"Person, Shoes, Tree. Is the Person Naked?" What People with Vision Impairments Want in Image Descriptions
Abigale Stangl, Meredith Ringel Morris, Danna Gurari
摘要
Access to digital images is important to people who are blind or have low vision (BLV). Many contemporary image description efforts do not take into account this population's nuanced image description preferences. In this paper, we present a qualitative study that provides insight into 28 BLV people's experiences with descriptions of digital images from news websites, social networking sites/platforms, eCommerce websites, employment websites, online dating websites/platforms, productivity applications, and e-publications. Our findings reveal how image description preferences vary based on the source where digital images are encountered and the surrounding context. We provide recommendations for the development of next-generation image description technologies inspired by our empirical analysis.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper23
- CLIPScore: A Reference-free Evaluation Metric for Image CaptioningJack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras 等EMNLP 2021 · 被引用 937 次
- "It's Complicated": Negotiating Accessibility and (Mis)Representation in Image Descriptions of Race, Gender, and DisabilityCynthia L. Bennett, Cole Gleason, Morgan Klaus Scheuerman, Jeffrey P. Bigham 等CHI 2021 · 被引用 125 次
- ImageExplorer: Multi-Layered Touch Exploration to Encourage Skepticism Towards Imperfect AI-Generated Image CaptionsJaewook Lee, Jaylin Herskovitz, Yi-Hao Peng, Anhong GuoCHI 2022 · 被引用 55 次
- WorldScribe: Towards Context-Aware Live Visual DescriptionsRuei-Che Chang, Yuxuan Liu, Anhong GuoUIST 2024 · 被引用 54 次
- Investigating Use Cases of AI-Powered Scene Description Applications for Blind and Low Vision PeopleRicardo E. Gonzalez Penuela, Jazmin Collins, Cynthia L. Bennett, Shiri AzenkotCHI 2024 · 被引用 44 次
它引用的顶会 Paper1
相关 Paper
- Accessibility of Profile Pictures: Alt Text and Beyond to Express Identity OnlineMartez E. Mott, John C. Tang, Edward CutrellCHI 2023 · 被引用 6 次
- Examining Visual Semantic Understanding in Blind and Low-Vision Technology UsersVenkatesh Potluri, Tadashi E. Grindeland, Jon E. Froehlich, Jennifer MankoffCHI 2021 · 被引用 42 次
- Communicating Visualizations without Visuals: Investigation of Visualization Alternative Text for People with Visual ImpairmentsCrescentia Jung, Shubham Mehta, Atharva Kulkarni, Yuhang Zhao 等IEEE VIS 2021 · 被引用 2 次
- "It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language ModelsKapil Garg, Xinru Tang, Jimin Heo, Dwayne R. Morgan 等CHI 2026 · 被引用 2 次
- "It's Kind of Context Dependent": Understanding Blind and Low Vision People's Video Accessibility Preferences Across Viewing ScenariosLucy Jiang, Crescentia Jung, Mahika Phutane, Abigale Stangl 等CHI 2024 · 被引用 23 次
