keyword

VizWiz Grand Challenge

The VizWiz Grand Challenge is a recurring computer vision competition and benchmark initiative designed to encourage the development of artificial intelligence algorithms that assist people who are blind or visually impaired. Unlike standard visual question answering benchmarks collected under controlled conditions, the challenge relies on real-world data gathered from visually impaired mobile phone users who take pictures and ask spoken questions about their everyday surroundings. The resulting datasets often feature imperfect, blurry, or poorly framed images paired with conversational queries, and participating models are evaluated on practical assistive tasks such as accurately answering visual questions, recognizing when an image lacks sufficient visual information to be answered, and identifying the image regions providing the answer evidence.

1 item

VizWiz Grand Challenge: Answering Visual Questions from Blind People

Danna Gurari, Qing Li, Abigale J. Stangl, Anhong Guo, Chi Lin, Kristen Grauman, Jiebo Luo, Jeffrey P. Bigham

OrganizationsCarnegie Mellon UniversityUniversity of Colorado BoulderUniversity of RochesterUniversity of Science and Technology of ChinaUniversity of Texas at Austin

Why you should read this

Introduces VizWiz, a dataset of over 31,000 real-world visual questions from blind users that challenges visual question answering models to handle conversational queries, imperfect mobile photos, and unanswerable prompts in genuine assistive settings.

The study of algorithms to automatically answer visual questions currently is motivated by visual question answering (VQA) datasets constructed in artificial VQA settings. We propose VizWiz, the first goal-oriented VQA dataset arising from a natural VQA setting. VizWiz consists of over 31,000 visual questions originating from blind people who each took a picture using a mobile phone and recorded a spoken question about it, together with 10 crowdsourced answers per visual question. VizWiz differs from the many existing VQA datasets because (1) images are captured by blind photographers and so are often poor quality, (2) questions are spoken and so are more conversational, and (3) often visual questions cannot be answered. Evaluation of modern algorithms for answering visual questions and deciding if a visual question is answerable reveals that VizWiz is a challenging dataset. We introduce this dataset to encourage a larger community to develop more generalized algorithms that can assist blind people.

Source

https://arxiv.org/pdf/1802.08218

Added

2026-09-25