{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:41:23Z","timestamp":1762368083673,"version":"build-2065373602"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,31]]},"DOI":"10.1109\/mlsp62443.2025.11204345","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:52Z","timestamp":1761326152000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Artwork Topic Modeling via Fine-Tuned Clip and Knowledge-Driven Prompts"],"prefix":"10.1109","author":[{"given":"Raffaele","family":"Scaringi","sequence":"first","affiliation":[{"name":"University of Bari Aldo Moro,Department of Computer Science,Italy"}]},{"given":"Giovanni","family":"Stea","sequence":"additional","affiliation":[{"name":"University of Bari Aldo Moro,Department of Computer Science,Italy"}]},{"given":"Nicola","family":"Fanelli","sequence":"additional","affiliation":[{"name":"University of Bari Aldo Moro,Department of Computer Science,Italy"}]},{"given":"Gennaro","family":"Vessio","sequence":"additional","affiliation":[{"name":"University of Bari Aldo Moro,Department of Computer Science,Italy"}]},{"given":"Giovanna","family":"Castellano","sequence":"additional","affiliation":[{"name":"University of Bari Aldo Moro,Department of Computer Science,Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2133806.2133826"},{"article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112857"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01664-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2921101"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108859"},{"key":"ref10","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2022.102131"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1120.003.0082"},{"key":"ref13","article-title":"Mixing dirichlet topic models and word embeddings to make 1da2vec","author":"Moody","year":"2016","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.135"},{"article-title":"Autoencoding Variational Inference For Topic Models","volume-title":"International Conference on Learning Representations","author":"Srivastava","key":"ref15"},{"key":"ref16","article-title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","author":"Grootendorst","year":"2022","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"12159","article-title":"Neural Multimodal Topic Modeling: A Comprehensive Evaluation","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Gonzalez-Pizarro"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00592"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92808-6_11"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01100"},{"key":"ref21","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00325"},{"key":"ref24","article-title":"Neural Multimodal Topic Modeling: A Comprehensive Evaluation","author":"Gonz\u00e1lez-Pizarro","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","start":{"date-parts":[[2025,8,31]]},"location":"Istanbul, Turkiye","end":{"date-parts":[[2025,9,3]]}},"container-title":["2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204201\/11204202\/11204345.pdf?arnumber=11204345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:37:11Z","timestamp":1762367831000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204345","relation":{},"subject":[],"published":{"date-parts":[[2025,8,31]]}}}