Attention-based neural encoder-decoder frameworks have been widely adopted
for image captioning. Most methods force visual attention to be active for
every generated word. However, the decoder likely requires little to no visual
information from the image to predict non-visual words such as "the" and "of".
Other words that may seem visual can often be predicted reliably just from the
language model e.g., "sign" after "behind a red stop" or "phone" following
"talking on a cell". In this paper, we propose a novel adaptive attention model
with a visual sentinel. At each time step, our model decides whether to attend
to the image (and if so, to which regions) or to the visual sentinel. The model
decides whether to attend to the image and where, in order to extract
meaningful information for sequential word generation. We test our method on
the COCO image captioning 2015 challenge dataset and Flickr30K. Our approach
sets the new state-of-the-art by a significant margin.

本文提出了一种新的自适应注意力模型，具有视觉哨兵，在每个时间步骤，模型决定是关注图像还是关注视觉哨兵，通过这种方式针对性地提取有意义的信息以生成图像字幕，实验证明我们的方法在 COCO 图像字幕 2015 年挑战数据集和 Flickr30K 上的效果优越并创造了新的最佳表现。