VQA Therapy：通过答案的视觉 grounding 探究答案差异
VQA Therapy: Exploring Answer Differences by Visually Grounding Answers
AI总结：
该研究针对视觉问答中答案存在差异的问题，推出首个提供答案视觉grounding的数据集VQAAnswerTherapy，提出两个相关新任务并基准测试现有算法，为理解答案差异成因提供数据与任务支撑。
摘要：
视觉问答（Visual question answering）是预测与图像相关问题答案的任务。鉴于不同的人对同一视觉问题可能给出不同答案，我们旨在通过答案 grounding 更好地理解差异成因。我们推出首个为每个视觉问题的每个唯一答案提供视觉 grounding 的数据集，命名为VQAAnswerTherapy。随后我们提出两个新问题：预测视觉问题是否仅有单一答案grounding，以及定位所有答案grounding。我们针对这些新问题对现代算法进行基准测试，明确其优势与不足。数据集与评测服务器可在https://vizwiz.org/tasks-and-datasets/vqa-answer-therapy/ 公开获取。
英文摘要：
Visual question answering is a task of predicting the answer to a question about an image. Given that different people can provide different answers to a visual question, we aim to better understand why with answer groundings. We introduce the first dataset that visually grounds each unique answer to each visual question, which we call VQAAnswerTherapy. We then propose two novel problems of predicting whether a visual question has a single answer grounding and localizing all answer groundings. We benchmark modern algorithms for these novel problems to show where they succeed and struggle. The dataset and evaluation server can be found publicly at https://vizwiz.org/tasks-and-datasets/vqa-answer-therapy/.
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。
