We propose Subject-Conditional Relation Detection SCoRD, where condition...
We propose a margin-based loss for vision-language model pretraining tha...
Dataset bias and spurious correlations can significantly impair
generali...
Visual attributes constitute a large portion of information contained in...
A critical problem in deep learning is that systems learn inappropriate
...
Traditionally, deep convolutional neural networks consist of a series of...
Existing Visual Question Answering (VQA) methods tend to exploit dataset...
In lifelong machine learning, a robotic agent must be incrementally upda...
Chart question answering (CQA) is a newly proposed visual question answe...
Language grounded image understanding tasks have often been proposed as ...
Visual Question Answering (VQA) research is split into two camps: the fi...
Most counting questions in visual question answering (VQA) datasets are
...
Bar charts are an effective way for humans to convey information to each...
In visual question answering (VQA), an algorithm must answer text-based
...
Visual Question Answering (VQA) is a recent problem in computer vision a...