{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:41:20Z","timestamp":1762368080671,"version":"build-2065373602"},"reference-count":41,"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\/mlsp62443.2025.11204281","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":["Speaking Images. A Novel Framework for the Automated Self-Description of Artworks"],"prefix":"10.1109","author":[{"given":"Valentine","family":"Bernasconi","sequence":"first","affiliation":[{"name":"University of Bologna,Virtual and Augmented Reality Lab,Bologna,Italy"}]},{"given":"Gustavo","family":"Marfia","sequence":"additional","affiliation":[{"name":"University of Bologna,Virtual and Augmented Reality Lab,Bologna,Italy"}]}],"member":"263","reference":[{"volume-title":"Painting the word: Christian pictures and their meanings","year":"1999","author":"Drury","key":"ref1"},{"volume-title":"Image As Theology: The Power of Art in Shaping Christian Thought, Devotion, and Imagination","year":"2022","author":"Strine","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2307\/jj.10518935"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv36xw66c"},{"journal-title":"Patterns of creativity: How user input shapes ai-generated visual diversity","year":"2024","author":"De Rosa Palmini","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.671"},{"key":"ref7","article-title":"Culturepark: Boosting cross-cultural understanding in large language models","volume-title":"The Thirtyeighth Annual Conference on Neural Information Processing Systems","author":"Li","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611891"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109288"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445948"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2025.3530171"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887583"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083257"},{"journal-title":"From sora what we can see: A survey of text-to-video generation","year":"2024","author":"Sun","key":"ref14"},{"key":"ref15","article-title":"The influence of audiovisual elements on the realism of generative AI videos: the case of sora","volume-title":"Proceedings of the International Workshop on Artificial Intelligence and Creativity (CREAI), co-located with ECAI 2024","author":"Sanchez-Acedo","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/23080477.2023.2268380"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/13548565211029401"},{"journal-title":"Liveportrait: Efficient portrait animation with stitching and retargeting control","year":"2025","author":"Guo","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604681"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/14703297.2023.2195846"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.61969\/jai.1337500"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642731"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11389-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15968-9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging9060120"},{"journal-title":"The llama 3 herd of models","year":"2024","author":"Grattafiori","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.17671\/gazibtd.1399077"},{"journal-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation","year":"2024","author":"Xu","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e16757"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"journal-title":"Mauve scores for generative models: Theory and practice","year":"2023","author":"Pillutla","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681656"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10727-0"},{"journal-title":"Cognartive: Large language models for automating art analysis and decoding aesthetic elements","year":"2025","author":"Khadangi","key":"ref35"},{"journal-title":"Llama guard 3 vision: Safeguarding human-ai image understanding conversations","year":"2024","author":"Chi","key":"ref36"},{"journal-title":"Palm-e: An embodied multimodal language model","year":"2023","author":"Driess","key":"ref37"},{"key":"ref38","article-title":"Human simulacra: Benchmarking the personification of large language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xie","year":"2025"},{"journal-title":"The grid audio-visual speech corpus","year":"2006","author":"Cooke","key":"ref39"},{"key":"ref40","article-title":"Internalized biases in fr\u00e9chet inception distance","volume-title":"NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications","author":"Jung","year":"2021"},{"journal-title":"How i smoothly injected a mona lisa talking-head into the full portrait","year":"2024","author":"El komy","key":"ref41"}],"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\/11204281.pdf?arnumber=11204281","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:37:08Z","timestamp":1762367828000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204281\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204281","relation":{},"subject":[],"published":{"date-parts":[[2025,8,31]]}}}