A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions

arXiv:2403.17545v1 Announce Type: cross
Abstract: Situated conversations, which refer to visual information as visual question answering (VQA), often contain ambiguities caused by reliance on directive information. This problem is exacerbated because some languages, such as Japanese, often omit subjective or objective terms. Such ambiguities in questions are often clarified by the contexts in conversational situations, such as joint attention with a user or user gaze information. In this study, we propose the Gaze-grounded VQA dataset (GazeVQA) that clarifies ambiguous questions …

abstract arxiv conversations cs.cl cs.cv dataset information japanese languages question question answering questions reliance terms type visual vqa