{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T06:30:33Z","timestamp":1764311433087,"version":"3.46.0"},"reference-count":15,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:00:00Z","timestamp":1756771200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:00:00Z","timestamp":1756771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100014440","name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","doi-asserted-by":"publisher","award":["PID2019-108927RB-I00 AEI\/10.13039\/501100011033","PID2019-108927RB-I00 AEI\/10.13039\/501100011033"],"award-info":[{"award-number":["PID2019-108927RB-I00 AEI\/10.13039\/501100011033","PID2019-108927RB-I00 AEI\/10.13039\/501100011033"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Univ Access Inf Soc"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s10209-025-01256-w","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T04:37:50Z","timestamp":1756787870000},"page":"3165-3183","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-guided interpretation of images for blind users based on multi-layered interaction"],"prefix":"10.1007","volume":"24","author":[{"given":"Walid","family":"Bousnitra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raquel","family":"Herv\u00e1s","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alberto","family":"D\u00edaz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Leo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Mart\u00edn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sirma","family":"Sosa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,2]]},"reference":[{"key":"1256_CR1","unstructured":"Brooke, J.: SUS: a quick and dirty usability scale. Usability Eval Ind vol 189 (1995)"},{"key":"1256_CR2","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G. et\u00a0al.: End-to-end object detection with transformers. In CoRR (2020) arXiv:2005.12872","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1256_CR3","doi-asserted-by":"publisher","unstructured":"Herv\u00e1s, R., D\u00edaz, A., Amor, M. et\u00a0al.: Self-guided spatial composition as an additional layer of information to enhance accessibility of images for blind users. In: Proceedings of the XXIV International Conference on Human Computer Interaction. Association for Computing Machinery, New York, NY, USA, Interacci\u00f3n \u201924, (2024) https:\/\/doi.org\/10.1145\/3657242.3658590","DOI":"10.1145\/3657242.3658590"},{"key":"1256_CR4","doi-asserted-by":"publisher","unstructured":"Jain, SM.: Hugging Face, Apress, Berkeley, CA, pp 51\u201367. (2022) https:\/\/doi.org\/10.1007\/978-1-4842-8844-3_4","DOI":"10.1007\/978-1-4842-8844-3_4"},{"key":"1256_CR5","doi-asserted-by":"publisher","unstructured":"Lee, J., Herskovitz, J., Peng, YH. et\u00a0al.: Imageexplorer: Multi-layered touch exploration to encourage skepticism towards imperfect AI-generated image captions. In: Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, New York, NY, USA, CHI \u201922, (2022) https:\/\/doi.org\/10.1145\/3491102.3501966,","DOI":"10.1145\/3491102.3501966"},{"key":"1256_CR6","doi-asserted-by":"publisher","unstructured":"Li, J., Li, D., Xiong, C. et\u00a0al.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. (2022) https:\/\/doi.org\/10.48550\/ARXIV.2201.12086, [Web; accedido el 14 May 2024]","DOI":"10.48550\/ARXIV.2201.12086"},{"key":"1256_CR7","doi-asserted-by":"crossref","unstructured":"Lin, TY., Maire, M., Belongie, S. et\u00a0al.: Microsoft coco: Common objects in context. (2015). arXiv:1405.0312","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1256_CR8","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"SSD: Single Shot MultiBox Detector","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., et al.: SSD: Single Shot MultiBox Detector, pp. 21\u201337. Springer International Publishing, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"1256_CR9","doi-asserted-by":"publisher","unstructured":"Lu, J., Xiong, C., Parikh, D. et\u00a0al.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3242\u20133250 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.345","DOI":"10.1109\/CVPR.2017.345"},{"key":"1256_CR10","unstructured":"Lu, J., Batra, D., Parikh, D. et\u00a0al.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"1256_CR11","doi-asserted-by":"publisher","unstructured":"Nair, V., Zhu, HH., Smith, B.A.: Imageassist: tools for enhancing touchscreen-based image exploration systems for blind and low vision users. In: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, New York, NY, USA, (2023). https:\/\/doi.org\/10.1145\/3544548.3581302","DOI":"10.1145\/3544548.3581302"},{"key":"1256_CR12","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., et\u00a0al.: You only look once: Unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788. (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"1256_CR13","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R. et\u00a0al.: Faster r-cnn: towards real-time object detection with region proposal networks. (2016) arXiv:1506.01497","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"1256_CR14","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Deng, J., Su, H. et\u00a0al.: Imagenet large scale visual recognition challenge. (2015). arXiv:1409.0575","DOI":"10.1007\/s11263-015-0816-y"},{"key":"1256_CR15","doi-asserted-by":"publisher","unstructured":"Vinyals, O., Toshev, A., Bengio, S. et\u00a0al.: Show and tell: A neural image caption generator. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164. (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298935","DOI":"10.1109\/CVPR.2015.7298935"}],"container-title":["Universal Access in the Information Society"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10209-025-01256-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10209-025-01256-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10209-025-01256-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T06:25:31Z","timestamp":1764311131000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10209-025-01256-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,2]]},"references-count":15,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["1256"],"URL":"https:\/\/doi.org\/10.1007\/s10209-025-01256-w","relation":{},"ISSN":["1615-5289","1615-5297"],"issn-type":[{"type":"print","value":"1615-5289"},{"type":"electronic","value":"1615-5297"}],"subject":[],"published":{"date-parts":[[2025,9,2]]},"assertion":[{"value":"4 August 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All participants consented to participate in this work.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}