Grounding Answers for Visual Questions Asked by Visually Impaired People
By Chongyan Chen, Samreen Anjum, Danna Gurari. 2022
67 citations recorded by the source corpus.
Visual question answering is the task of answering questions about images. We introduce the VizWiz-VQA-Grounding dataset, the first dataset that visually grounds answers to visual questions asked by people with visual impairments. We analyze our dataset and compare it with five VQA-Grounding datasets to demonstrate what makes it similar and different. We then evaluate the SOTA VQA and VQA-Grounding models and demonstrate that current SOTA algorithms often fail to identify the correct visual evidence where the answer is located. These models regularly struggle when the visual evidence occupies a small fraction of the image, for images that are higher quality, as well as for visual questions that require skills in text recognition. The dataset, evaluation server, and leader-board all can be found at the following link: https://vizwiz.org/tasks-and-datasets/answer-grounding-for-vqa/.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Question Answering & Reading Comprehension, Human-Computer Interaction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Aniruddha Kembhavi
- Roozbeh Mottaghi
- Jianfeng Gao
- Yejin Choi
- Rowan Zellers
- Luke S. Zettlemoyer
- Christopher Clark
In Computer Vision and Pattern Recognition
- Jitendra Malik
- Luc Van Gool
- Trevor Darrell
- Kristen Grauman
- Dacheng Tao
- Abhinav Kumar Gupta
- Xiaogang Wang
- Cordelia Schmid
In Question Answering & Reading Comprehension
In Human-Computer Interaction
- Dandan Shan
- Dima Damen
- David F. Fouhey
- Amlan Kar
- Roozbeh Mottaghi
- Sanja Fidler
- Jitendra Malik
- Louis-philippe Morency
Citations in the corpus
- EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations (2022, methodology): “In [15], the aim is to find the previous encounter of the object itself and [9] aims to ground the object in a single image.”
- Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks (2022, methodology): “We encode sparse structures such as bounding boxes or human joints by adding 1000 special tokens to the vocabulary to represent discretized image coordinates (Chen et al., 2022b).”