From Pixels to Objects: Cubic Visual Attention for Visual Question Answering. (arXiv:2206.01923v1 [cs.CV])

Recently, attention-based Visual Question Answering (VQA) has achieved great
success by utilizing question to selectively target different visual areas that
are related to the answer. Existing visual attention models are generally
planar, i.e., different channels of the last conv-layer feature map of an image
share the same weight. This conflicts with the attention mechanism because CNN
features are naturally spatial and channel-wise. Also, visual attention models
are usually conducted on pixel-level, which may cause region discontinuous
problems. In this paper, …

arxiv attention cv objects question answering visual attention