It has been shown that network pruning ( Han et al., 2015) is an effective technique to reduce the

We follow the same architectural hyperparameters as in V eli ˇ ckovi c et al. We adopt hypothesis testing to quantify the uncertainty of a model's prediction. Acc (ans) = min{ (#human that said ans)/ 3, 1}. By stacking MCA layers, MCAN enables deep interactions between the question and image features. We conduct experiments on an attention-based model for image captioning, Att2in, in Rennie et al.

Most current models use deterministic attention modules due to their simplicity and ease of optimization. Stochastic counterparts, on the other hand, are less popular despite their potential benefits.

Despite recent success of rasterized image generation and content creation, little effort has been directed towards generation of vector graphics. Y et, vector images, often in the form of Scalable V ector Graphics [20] (SVG), have become a standard in digital graphics, publication-ready image assets, and web-animations. The main advantage over their rasterized counterpart is their scaling ability, making the same image file suitable for both tiny web-icons or billboard-scale graphics.

We evaluate the performance of DMFA on a synthetic and two real large-scale fMRI datasets.