{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T12:06:23Z","timestamp":1784635583739,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["101070396"],"award-info":[{"award-number":["101070396"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,21]]},"DOI":"10.1145\/3816046.3816207","type":"proceedings-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T11:44:18Z","timestamp":1784634258000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Captions: Shaping Imagery Models for Blind or Visually Impaired People During Interacting with AI-powered Conversational Visual Assistant"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7546-4657","authenticated-orcid":false,"given":"Mazen","family":"Salous","sequence":"first","affiliation":[{"name":"Society, OFFIS Institute for Information technology, Oldenburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6404-5169","authenticated-orcid":false,"given":"Miko\u0142aj P.","family":"Wo\u017aniak","sequence":"additional","affiliation":[{"name":"Carl von Ossietzky Universit\u00e4t Oldenburg, Oldenburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0674-1843","authenticated-orcid":false,"given":"Timo","family":"von Reeken","sequence":"additional","affiliation":[{"name":"Society, OFFIS Institute for Information technology, Oldenburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5114-9399","authenticated-orcid":false,"given":"Matthias","family":"Kramer","sequence":"additional","affiliation":[{"name":"Society, OFFIS Institute for Information Technology, Oldenburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2085-193X","authenticated-orcid":false,"given":"Wilko","family":"Heuten","sequence":"additional","affiliation":[{"name":"OFFIS - Institute for Information Technology, Oldenburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4293-1623","authenticated-orcid":false,"given":"Susanne","family":"Boll","sequence":"additional","affiliation":[{"name":"Carl von Ossietzky Universit\u00e4t Oldenburg, Oldenburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6048-042X","authenticated-orcid":false,"given":"Larbi","family":"Abdenebaoui","sequence":"additional","affiliation":[{"name":"Society, OFFIS Institute for Information Technology, Oldenburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","unstructured":"Jamil Abedalrahim\u00a0Jamil Alsayaydeh Irianto Maslan Zainon Hasvinii Baskaran and Safarudin\u00a0Gazali Herawan. 2022. Intelligent Interfaces for Assisting Blind People using Object Recognition Methods. International Journal of Advanced Computer Science and Applications 13 5 (2022). 10.14569\/IJACSA.2022.0130584","DOI":"10.14569\/IJACSA.2022.0130584"},{"key":"e_1_3_3_3_3_2","unstructured":"Peter Anderson Xiaodong He Chris Buehler Damien Teney Mark Johnson Stephen Gould and Lei Zhang. 2018. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. arxiv:https:\/\/arXiv.org\/abs\/1707.07998\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1707.07998"},{"key":"e_1_3_3_3_4_2","first-page":"3","volume-title":"Proceedings of the 2nd LUHME Workshop","author":"Anikina Tatiana","year":"2025","unstructured":"Tatiana Anikina, Alina Leippert, and Simon Ostermann. 2025. Building Common Ground in Dialogue: A Survey. In Proceedings of the 2nd LUHME Workshop, Henrique\u00a0Lopes Cardoso, Rui Sousa-Silva, Maarit Koponen, and Antonio Pareja-Lora (Eds.). UP - Universidade do Porto (https:\/\/doi.org\/10.21747\/978-989-9193-73-4\/lan2), LIACC - Laborat\u00f3rio de Intelig\u00eancia Artificial e Ci\u00eancia de Computadores da Universidade do Porto, CLUP - Centro de Lingu\u00edstica da Universidade do Porto, UEF - The University of Eastern Finland and UAH - Universidad de Alcal\u00e1., Bologna, Italy, 3\u201328. https:\/\/aclanthology.org\/2025.luhme-1.2\/"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sigdial-1.25"},{"key":"e_1_3_3_3_6_2","unstructured":"Uri Berger Gabriel Stanovsky Omri Abend and Lea Frermann. 2025. Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy Trends and Metrics Analysis. arxiv:https:\/\/arXiv.org\/abs\/2408.04909\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2408.04909"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"crossref","unstructured":"Jakub Berka Jan Balata Catholijn\u00a0M Jonker Zdenek Mikovec M\u00a0Birna van Riemsdijk and Myrthe\u00a0L Tielman. 2022. Misalignment in semantic user model elicitation via conversational agents: A case study in navigation support for visually impaired people. International Journal of Human\u2013Computer Interaction 38 18-20 (2022) 1909\u20131925.","DOI":"10.1080\/10447318.2022.2059925"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","unstructured":"Saidarshan Bhagat Padmaja Joshi Avinash Agarwal and Shubhanshu Gupta. 2023. Accessibility evaluation of major assistive mobile applications available for the visually impaired. ITU Journal on Future and Evolving Technologies 4 4 (Dec. 2023) 631\u2013643. 10.52953\/tnrv4696","DOI":"10.52953\/tnrv4696"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481291"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712082"},{"key":"e_1_3_3_3_12_2","unstructured":"Marcella Cornia Matteo Stefanini Lorenzo Baraldi and Rita Cucchiara. 2020. Meshed-Memory Transformer for Image Captioning. arxiv:https:\/\/arXiv.org\/abs\/1912.08226\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1912.08226"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"crossref","unstructured":"Nicole\u00a0M Deterding and Mary\u00a0C Waters. 2021. Flexible coding of in-depth interviews: A twenty-first-century approach. Sociological methods & research 50 2 (2021) 708\u2013739.","DOI":"10.1177\/0049124118799377"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"crossref","unstructured":"Stacy\u00a0A Doore David Istrati Chenchang Xu Yixuan Qiu Anais Sarrazin and Nicholas\u00a0A Giudice. 2024. Images Words and Imagination: Accessible Descriptions to Support Blind and Low Vision Art Exploration and Engagement. Journal of Imaging 10 1 (2024) 26.","DOI":"10.3390\/jimaging10010026"},{"key":"e_1_3_3_3_15_2","unstructured":"Be\u00a0My Eyes. 2020. Be my eyes. Retrieved May 29 (2020)."},{"key":"e_1_3_3_3_16_2","unstructured":"Bhanuka Gamage Thanh-Toan Do Nicholas Seow\u00a0Chiang Price Arthur Lowery and Kim Marriott. 2025. What do Blind and Low-Vision People Really Want from Assistive Smart Devices? Comparison of the Literature with a Focus Study. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.19325 (2025). Available online."},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313605"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642211"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719714"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","unstructured":"Arthur\u00a0C. Graesser Murray Singer and Tom Trabasso. 1994. Constructing inferences during narrative text comprehension. Psychological Review 101 3 (1994) 371\u2013395. 10.1037\/0033-295X.101.3.371","DOI":"10.1037\/0033-295X.101.3.371"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3058555.3058586"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675635"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Helene Joffe. 2012. Thematic analysis. Qualitative research methods in mental health and psychotherapy 1 (2012) 210\u2013223.","DOI":"10.1002\/9781119973249.ch15"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.nlp4pi-1.26"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581532"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","unstructured":"Walter Kintsch. 1988. The role of knowledge in discourse comprehension: A construction-integration model. Psychological Review 95 2 (1988) 163\u2013182. 10.1037\/0033-295X.95.2.163","DOI":"10.1037\/0033-295X.95.2.163"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"crossref","unstructured":"Bineeth Kuriakose Raju Shrestha and Frode\u00a0Eika Sandnes. 2023. DeepNAVI: A deep learning based smartphone navigation assistant for people with visual impairments. Expert Systems with Applications 212 (2023) 118720.","DOI":"10.1016\/j.eswa.2022.118720"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"crossref","unstructured":"J\u00a0Richard Landis and Gary\u00a0G Koch. 1977. The measurement of observer agreement for categorical data. biometrics (1977) 159\u2013174.","DOI":"10.2307\/2529310"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501966"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"crossref","unstructured":"Maurizio Leotta Fabrizio Mori and Marina Ribaudo. 2023. Evaluating the effectiveness of automatic image captioning for web accessibility. Universal access in the information society 22 4 (2023) 1293\u20131313.","DOI":"10.1007\/s10209-022-00906-7"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663547.3759700"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025483"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","unstructured":"Nora McDonald Sarita Schoenebeck and Andrea Forte. 2019. Reliability and Inter-rater Reliability in Qualitative Research: Norms and Guidelines for CSCW and HCI Practice. Proc. ACM Hum.-Comput. Interact. 3 CSCW Article 72 (Nov. 2019) 23\u00a0pages. 10.1145\/3359174","DOI":"10.1145\/3359174"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.63317\/4696hcm84ehz"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173633"},{"key":"e_1_3_3_3_38_2","unstructured":"Sacha M\u00fcller Ant\u00f3nio Loison Bilel Omrani and Gautier Viaud. 2024. GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering. (2024). arxiv:https:\/\/arXiv.org\/abs\/2409.06595\u00a0[cs.CL]"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.306"},{"key":"e_1_3_3_3_40_2","unstructured":"Helen Petrie Chandra Harrison and Sundeep Dev. 2005. Describing images on the web: a survey of current practice and prospects for the future. Proceedings of Human Computer Interaction International (HCII) 71 2 (2005) 1\u201310."},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","unstructured":"Martin\u00a0J. Pickering and Simon Garrod. 2004. The interactive-alignment model: Developments and refinements. Behavioral and Brain Sciences 27 2 (2004) 212\u2013225. 10.1017\/S0140525X04450055","DOI":"10.1017\/S0140525X04450055"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445040"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584037"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1515\/9781503628243"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"crossref","unstructured":"Mazen Salous Daniel Lange Timo Von\u00a0Reeken Maria Wolters Wilko Heuten Sussane Boll and Larbi Abdenebaoui. 2025. Semi-Automatic BVI Human-Centered Image Conversational Descriptions: Leveraging LLMs and Expert Refinements for Inclusive Visual Accessibility. IEEE Access (2025).","DOI":"10.1109\/ACCESS.2025.3605490"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376404"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471233"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/2856767.2856818"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"crossref","unstructured":"Asahi Ushio Fernando Alva-Manchego and Jose Camacho-Collados. 2023. An Empirical Comparison of LM-based Question and Answer Generation Methods. (2023). arxiv:https:\/\/arXiv.org\/abs\/2305.17002\u00a0[cs.CL]","DOI":"10.18653\/v1\/2023.findings-acl.899"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"crossref","unstructured":"Ankit\u00a0S Varshney Maryam\u00a0E Chougle Chetna\u00a0V Patel and Mahendrasinh\u00a0D Chauhan. 2025. Evaluating usability of \u201cthe smart vision glasses\u201d for individuals who are visually impaired and totally blind. Saudi Journal of Ophthalmology (2025) 10\u20134103.","DOI":"10.4103\/sjopt.sjopt_241_24"},{"key":"e_1_3_3_3_51_2","unstructured":"Oriol Vinyals Alexander Toshev Samy Bengio and Dumitru Erhan. 2015. Show and Tell: A Neural Image Caption Generator. arxiv:https:\/\/arXiv.org\/abs\/1411.4555\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1411.4555"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","unstructured":"Iris Xie Wonchan Choi Shengang Wang Hyun\u00a0Seung Lee Bo\u00a0Hyun Hong Ning-Chiao Wang and Esther\u00a0K. Cudjoe. 2024. Help-Seeking Situations Related to Visual Interactions on Mobile Platforms and Recommended Designs for Blind and Visually Impaired Users. Journal of Imaging 10 8 (2024) 205. 10.3390\/jimaging10080205","DOI":"10.3390\/jimaging10080205"},{"key":"e_1_3_3_3_53_2","volume-title":"International Conference on Machine Learning","author":"Xu Ke","year":"2015","unstructured":"Ke Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron\u00a0C. Courville, Ruslan Salakhutdinov, Richard\u00a0S. Zemel, and Yoshua Bengio. 2015. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:1055111"},{"key":"e_1_3_3_3_54_2","first-page":"417","volume-title":"Nineteenth Symposium on Usable Privacy and Security (SOUPS 2023)","author":"Zhang Zhuohao\u00a0Jerry","year":"2023","unstructured":"Zhuohao\u00a0Jerry Zhang, Smirity Kaushik, JooYoung Seo, Haolin Yuan, Sauvik Das, Leah Findlater, Danna Gurari, Abigale Stangl, and Yang Wang. 2023. { ImageAlly} : A { Human-AI} hybrid approach to support blind people in detecting and redacting private image content. In Nineteenth Symposium on Usable Privacy and Security (SOUPS 2023). 417\u2013436."},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","unstructured":"Rolf\u00a0A. Zwaan and Gabriel\u00a0A. Radvansky. 1998. Situation models in language comprehension and memory. Psychological Bulletin 123 2 (1998) 162\u2013185. 10.1037\/0033-2909.123.2.162","DOI":"10.1037\/0033-2909.123.2.162"}],"event":{"name":"CUI '26: ACM Conversational User Interfaces 2026","location":"Bremen Germany","acronym":"CUI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 8th ACM Conference on Conversational User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3816046.3816207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T11:48:09Z","timestamp":1784634489000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3816046.3816207"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":54,"alternative-id":["10.1145\/3816046.3816207","10.1145\/3816046"],"URL":"https:\/\/doi.org\/10.1145\/3816046.3816207","relation":{},"subject":[],"published":{"date-parts":[[2026,7,21]]},"assertion":[{"value":"2026-07-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}