{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:07:22Z","timestamp":1742998042781,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781032"},{"type":"electronic","value":"9783031781049"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-78104-9_14","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:44:09Z","timestamp":1733089449000},"page":"198-212","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Adapter on Pre-trained Visual Feature Reliance in\u00a0Medical Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Aakansha","family":"Mishra","sequence":"first","affiliation":[]},{"given":"Prateek","family":"Keserwani","sequence":"additional","affiliation":[]},{"given":"Vikram N.","family":"Rajendiran","sequence":"additional","affiliation":[]},{"given":"Ashok K.","family":"Senapati","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"14_CR1","unstructured":"Abacha, A.B., Gayen, S., Lau, J.J., Rajaraman, S., Demner-Fushman, D.: NLM at imageclef 2018 visual question answering in the medical domain. In: CLEF (Working Notes) (2018)"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"14_CR3","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1007\/s10462-019-09766-9","volume":"53","author":"KR Bhatele","year":"2020","unstructured":"Bhatele, K.R., Bhadauria, S.S.: Brain structural disorders detection and classification approaches: a review. Artif. Intell. Rev. 53, 3349\u20133401 (2020)","journal-title":"Artif. Intell. Rev."},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"14_CR5","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1007\/978-3-031-16443-9_65","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Z Chen","year":"2022","unstructured":"Chen, Z., et al.: Multi-modal masked autoencoders for medical vision-and-language pre-training. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13435, pp. 679\u2013689. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16443-9_65"},{"key":"14_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":"14_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/978-3-030-87240-3_7","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"T Do","year":"2021","unstructured":"Do, T., Nguyen, B.X., Tjiputra, E., Tran, M., Tran, Q.D., Nguyen, A.: Multiple meta-model quantifying for medical visual question answering. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 64\u201374. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_7"},{"key":"14_CR8","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint arXiv:1606.01847 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"issue":"11","key":"14_CR10","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)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"14_CR11","unstructured":"He, J., Li, P., Liu, G., Zhao, Z., Zhong, S.: Pefomed: parameter efficient fine-tuning on multimodal large language models for medical visual question answering. arXiv preprint arXiv:2401.02797 (2024)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"He, X., et al.: Pathological visual question answering. arXiv preprint arXiv:2010.12435 (2020)","DOI":"10.36227\/techrxiv.13127537.v1"},{"issue":"8","key":"14_CR13","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"14_CR14","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"14_CR15","first-page":"1022","volume":"34","author":"R Karimi Mahabadi","year":"2021","unstructured":"Karimi Mahabadi, R., Henderson, J., Ruder, S.: Compacter: efficient low-rank hypercomplex adapter layers. Adv. Neural. Inf. Process. Syst. 34, 1022\u20131035 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"14_CR16","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":"14_CR17","doi-asserted-by":"crossref","unstructured":"Li, P., Liu, G., Tan, L., Liao, J., Zhong, S.: Self-supervised vision-language pretraining for medial visual question answering. In: IEEE 20th International Symposium on Biomedical Imaging, pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ISBI53787.2023.10230743"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: Medical visual question answering: a survey. Artif. Intell. Med. 102611 (2023)","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"14_CR19","doi-asserted-by":"crossref","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, pp. 1650\u20131654. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Parameter-efficient transfer learning for medical visual question answering. IEEE Trans. Emerg. Top. Comput. Intell. (2023)","DOI":"10.1109\/TETCI.2023.3311333"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., et\u00a0al.: Swin transformer V2: scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12009\u201312019 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"14_CR22","unstructured":"Mahabadi, R.K., Ruder, S., Dehghani, M., Henderson, J.: Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks. arXiv preprint arXiv:2106.04489 (2021)"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Mishra, A., Anand, A., Guha, P.: CQ-VQA: visual question answering on categorized questions. In: 2020 International Joint Conference on Neural Networks, pp.\u00a01\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9206913"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Mishra, A., Anand, A., Guha, P.: Multi-stage attention based visual question answering. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9407\u20139414. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413173"},{"issue":"1","key":"14_CR25","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/TAI.2022.3160418","volume":"4","author":"A Mishra","year":"2022","unstructured":"Mishra, A., Anand, A., Guha, P.: Dual attention and question categorization-based visual question answering. IEEE Trans. Artif. Intell. 4(1), 81\u201391 (2022)","journal-title":"IEEE Trans. Artif. Intell."},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Mishra, A., Anand, A., Guha, P.: Aggregated co-attention based visual question answering. In: Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing, pp. 1\u201310 (2023)","DOI":"10.1145\/3627631.3627659"},{"key":"14_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1007\/978-3-030-32251-9_57","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"BD Nguyen","year":"2019","unstructured":"Nguyen, B.D., Do, T.-T., Nguyen, B.X., Do, T., Tjiputra, E., Tran, Q.D.: Overcoming data limitation in medical visual question answering. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 522\u2013530. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32251-9_57"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"14_CR29","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR30","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":"14_CR31","doi-asserted-by":"crossref","unstructured":"Seyfi, G., Esme, E., Yilmaz, M., Kiran, M.S.: A literature review on deep learning algorithms for analysis of x-ray images. Int. J. Mach. Learn. Cybern. 1\u201317 (2023)","DOI":"10.1007\/s13042-023-01961-z"},{"key":"14_CR32","unstructured":"Shi, L., Liu, F., Rosen, M.P.: Deep multimodal learning for medical visual question answering. In: CLEF (working notes) (2019)"},{"key":"14_CR33","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"van Sonsbeek, T., Derakhshani, M.M., Najdenkoska, I., Snoek, C.G., Worring, M.: Open-ended medical visual question answering through prefix tuning of language models. arXiv preprint arXiv:2303.05977 (2023)","DOI":"10.1007\/978-3-031-43904-9_70"},{"key":"14_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"14_CR36","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR.2016.10"},{"key":"14_CR37","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1016\/j.neucom.2020.05.113","volume":"469","author":"W Yin","year":"2022","unstructured":"Yin, W., Li, L., Wu, F.X.: Deep learning for brain disorder diagnosis based on FMRI images. Neurocomputing 469, 332\u2013345 (2022)","journal-title":"Neurocomputing"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., Tao, D.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1821\u20131830 (2017)","DOI":"10.1109\/ICCV.2017.202"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, K., et al.: Multi-task paired masking with alignment modeling for medical vision-language pre-training. IEEE Trans. Multimedia (2023)","DOI":"10.1109\/TMM.2023.3325965"},{"key":"14_CR40","unstructured":"Zhang, X., et al.: PMC-VQA: visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415 (2023)"},{"key":"14_CR41","unstructured":"Zhou, S.K., Greenspan, H., Shen, D.: Deep Learning for Medical Image Analysis. Academic Press (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78104-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:28:51Z","timestamp":1733095731000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78104-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031781032","9783031781049"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78104-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 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":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}