Recent VQA models may tend to rely on language bias as a shortcut and thus fail to
sufficiently learn the multi-modal knowledge from both vision and language. In this paper …

Data Augmentation (DA)—generating extra training samples beyond the original training set—
has been widely-used in today's unbiased VQA models to mitigate language biases. Current …

Visual question answering (VQA) is designed to examine the visual-textual reasoning ability
of an intelligent agent. However, recent observations show that many VQA models may only …

Question answering (QA) models are well-known to exploit data bias, eg, the language prior
in visual QA and the position bias in reading comprehension. Recent debiasing methods …

Visual question answering (VQA) is a challenging task, which has attracted more and more
attention in the field of computer vision and natural language processing. However, the …

Our commonsense knowledge about objects includes their typical visual attributes; we know
that bananas are typically yellow or green, and not purple. Text and image corpora, being …

Visual question answering (VQA) is a prevalent task in real-world, and plays an essential
role in helping the blind understand the physical world. However, due to the real-world …

Abstract The task of Visual Question Answering (VQA) is known to be plagued by the issue
of VQA models exploiting biases within the dataset to make its final prediction. Various …

Recent studies have pointed out that many well-developed Visual Question Answering
(VQA) models are heavily affected by the language prior problem. It refers to making …

Abstract Audio-Visual Question Answering (AVQA) is a sophisticated QA task, which aims at
answering textual questions over given video-audio pairs with comprehensive multimodal …