Grounding Answers for Visual Questions Asked by Visually Impaired People

Grounding Answers for Visual Questions Asked by Visually Impaired People
复制标题

视障人士提出的视觉问题的基础答案

DOI:
--
复制
发表时间:
2022
期刊:
Computer Vision and Pattern Recognition
影响因子:
--
通讯作者:
D. Gurari
D. Gurari
中科院分区:
--
文献类型:
--
作者:
Chongyan Chen;Samreen Anjum;D. Gurari

文献摘要

参考文献

被引文献

相似文献

视觉问答是回答关于图像的问题的任务。我们介绍了VizWiz-VQA-Grounding数据集,这是第一个在视觉上为视觉障碍人士提出的视觉问题提供答案的数据集。我们分析了我们的数据集,并将其与五个VQA接地数据集进行了比较,以证明是什么使它相似和不同。然后,我们评估的SOTA VQA和VQA接地模型,并证明,目前的SOTA算法往往无法识别正确的视觉证据的答案位于。当视觉证据占据图像的一小部分时,这些模型经常会遇到困难,例如图像质量更高,以及需要文本识别技能的视觉问题。数据集、评估服务器和排行榜都可以在以下链接中找到:https://vizwiz.org/tasks-and-datasets/answer-grounding-for-vqa/。
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/.
DOI: 10.1109/cvpr.2018.00380
发表时间: 2018-02
期刊: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
D. Gurari;Qing Li;Abigale Stangl;Anhong Guo;Chi Lin;K. Grauman;Jiebo Luo;Jeffrey P. Bigham
通讯作者: D. Gurari;Qing Li;Abigale Stangl;Anhong Guo;Chi Lin;K. Grauman;Jiebo Luo;Jeffrey P. Bigham
DOI: 10.1145/3517384
发表时间: 2022
影响因子: 2.4
作者:
Stangl, Abigale;Shiroma, Kristina;Davis, Nathan;Xie, Bo;Fleischmann, Kenneth R.;Findlater, Leah;Gurari, Danna
通讯作者: Gurari, Danna