@inproceedings{kim-etal-2026-guidedog,
    title = "{G}uide{D}og: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance",
    author = "Kim, Junhyeok  and
      Park, Jaewoo  and
      Park, Junhee  and
      Lee, Sangeyl  and
      Chung, Jiwan  and
      Kim, Jisung  and
      Joung, Ji Hoon  and
      Yu, Youngjae",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.251/",
    pages = "5545--5574",
    ISBN = "979-8-89176-390-6",
    abstract = "For people affected by blindness and low vision (BLV), safe and independent navigation remains a major challenge, impacting over 2.2 billion individuals worldwide. Although multimodal large language models (MLLMs) offer new opportunities for assistive navigation, progress has been limited by the scarcity of accessibility-aware datasets, requiring labor-intensive, expert annotation. To this end, we introduce GuideDog, a novel dataset containing 22K image-description pairs (2K human-verified) capturing real-world pedestrian scenes across 46 countries. Our human-AI pipeline shifts annotation from generation to verification, grounded in established BLV guidance standards from experts and research, improving scalability while maintaining quality. We also present GuideDogQA, an 818-sample benchmark evaluating object recognition and depth perception. Experiments reveal that depth perception and adherence to these standards remain challenging for current MLLMs. Code and dataset will be publicly available."
}