{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:27Z","timestamp":1777889667752,"version":"3.51.4"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02259","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24370-24379","source":"Crossref","is-referenced-by-count":0,"title":["Embodied Image Captioning: Self-Supervised Learning Agents for Spatially Coherent Image Descriptions"],"prefix":"10.1109","author":[{"given":"Tommaso","family":"Galliena","sequence":"first","affiliation":[{"name":"Istituto Italiano di Tecnologia,Genoa,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tommaso","family":"Apicella","sequence":"additional","affiliation":[{"name":"Istituto Italiano di Tecnologia,Genoa,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Rosa","sequence":"additional","affiliation":[{"name":"Istituto Italiano di Tecnologia,Genoa,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pietro","family":"Morerio","sequence":"additional","affiliation":[{"name":"Istituto Italiano di Tecnologia,Genoa,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessio","family":"Del Bue","sequence":"additional","affiliation":[{"name":"Istituto Italiano di Tecnologia,Genoa,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorenzo","family":"Natale","sequence":"additional","affiliation":[{"name":"Istituto Italiano di Tecnologia,Genoa,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412628"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160668"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.556"},{"key":"ref4","article-title":"Learning to explore using active neural slam","volume-title":"International Conference on Learning Representations","author":"Chaplot","year":"2020"},{"key":"ref5","volume-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref6","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref8","volume-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00888"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00235"},{"key":"ref11","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01273"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00732"},{"key":"ref15","volume-title":"A rank stabilization scaling factor for finetuning with lora","author":"Kalajdzievski","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00275"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref18","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Learning Representations","author":"Li","year":"2022"},{"key":"ref19","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref20","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Text summarization branches out","author":"Lin","year":"2004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"key":"ref24","volume-title":"Chatgpt conversation on citation formats","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref26","volume-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023"},{"key":"ref27","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref28","volume-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai","author":"Ramakrishnan","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445969"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref32","article-title":"Look around and learn: self-improving object detection by exploration","volume-title":"Proceedings of European Conference on Computer Vision","author":"Scarpellini","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-021-10014-9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref37","volume-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022"},{"key":"ref38","volume-title":"Caption anything: Interactive image description with diverse multimodal controls","author":"Wang","year":"2023"},{"key":"ref39","volume-title":"The all-seeing project: Towards panoptic visual recognition and understanding of the open world","author":"Wang","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02558"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/280765.280773"},{"key":"ref45","volume-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref46","volume-title":"Opt: Open pretrained transformer language models.","author":"Zhang","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref48","volume-title":"Regionblip: A unified multi-modal pre-training framework for holistic and regional comprehension","author":"Zhou","year":"2023"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445581.pdf?arnumber=11445581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:17:25Z","timestamp":1777612645000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02259","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}