wang, B.: U-Mamba: enhancing long-range dependency for biomedical image segmentation. arXiv preprint arXiv:2401.04722 (2024)"},{"key":"24_CR21","unstructured":"Ruan, J., Xiang, S.: VM-UNet: vision mamba UNet for medical image segmentation. arXiv preprint arXiv:2402.02491 (2024)"},{"key":"24_CR22","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":"24_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121526","volume":"238","author":"C Shu","year":"2024","unstructured":"Shu, C., et al.: MITER: medical image-text joint adaptive pretraining with multi-level contrastive learning. Expert Syst. Appl. 238, 121526 (2024)","journal-title":"Expert Syst. Appl."},{"key":"24_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Wu, Z., Shu, X., Yan, S., Lu, Z.: FGCVQA: fine-grained cross-attention for medical VQA. In: 2023 IEEE International Conference on Image Processing (ICIP), pp. 975\u2013979. IEEE (2023)","DOI":"10.1109\/ICIP49359.2023.10222540"},{"key":"24_CR26","doi-asserted-by":"publisher","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21\u201329 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.10","DOI":"10.1109\/CVPR.2016.10"},{"key":"24_CR27","doi-asserted-by":"publisher","unstructured":"Yuan, Z., et al.: RAMM: retrieval-augmented biomedical visual question answering with multi-modal pre-training. arXiv e-prints, arXiv-2303 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.00534","DOI":"10.48550\/arXiv.2303.00534"},{"key":"24_CR28","doi-asserted-by":"publisher","unstructured":"Zhan, L.M., Liu, B., Fan, L., Chen, J., Wu, X.M.: Medical visual question answering via conditional reasoning. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2345\u20132354 (2020). https:\/\/doi.org\/10.1145\/3394171.3413761","DOI":"10.1145\/3394171.3413761"},{"key":"24_CR29","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72353-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T06:34:14Z","timestamp":1732775654000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72353-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723520","9783031723537"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72353-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","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":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}