{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:00:43Z","timestamp":1772910043495,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Academy of Finland Profi5 DigiHealth project","award":["326291"],"award-info":[{"award-number":["326291"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,9,20]]},"DOI":"10.1145\/3617233.3617246","type":"proceedings-article","created":{"date-parts":[[2023,12,30]],"date-time":"2023-12-30T06:05:32Z","timestamp":1703916332000},"page":"48-54","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Retrieved Generative Captioning for Medical Images"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1371-3881","authenticated-orcid":false,"given":"Djamila Romaissa","family":"Beddiar","sequence":"first","affiliation":[{"name":"Center for machine vision and signal analysis, university of Oulu, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4422-8723","authenticated-orcid":false,"given":"Mourad","family":"Oussalah","sequence":"additional","affiliation":[{"name":"Center for machine vision and signal analysis, university of Oulu; Faculty of Medicine, University of Oulu, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3963-0750","authenticated-orcid":false,"given":"Tapio","family":"Seppanen","sequence":"additional","affiliation":[{"name":"Center for machine vision and signal analysis, university of Oulu, Finland"}]}],"member":"320","published-online":{"date-parts":[[2023,12,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Working Notes of CLEF 2017-Conference and Labs of the Evaluation Forum (CLEF 2017), Dublin, Ireland, September 11-14, 2017.","author":"Abacha Asma\u00a0Ben","year":"2017","unstructured":"Asma\u00a0Ben Abacha, AG Seco De\u00a0Herrera, Soumya Gayen, Dina Demner-Fushman, and Sameer Antani. 2017. NLM at ImageCLEF 2017 caption task. In Working Notes of CLEF 2017-Conference and Labs of the Evaluation Forum (CLEF 2017), Dublin, Ireland, September 11-14, 2017., Vol.\u00a01866. CEUR Workshop Proceedings."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107856"},{"key":"e_1_3_2_1_3_1","volume-title":"Automatic captioning for medical imaging (MIC): a rapid review of literature. Artificial Intelligence Review","author":"Beddiar Djamila-Romaissa","year":"2022","unstructured":"Djamila-Romaissa Beddiar, Mourad Oussalah, and Tapio Sepp\u00e4nen. 2022. Automatic captioning for medical imaging (MIC): a rapid review of literature. Artificial Intelligence Review (2022), 1\u201358."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/app122111092"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Romaissa Beddiar and Mourad Oussalah. 2023. Chapter 12 - Explainability in medical image captioning. In Explainable Deep Learning AI Jenny Benois-Pineau Romain Bourqui Dragutin Petkovic and Georges Qu\u00e9not (Eds.). Academic Press 239\u2013261. https:\/\/doi.org\/10.1016\/B978-0-32-396098-4.00018-1","DOI":"10.1016\/B978-0-32-396098-4.00018-1"},{"key":"e_1_3_2_1_6_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877\u20131901."},{"key":"e_1_3_2_1_7_1","volume-title":"Generating radiology reports via memory-driven transformer. arXiv preprint arXiv:2010.16056","author":"Chen Zhihong","year":"2020","unstructured":"Zhihong Chen, Yan Song, Tsung-Hui Chang, and Xiang Wan. 2020. Generating radiology reports via memory-driven transformer. arXiv preprint arXiv:2010.16056 (2020)."},{"key":"e_1_3_2_1_8_1","volume-title":"Electronic and Automation Control Conference (IMCEC), Vol.\u00a05. IEEE, 316\u2013322","author":"Chen Zhixian","year":"2022","unstructured":"Zhixian Chen and Yuhao Tang. 2022. Improving Radiology Report Generation via Object Dropout Strategy and MLP-based Captioner. In 2022 IEEE 5th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Vol.\u00a05. IEEE, 316\u2013322."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"J. Deng W. Dong R. Socher L.-J. Li K. Li and L. Fei-Fei. 2009. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR09.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_10_1","volume-title":"On the automatic generation of medical imaging reports. arXiv preprint arXiv:1711.08195","author":"Jing Baoyu","year":"2017","unstructured":"Baoyu Jing, Pengtao Xie, and Eric Xing. 2017. On the automatic generation of medical imaging reports. arXiv preprint arXiv:1711.08195 (2017)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22041429"},{"key":"e_1_3_2_1_12_1","volume-title":"Hybrid retrieval-generation reinforced agent for medical image report generation. Advances in neural information processing systems 31","author":"Li Yuan","year":"2018","unstructured":"Yuan Li, Xiaodan Liang, Zhiting Hu, and Eric\u00a0P Xing. 2018. Hybrid retrieval-generation reinforced agent for medical image report generation. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_13_1","unstructured":"Sisi Liang Xiangyang Li Yongqing Zhu Xue Li and Shuqiang Jiang. 2017. ISIA at the ImageCLEF 2017 Image Caption Task.. In CLEF (Working Notes)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Obioma Pelka Sven Koitka Johannes R\u00fcckert Felix Nensa and Christoph\u00a0M Friedrich. 2018. Radiology Objects in COntext (ROCO): a multimodal image dataset. In Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis: 7th Joint International Workshop CVII-STENT 2018 and Third International Workshop LABELS 2018 Held in Conjunction with MICCAI 2018 Granada Spain September 16 2018 Proceedings 3. Springer 180\u2013189.","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"e_1_3_2_1_16_1","volume-title":"Medical Image Captioning via Generative Pretrained Transformers. arXiv preprint arXiv:2209.13983","author":"Selivanov Alexander","year":"2022","unstructured":"Alexander Selivanov, Oleg\u00a0Y Rogov, Daniil Chesakov, Artem Shelmanov, Irina Fedulova, and Dmitry\u00a0V Dylov. 2022. Medical Image Captioning via Generative Pretrained Transformers. arXiv preprint arXiv:2209.13983 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Medical image captioning using optimized deep learning model. Computational Intelligence and Neuroscience 2022","author":"Singh Arjun","year":"2022","unstructured":"Arjun Singh, Jaya Krishna\u00a0Raguru, Gaurav Prasad, Surbhi Chauhan, Pradeep\u00a0Kumar Tiwari, Atef Zaguia, and Mohammad\u00a0Aman Ullah. 2022. Medical image captioning using optimized deep learning model. Computational Intelligence and Neuroscience 2022 (2022)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531415"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00943"},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. PMLR","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning. PMLR, 2048\u20132057."},{"key":"e_1_3_2_1_21_1","volume-title":"CLEF CEUR Workshop","author":"Zhang Yu","year":"2018","unstructured":"Yu Zhang, Xuwen Wang, Zhen Guo, and Jiao Li. 2018. ImageSem at ImageCLEF 2018 caption task: Image retrieval and transfer learning. In CLEF CEUR Workshop, Avignon, France."},{"key":"e_1_3_2_1_22_1","volume-title":"SPEA2: Improving the strength Pareto evolutionary algorithm. TIK-report 103","author":"Zitzler Eckart","year":"2001","unstructured":"Eckart Zitzler, Marco Laumanns, and Lothar Thiele. 2001. SPEA2: Improving the strength Pareto evolutionary algorithm. TIK-report 103 (2001)."}],"event":{"name":"CBMI 2023: 20th International Conference on Content-based Multimedia Indexing","location":"Orleans France","acronym":"CBMI 2023"},"container-title":["20th International Conference on Content-based Multimedia Indexing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617233.3617246","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3617233.3617246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:00:08Z","timestamp":1756486808000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617233.3617246"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,20]]},"references-count":22,"alternative-id":["10.1145\/3617233.3617246","10.1145\/3617233"],"URL":"https:\/\/doi.org\/10.1145\/3617233.3617246","relation":{},"subject":[],"published":{"date-parts":[[2023,9,20]]},"assertion":[{"value":"2023-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}