Context-VQA：迈向上下文感知且有目的的视觉问答
Context-VQA: Towards Context-Aware and Purposeful Visual Question Answering
AI总结：
本研究提出Context-VQA数据集，将图像与网站类型配对，证明上下文显著影响问题类型，强调VQA模型需上下文感知以满足用户需求。
摘要：
视觉问答（VQA）有潜力以交互方式使互联网更易于访问，使无法看到图像的人能够就其提出问题。然而，多项研究表明，盲人或低视力者更倾向于包含图像出现上下文的图像解释，而当前的VQA数据集仅关注孤立图像。我们认为，除非考虑上下文，否则VQA模型无法完全满足人们的需求。为了进一步激励和分析不同上下文之间的区别，我们引入了Context-VQA，这是一个将图像与上下文（特别是网站类型，如购物网站）配对的数据集。我们发现，问题类型在不同上下文中系统性变化。例如，在旅行上下文中呈现的图像产生“哪里？”问题的频率是平均值的2倍，而在社交媒体和新闻上的图像产生“谁？”问题的频率分别是平均值的2.8倍和1.8倍。我们还发现，当参与者无法看到图像时，上下文效应尤为重要。这些结果表明，上下文影响所问问题的类型，VQA模型应对上下文敏感，以更好地满足人们的需求，特别是在无障碍设置中。
英文摘要：
Visual question answering (VQA) has the potential to make the Internet more accessible in an interactive way, allowing people who cannot see images to ask questions about them. However, multiple studies have shown that people who are blind or have low-vision prefer image explanations that incorporate the context in which an image appears, yet current VQA datasets focus on images in isolation. We argue that VQA models will not fully succeed at meeting people's needs unless they take context into account. To further motivate and analyze the distinction between different contexts, we introduce Context-VQA, a VQA dataset that pairs images with contexts, specifically types of websites (e.g., a shopping website). We find that the types of questions vary systematically across contexts. For example, images presented in a travel context garner 2 times more "Where?" questions, and images on social media and news garner 2.8 and 1.8 times more "Who?" questions than the average. We also find that context effects are especially important when participants can't see the image. These results demonstrate that context affects the types of questions asked and that VQA models should be context-sensitive to better meet people's needs, especially in accessibility settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
