{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T12:13:49Z","timestamp":1771244029995,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,21]]},"DOI":"10.1145\/3777490.3777491","type":"proceedings-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:24:28Z","timestamp":1771241068000},"page":"75-78","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["On The Automatic Image Captioning Task In Italian: A Human-Centric Approach"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6839-592X","authenticated-orcid":false,"given":"Valentina","family":"De Amicis","sequence":"first","affiliation":[{"name":"Technological University Dublin, Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4530-7079","authenticated-orcid":false,"given":"Rajesh","family":"Jaiswal","sequence":"additional","affiliation":[{"name":"Technological University Dublin, Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4978-2843","authenticated-orcid":false,"given":"Fernando","family":"Perez-Tellez","sequence":"additional","affiliation":[{"name":"Technological University Dublin, Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2,16]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Abien\u00a0Fred Agarap. 2019. Deep Learning using Rectified Linear Units (ReLU). arxiv:https:\/\/arXiv.org\/abs\/1803.08375\u00a0[cs.NE] https:\/\/arxiv.org\/abs\/1803.08375"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Rasha\u00a0Saleh Al-Malki and Arwa\u00a0Yousuf Al-Aama. 2023. Arabic Captioning for Images of Clothing Using Deep Learning. Sensors (Basel Switzerland) 23 8 (4 2023) 3783. 10.3390\/S23083783","DOI":"10.3390\/S23083783"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Ashwaq Alsayed Muhammad Arif Thamir\u00a0M. Qadah and Saud Alotaibi. 2023. A Systematic Literature Review on Using the Encoder-Decoder Models for Image Captioning in English and Arabic Languages. Applied Sciences (Switzerland) 13 19 (10 2023). 10.3390\/app131910894","DOI":"10.3390\/app131910894"},{"key":"e_1_3_3_2_5_2","unstructured":"Ms\u00a0G Aninthitha. 2024. IMPROVED IMAGE CAPTION GENERATION FOR LOW RESOURCE LANGUAGES. International Journal of Creative Research Thoughts 12 (2024) 2320\u20132882. www.ijcrt.org"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Antonio Scaiella Danilo Croce and Roberto Basili. 2019. Large scale datasets for Image and Video Captioning in Italian. Italian Journal of Computational Linguistics 2 5 (12 2019) 49\u201360. www.aAccademia.it\/IJCoL_5_2","DOI":"10.4000\/ijcol.478"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Viktar Atliha and Dmitrij \u0160e\u0161ok. 2020. Text Augmentation Using BERT for Image Captioning. Applied Sciences 10 17 (2020). 10.3390\/app10175978","DOI":"10.3390\/app10175978"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Shuang Bai and Shan An. 2018. A survey on automatic image caption generation. Neurocomputing 311 (10 2018) 291\u2013304. 10.1016\/j.neucom.2018.05.080","DOI":"10.1016\/j.neucom.2018.05.080"},{"key":"e_1_3_3_2_9_2","unstructured":"Federico Bianchi Giuseppe Attanasio Raphael Pisoni Silvia Terragni Gabriele Sarti and Dario Balestri. 2021. Contrastive Language-Image Pre-training for the Italian Language. CEUR Workshop Proceedings 3596 (8 2021). https:\/\/arxiv.org\/abs\/2108.08688v1"},{"key":"e_1_3_3_2_10_2","unstructured":"Yarin Gal and Zoubin Ghahramani. 2015. A Theoretically Grounded Application of Dropout in Recurrent Neural Networks. Advances in Neural Information Processing Systems (12 2015) 1027\u20131035. https:\/\/arxiv.org\/pdf\/1512.05287"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Lisa\u00a0Anne Hendricks Kaylee Burns Kate Saenko Trevor Darrell and Anna Rohrbach. 2018. Women also Snowboard: Overcoming Bias in Captioning Models. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) 11207 LNCS (3 2018) 793\u2013811. 10.1007\/978-3-030-01219-947","DOI":"10.1007\/978-3-030-01219-947"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Wenjin Hu Lang Qiao Wendong Kang and Xinyue Shi. 2023. Thangka Image Captioning Based on Semantic Concept Prompt and Multimodal Feature Optimization. Journal of Imaging 2023 Vol. 9 Page 162 9 8 (8 2023) 162. 10.3390\/JIMAGING9080162","DOI":"10.3390\/JIMAGING9080162"},{"key":"e_1_3_3_2_13_2","unstructured":"Diederik\u00a0P. Kingma and Jimmy\u00a0Lei Ba. 2014. Adam: A Method for Stochastic Optimization. 3rd International Conference on Learning Representations ICLR 2015 - Conference Track Proceedings (12 2014). https:\/\/arxiv.org\/pdf\/1412.6980"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Maurizio Leotta Fabrizio Mori and Marina Ribaudo. 2023. Evaluating the effectiveness of automatic image captioning for web accessibility. Universal Access in the Information Society 22 4 (11 2023) 1293\u20131313. 10.1007\/s10209-022-00906-7","DOI":"10.1007\/s10209-022-00906-7"},{"key":"e_1_3_3_2_15_2","unstructured":"Tsung-Yi Lin Michael Maire Serge Belongie Lubomir Bourdev Ross Girshick James Hays Pietro Perona Deva Ramanan C.\u00a0Lawrence Zitnick and Piotr Doll\u00e1r. 2015. Microsoft COCO: Common Objects in Context. arxiv:https:\/\/arXiv.org\/abs\/1405.0312\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1405.0312"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Kaiji Lu Piotr Mardziel Fangjing Wu Preetam Amancharla and Anupam Datta. 2018. Gender Bias in Neural Natural Language Processing. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) 12300 LNCS (7 2018) 189\u2013202. 10.1007\/978-3-030-62077-614","DOI":"10.1007\/978-3-030-62077-614"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Caterina Masotti Danilo Croce and Roberto Basili. 2018. Deep Learning for Automatic Image Captioning in Poor Training Conditions. http:\/\/journals.openedition.org\/ijcol 4 4-1 (6 2018) 43\u201355. 10.4000\/IJCOL.538","DOI":"10.4000\/IJCOL.538"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Yue Ming Nannan Hu Chunxiao Fan Fan Feng Jiangwan Zhou and Hui Yu. 2022. Visuals to Text: A Comprehensive Review on Automatic Image Captioning. IEEE\/CAA Journal of Automatica Sinica 9 8 (8 2022) 1339\u20131365. 10.1109\/JAS.2022.105734","DOI":"10.1109\/JAS.2022.105734"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Antonio Scaiella Danilo Croce and Roberto Basili. 2019. Large scale datasets for Image and Video Captioning in Italian. Italian Journal of Computational Linguistics 5 2 (3 2019) 49\u201360. www.aAccademia.it\/IJCoL_5_2","DOI":"10.4000\/ijcol.478"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Dhruv Sharma Chhavi Dhiman and Dinesh Kumar. 2023. Evolution of visual data captioning Methods Datasets and evaluation Metrics: A comprehensive survey. Expert Systems with Applications 221 (7 2023). 10.1016\/j.eswa.2023.119773","DOI":"10.1016\/j.eswa.2023.119773"},{"key":"e_1_3_3_2_22_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. 3rd International Conference on Learning Representations ICLR 2015 - Conference Track Proceedings (9 2014). https:\/\/arxiv.org\/abs\/1409.1556v6"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Matteo Stefanini Marcella Cornia Lorenzo Baraldi Silvia Cascianelli Giuseppe Fiameni and Rita Cucchiara. 2023. From Show to Tell: A Survey on Deep Learning-Based Image Captioning. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 1 (1 2023) 539\u2013559. 10.1109\/TPAMI.2022.3148210","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Ruixiang Tang Mengnan Du Yuening Li Zirui Liu Na Zou and Xia Hu. 2021. Mitigating gender bias in captioning systems. The Web Conference 2021 - Proceedings of the World Wide Web Conference WWW 2021 13 (6 2021) 633\u2013645. Issue 21. 10.1145\/3442381.3449950;JOURNAL:JOURNAL:ACMCONFERENCES;PAGEGROUP:STRING:PUBLICATION","DOI":"10.1145\/3442381.3449950"},{"key":"e_1_3_3_2_25_2","unstructured":"Emiel van Miltenburg. 2025. Image captioning in different languages. arxiv:https:\/\/arXiv.org\/abs\/2407.09495\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2407.09495"},{"key":"e_1_3_3_2_26_2","unstructured":"Eva Vanmassenhove. 2024. Gender Bias in Machine Translation and The Era of Large Language Models. arXiv:https:\/\/arXiv.org\/abs\/2401.10016 (2024). http:\/\/arxiv.org\/abs\/2401.10016"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Tianlu Wang Jieyu Zhao Mark Yatskar Kai\u00a0Wei Chang and Vicente Ordonez. 2018. Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations. Proceedings of the IEEE International Conference on Computer Vision (11 2018) 5309\u20135318. 10.1109\/ICCV.2019.00541","DOI":"10.1109\/ICCV.2019.00541"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3607827.3616839"},{"key":"e_1_3_3_2_29_2","unstructured":"Kelvin Xu Jimmy\u00a0Lei Ba Ryan Kiros Kyunghyun Cho Aaron Courville Ruslan Salakhutdinov Richard\u00a0S. Zemel and Yoshua Bengio. 2015. Show attend and tell: neural image caption generation with visual attention. Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37 (2015) 2048\u20132057."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Serdar Yildiz Abbas Memis and Songul Carli. 2023. Automatic Turkish Image Captioning: The Impact of Deep Machine Translation. UBMK 2023 - Proceedings: 8th International Conference on Computer Science and Engineering (2023) 414\u2013419. 10.1109\/UBMK59864.2023.10286693","DOI":"10.1109\/UBMK59864.2023.10286693"},{"key":"e_1_3_3_2_31_2","unstructured":"Quanzeng You Hailin Jin Zhaowen Wang Chen Fang and Jiebo Luo. 2016. Image Captioning with Semantic Attention. https:\/\/arxiv.org\/abs\/1603.03925"}],"event":{"name":"HCAIep '26: Human Centred Artificial Intelligence - Education and Practice","location":"Kildare Ireland","acronym":"HCAIep '26"},"container-title":["Proceedings of the 2026 Conference on Human Centred Artificial Intelligence - Education and Practice"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3777490.3777491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:27:59Z","timestamp":1771241279000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3777490.3777491"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,21]]},"references-count":30,"alternative-id":["10.1145\/3777490.3777491","10.1145\/3777490"],"URL":"https:\/\/doi.org\/10.1145\/3777490.3777491","relation":{},"subject":[],"published":{"date-parts":[[2026,1,21]]},"assertion":[{"value":"2026-02-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}