{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T07:03:46Z","timestamp":1776841426569,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T00:00:00Z","timestamp":1718755200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"funder":[{"name":"Agencia Estatal de Investigaci\u00f3n, Espa\u00f1a","award":["AEI\/10.13039\/501100011033"],"award-info":[{"award-number":["AEI\/10.13039\/501100011033"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,19]]},"DOI":"10.1145\/3657242.3658590","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T12:26:07Z","timestamp":1717763167000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Self-guided Spatial Composition as an Additional Layer of Information to Enhance Accessibility of Images for Blind Users"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2900-9992","authenticated-orcid":false,"given":"Raquel","family":"Herv\u00e1s","sequence":"first","affiliation":[{"name":"Facultad de Inform\u00e1tica and Instituto de Tecnolog\u00eda del Conocimiento, Universidad Complutense de Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1966-3421","authenticated-orcid":false,"given":"Alberto","family":"D\u00edaz","sequence":"additional","affiliation":[{"name":"Facultad de Inform\u00e1tica and Instituto de Tecnolog\u00eda del Conocimiento, Universidad Complutense de Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6900-4268","authenticated-orcid":false,"given":"Mat\u00edas","family":"Amor","sequence":"additional","affiliation":[{"name":"Facultad de Inform\u00e1tica, Universidad Complutense de Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7491-1337","authenticated-orcid":false,"given":"Alberto","family":"Chaves","sequence":"additional","affiliation":[{"name":"Facultad de Inform\u00e1tica, Universidad Complutense de Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3199-7197","authenticated-orcid":false,"given":"V\u00edctor","family":"Ruiz","sequence":"additional","affiliation":[{"name":"Facultad de Inform\u00e1tica, Universidad Complutense de Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"SUS: A quick and dirty usability scale. Usability Eval. Ind. 189 (11","author":"Brooke John","year":"1995","unstructured":"John Brooke. 1995. SUS: A quick and dirty usability scale. Usability Eval. Ind. 189 (11 1995)."},{"key":"e_1_3_2_1_2_1","volume-title":"End-to-End Object Detection with Transformers. CoRR abs\/2005.12872","author":"Carion Nicolas","year":"2020","unstructured":"Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. End-to-End Object Detection with Transformers. CoRR abs\/2005.12872 (2020). arxiv:2005.12872https:\/\/arxiv.org\/abs\/2005.12872"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Shashank\u00a0Mohan Jain. 2022. Hugging Face. Apress Berkeley CA 51\u201367. https:\/\/doi.org\/10.1007\/978-1-4842-8844-3_4","DOI":"10.1007\/978-1-4842-8844-3_4"},{"key":"e_1_3_2_1_4_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. arxiv:2201.12086","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. arxiv:2201.12086"},{"key":"e_1_3_2_1_5_1","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:1405.0312"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_7_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581302"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_11_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2016. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arxiv:1506.01497"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein Alexander\u00a0C. Berg and Li Fei-Fei. 2015. ImageNet Large Scale Visual Recognition Challenge. arxiv:1409.0575","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445242"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580655"}],"event":{"name":"INTERACCION 2024: XXIV Congreso Internacional de Interacci\u00f3n Persona-Ordenador \\ XXIV International Conference on Human Computer Interaction","location":"A Coru\u00f1a Spain","acronym":"INTERACCION 2024"},"container-title":["Proceedings of the XXIV International Conference on Human Computer Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3657242.3658590","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3657242.3658590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T02:09:59Z","timestamp":1755914999000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3657242.3658590"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,19]]},"references-count":15,"alternative-id":["10.1145\/3657242.3658590","10.1145\/3657242"],"URL":"https:\/\/doi.org\/10.1145\/3657242.3658590","relation":{},"subject":[],"published":{"date-parts":[[2024,6,19]]},"assertion":[{"value":"2024-06-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}