VizWiz: nearly real-time answers to visual questions

By Jeffrey P. Bigham, Chandrika Jayant, H. Ji, Greg Little, Andrew Miller, Rob Miller, Aubrey Tatarowicz, Brandyn Allen White, Samuel White, Tom Yeh. 2010

918 citations recorded by the source corpus.

Subfields: Computer Science Applications, Computer Vision and Pattern Recognition, Human Factors and Ergonomics, Multimodal Learning, Question Answering & Reading Comprehension

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Science Applications

In Computer Vision and Pattern Recognition

In Human Factors and Ergonomics

In Multimodal Learning

In Question Answering & Reading Comprehension

Citations in the corpus

TAP: Text-Aware Pre-training for Text-VQA and Text-Caption (2020, methodology): “The Vision-language tasks incorporating scene text [7, 18, 49, 46], e.”
VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning (2021, background): “In addition to its scientific value, the task finds practical applications such as facilitating people with impaired vision [7, 11] and generating medical imaging reports under human supervision [47, 10].”
VizWiz Grand Challenge: Answering Visual Questions from Blind People (2018, methodology): “Such VQA systems have been shown to be valuable for many daily tasks including grocery shopping [8], locating a specific object in a complex scene [9], and choosing clothes to wear [11].”
Visual Dialog (2016, background): “• Aiding visually impaired users in understanding their surroundings [5] or social media content [58] (AI: ‘John just uploaded a picture from his vacation in Hawaii’, Human: ‘Great, is he at the beach?’, AI: ‘No, on a mountain’).”
VQA: Visual Question Answering (2015, background): “[2] created an application that allows the visually impaired to capture images and ask open-ended questions that are answered by human subjects.”
Visual7W: Grounded Question Answering in Images (2015, background): “Visual question answering is a natural extension to the captioning tasks, but is more interactive and has a stronger connection to real-world applications [3].”
Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question (2015, background): “There has been recent effort on the visual question answering task [9, 2, 22, 37].”
Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning (2017, background): “We believe the next generation of intelligent systems will need to posses this ability to hold a dialog about visual content for a variety of applications: e.g ., helping visually impaired users understand their surroundings [ 3] or social media content [40] ( ‘Who is in the photo?”
Grounded Video Description (2018, background): “This makes models less accountable and trustworthy, which is important if we hope such models will eventually assist people in need [2, 27].”
A qualitative study to support a blind photography mobile application (2013, methodology): “VizWiz, which utilizes VizWiz::LocateIt’s object location techniques, allows users to snap a photo of their environment, and returns a textual description of that photo in almost real-time [7].”
Artificial Intelligence and Collective Intelligence (2014, background): “We may able to obtain near instantaneous work if we preemploy several workers so that, as work arrives, they are already waiting to work on it (Bigham et al. 2010).”
OpenVLA: An Open-Source Vision-Language-Action Model (2024, background): “…Language Models Visually-conditioned language models (VLMs), which are trained on Internet-scale data to generate natural language from input image(s) and language prompts, have been adopted for myriad applications from visual question answering [28–31] to object localization [32, 33].”