{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T18:30:09Z","timestamp":1743100209921,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031120527"},{"type":"electronic","value":"9783031120534"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-12053-4_14","type":"book-chapter","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T09:15:50Z","timestamp":1658740550000},"page":"187-198","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Weakly Supervised Captioning of\u00a0Ultrasound Images"],"prefix":"10.1007","author":[{"given":"Mohammad","family":"Alsharid","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harshita","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lior","family":"Drukker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aris T.","family":"Papageorgiou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J. Alison","family":"Noble","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,25]]},"reference":[{"key":"14_CR1","unstructured":"Google code archive (2018). https:\/\/code.google.com\/archive\/p\/word2vec\/"},{"key":"14_CR2","unstructured":"Evaluating models | automl translation documentation (2020). https:\/\/cloud.google.com\/translate\/automl\/docs\/evaluate"},{"key":"14_CR3","unstructured":"Grammarbot (2020). https:\/\/www.grammarbot.io\/"},{"key":"14_CR4","unstructured":"Textblob (2020). https:\/\/textblob.readthedocs.io\/en\/dev\/"},{"key":"14_CR5","unstructured":"Context analysis in NLP: why it\u2019s valuable and how it\u2019s done (2021). https:\/\/www.lexalytics.com\/lexablog\/context-analysis-nlp"},{"key":"14_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/978-3-030-60334-2_8","volume-title":"Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis","author":"M Alsharid","year":"2020","unstructured":"Alsharid, M., El-Bouri, R., Sharma, H., Drukker, L., Papageorghiou, A.T., Noble, J.A.: A curriculum learning based approach to captioning ultrasound images. In: Hu, Y., et al. (eds.) ASMUS\/PIPPI -2020. LNCS, vol. 12437, pp. 75\u201384. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-60334-2_8"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Alsharid, M., El-Bouri, R., Sharma, H., Drukker, L., Papageorghiou, A.T., Noble, J.A.: A course-focused dual curriculum for image captioning. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 716\u2013720. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434055"},{"key":"14_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1007\/978-3-030-32251-9_37","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"M Alsharid","year":"2019","unstructured":"Alsharid, M., Sharma, H., Drukker, L., Chatelain, P., Papageorghiou, A.T., Noble, J.A.: Captioning ultrasound images automatically. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 338\u2013346. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32251-9_37"},{"key":"14_CR9","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1613\/jair.4900","volume":"55","author":"R Bernardi","year":"2016","unstructured":"Bernardi, R., Cakici, R., Elliott, D., Erdem, A., Erdem, E., Ikizler-Cinbis, N., et al.: Automatic description generation from images: a survey of models, datasets, and evaluation measures. J. Artif. Intell. Res. 55, 409\u2013442 (2016)","journal-title":"J. Artif. Intell. Res."},{"key":"14_CR10","unstructured":"Burkov, A.: The Hundred-Page Machine Learning Book, pp. 100\u2013101. Andriy Burkov (2019)"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Chen, T.H., Liao, Y.H., Chuang, C.Y., Hsu, W.T., Fu, J., Sun, M.: Show, adapt and tell: adversarial training of cross-domain image captioner. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 521\u2013530 (2017)","DOI":"10.1109\/ICCV.2017.64"},{"key":"14_CR13","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Proceedings of the Workshop on Text Summarization Branches Out, Barcelona, Spain, pp. 56\u201360 (2004)"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Devlin, J., Cheng, H., Fang, H., Gupta, S., Deng, L., He, X., et al.: Language models for image captioning: the quirks and what works. arXiv preprint arXiv:1505.01809 (2015)","DOI":"10.3115\/v1\/P15-2017"},{"issue":"1","key":"14_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-92829-1","volume":"11","author":"L Drukker","year":"2021","unstructured":"Drukker, L., et al.: Transforming obstetric ultrasound into data science using eye tracking, voice recording, transducer motion and ultrasound video. Sci. Rep. 11(1), 1\u201312 (2021)","journal-title":"Sci. Rep."},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Feng, Y., Ma, L., Liu, W., Luo, J.: Unsupervised image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4125\u20134134 (2019)","DOI":"10.1109\/CVPR.2019.00425"},{"key":"14_CR17","unstructured":"Gal, Y., Ghahramani, Z.: A theoretically grounded application of dropout in recurrent neural networks. arXiv preprint arXiv:1512.05287 (2015)"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., et al.: YouTube2Text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2712\u20132719 (2013)","DOI":"10.1109\/ICCV.2013.337"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Gupta, A., Srinivasan, P., Shi, J., Davis, L.S.: Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2012\u20132019. IEEE (2009)","DOI":"10.1109\/CVPRW.2009.5206492"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Venugopalan, S., Rohrbach, M., Mooney, R., Saenko, K., Darrell, T.: Deep compositional captioning: describing novel object categories without paired training data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u201310 (2016)","DOI":"10.1109\/CVPR.2016.8"},{"key":"14_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Krishnamoorthy, N., Malkarnenkar, G., Mooney, R., Saenko, K., Guadarrama, S.: Generating natural-language video descriptions using text-mined knowledge. In: Proceedings of the Workshop on Vision and Natural Language Processing, pp. 10\u201319 (2013)","DOI":"10.1609\/aaai.v27i1.8679"},{"issue":"12","key":"14_CR23","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni, G., Premraj, V., Ordonez, V., Dhar, S., Li, S., Choi, Y., et al.: Babytalk: understanding and generating simple image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2891\u20132903 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR24","unstructured":"Lyndon, D., Kumar, A., Kim, J.: Neural captioning for the ImageCLEF 2017 medical image challenges. In: CLEF (Working Notes) (2017)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"14_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101973","volume":"69","author":"H Sharma","year":"2021","unstructured":"Sharma, H., Drukker, L., Chatelain, P., Droste, R., Papageorghiou, A.T., Noble, J.A.: Knowledge representation and learning of operator clinical workflow from full-length routine fetal ultrasound scan videos. Med. Image Anal. 69, 101973 (2021)","journal-title":"Med. Image Anal."},{"key":"14_CR27","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"14_CR28","unstructured":"Stuart, L.M., Taylor, J.M., Raskin, V.: The importance of nouns in text processing. In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol. 35 (2013)"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Tanti, M., Gatt, A., Camilleri, K.: What is the role of recurrent neural networks (RNNs) in an image caption generator? arXiv preprint arXiv:1708.02043 (2017)","DOI":"10.18653\/v1\/W17-3506"},{"issue":"3","key":"14_CR30","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1017\/S1351324918000098","volume":"24","author":"M Tanti","year":"2018","unstructured":"Tanti, M., Gatt, A., Camilleri, K.P.: Where to put the image in an image caption generator. Nat. Lang. Eng. 24(3), 467\u2013489 (2018)","journal-title":"Nat. Lang. Eng."},{"key":"14_CR31","unstructured":"Thomason, J., Venugopalan, S., Guadarrama, S., Saenko, K., Mooney, R.: Integrating language and vision to generate natural language descriptions of videos in the wild. In: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pp. 1218\u20131227 (2014)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Topol, E.J.: A decade of digital medicine innovation. Sci. Transl. Med. 11(498), eaaw7610 (2019)","DOI":"10.1126\/scitranslmed.aaw7610"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Pham, H., Dai, Z., Neubig, G.: SwitchOut: an efficient data augmentation algorithm for neural machine translation. arXiv preprint arXiv:1808.07512 (2018)","DOI":"10.18653\/v1\/D18-1100"},{"issue":"5","key":"14_CR35","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1007\/s11390-018-1874-8","volume":"33","author":"XH Zeng","year":"2018","unstructured":"Zeng, X.H., Liu, B.G., Zhou, M.: Understanding and generating ultrasound image description. J. Comput. Sci. Technol. 33(5), 1086\u20131100 (2018)","journal-title":"J. Comput. Sci. Technol."},{"key":"14_CR36","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.neucom.2018.11.114","volume":"392","author":"X Zeng","year":"2019","unstructured":"Zeng, X., Wen, L., Liu, B., Qi, X.: Deep learning for ultrasound image caption generation based on object detection. Neurocomputing 392, 132\u2013141 (2019)","journal-title":"Neurocomputing"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, W., et al.: Dual learning for cross-domain image captioning. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 29\u201338 (2017)","DOI":"10.1145\/3132847.3132920"}],"container-title":["Lecture Notes in Computer Science","Medical Image Understanding and Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-12053-4_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,8]],"date-time":"2024-02-08T08:05:24Z","timestamp":1707379524000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-12053-4_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031120527","9783031120534"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-12053-4_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"25 July 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MIUA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Annual Conference on Medical Image Understanding and Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambridge","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miua2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.miua2022.com\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}