{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T18:19:32Z","timestamp":1743099572389,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819770069"},{"type":"electronic","value":"9789819770076"}],"license":[{"start":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T00:00:00Z","timestamp":1726963200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T00:00:00Z","timestamp":1726963200000},"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\/978-981-97-7007-6_12","type":"book-chapter","created":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T18:01:43Z","timestamp":1726941703000},"page":"162-177","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Trilinear Distillation Learning and Question Feature Capturing for Medical Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Shaopei","family":"Long","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Buzhou","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fu Lee","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyong","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,22]]},"reference":[{"key":"12_CR1","unstructured":"Malinowski, M., Fritz, M.: Towards a visual turing challenge. arXiv preprint arXiv:1410.8027 (2014)"},{"key":"12_CR2","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems, pp. 1571\u20131581. NeurIPS, Montr\u00e9al, Canada (2018)"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Do, T., Do, T.T., Tran, H., Tjiputra, E., Tran, Q.D.: Compact trilinear interaction for visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 392\u2013401. Computer Vision Foundation\/IEEE (2019)","DOI":"10.1109\/ICCV.2019.00048"},{"key":"12_CR4","doi-asserted-by":"crossref","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)","DOI":"10.1038\/sdata.2018.251"},{"key":"12_CR5","doi-asserted-by":"crossref","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: Medical Image Computing and Computer Assisted Intervention -MICCAI 2019 - 22nd International Conference, Part IV (Lecture Notes in Computer Science, Vol. 11767), pp. 522\u2013530. Springer International Publishing (2019)","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"12_CR6","doi-asserted-by":"crossref","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., Cattin, P.C., Cotin, S., Padoy, N.,Speidel, S., Zheng, Y., Essert, C. (Eds.), Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021, pp. 64\u201374. Springer International Publishing (2021)","DOI":"10.1007\/978-3-030-87240-3_7"},{"key":"12_CR7","doi-asserted-by":"crossref","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 (MM20), pp. 2345\u20132354. ACM (2020)","DOI":"10.1145\/3394171.3413761"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., et al.: Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint arXiv:1606.01847 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Masci, J., Meier, U., Cire\u015fan, D., Schmidhuber, J.: Stacked convolutional auto-encoders for hierarchical feature extraction. In: Artificial Neural Networks and Machine Learning - ICANN 2011 - 21st International Conference on Artificial Neural Networks, Proceedings, Part I (Lecture Notes in Computer Science, Vol. 6791), pp. 52\u201359. Springer, Espoo, Finland (2011)","DOI":"10.1007\/978-3-642-21735-7_7"},{"key":"12_CR12","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. Advances in Neural Information Processing Systems, 31 (2018)"},{"issue":"1","key":"12_CR13","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1113\/jphysiol.1962.sp006837","volume":"160","author":"DH Hubel","year":"1962","unstructured":"Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cat\u2019s visual cortex. J. Physiol. 160(1), 106 (1962)","journal-title":"J. Physiol."},{"key":"12_CR14","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster RCNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems, NeurIPS, pp. 91\u201399. Montreal, Quebec, Canada (2015)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Graves, A., Graves, A.: Long short-term memory. Neural Computation. 9(8), 1735\u20131780 (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. In: Proceedings of SSST@EMNLP 2014, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, pp. 103\u2013111. Association for Computational Linguistics, Doha, Qatar (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"12_CR17","unstructured":"Chen, Z.W.X.L.L., Wang, L., Xie, Y.Q.X., Fowlkes, C.: Structured triplet learning with postag guided attention for visual question answering. In: WACV (2018)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Hu, H., Chao, W.L., Sha, F.: Learning answer embeddings for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pp. 5428\u20135436 (2018)","DOI":"10.1109\/CVPR.2018.00569"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Wu, X.M.: Contrastive pre-training and representation distillation for medical visual question answering based on radiology images. In: Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 210\u2013220 (2021)","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Gong, H., Chen, G., Liu, S., Yu, Y., Li, G.: Cross-modal self-attention with multitask pre-training for medical visual question answering. In: Proceedings of the 2021 International Conference on Multimedia Retrieval, pp. 456\u2013460 (2021)","DOI":"10.1145\/3460426.3463584"},{"key":"12_CR21","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, EMNLP, A meeting of SIGDAT, a Special Interest Group of the ACL, pp. 1532\u20131543. ACL, Doha, Qatar (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"12_CR22","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"12_CR23","unstructured":"Xiong, R., et al.: On layer normalization in the transformer architecture. In: International Conference on Machine Learning, pp. 10524\u201310533. PMLR (2020)"},{"key":"12_CR24","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":"12_CR25","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"12_CR26","unstructured":"Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"12_CR27","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Mo, D., et al.: SCLert: a span-based joint model for measurable quantitative information extraction from Chinese texts. IEEE Trans. Consumer Electron. 70(1), 3361\u20133371 (2024)","DOI":"10.1109\/TCE.2023.3327681"},{"issue":"1","key":"12_CR29","doi-asserted-by":"publisher","first-page":"2806","DOI":"10.1109\/TCE.2024.3363896","volume":"70","author":"G Chen","year":"2024","unstructured":"Chen, G., et al.: Improving open intent detection via triplet-contrastive learning and adaptive boundary. IEEE Trans. Consum. Electron. 70(1), 2806\u20132816 (2024)","journal-title":"IEEE Trans. Consum. Electron."}],"container-title":["Communications in Computer and Information Science","Neural Computing for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-7007-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T18:04:47Z","timestamp":1726941887000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-7007-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,22]]},"ISBN":["9789819770069","9789819770076"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-7007-6_12","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024,9,22]]},"assertion":[{"value":"22 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NCAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Computing for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guilin","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ncaa2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aaci.org.hk\/ncaa2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}