… to dynamically collocate neural modules on-the-fly during captioning. … of neural modules
for visual reasoning [58, 3]. However, we believe that a combination of simple neural modules …

… in an input image. Inspired by the idea of the compositional neural module networks in the
vi… introduce a hierarchical framework for image captioning that explores both compositionality …

… text according to the input image. In this paper, we … neural network (CNN) as the encoder
and recurrent neural network (RNN) as the decoder. In order to get better image captioning …

… of collocating visual-linguistic modules is more challenging. … collocate the modules during
the process of image captioning. To … : (1) distinguishable module design—four modules in the …

… for image captioning. Instead of offering a comprehensive review of all prior work on deep
image captioning … mechanisms used for the task of image captioning in deep learning models. …

… in the generated captions, and … for image captioning, which factorizes the captioning
procedure into two stages: (1) extracting an explicit semantic representation from the given image; …

… With this in mind, we propose a novel stylized image captioning approach … neural modules
under the reinforcement learning paradigm. A low-level neural module called syntax module …

… In this work we focus on attention models for image captioning. The state-of-the-art … of image
captioning, we evaluated the state-of-the-art models with implicitly trained attention modules…

… Given an image I, the image captioning model needs to generate a caption sequence w =
{w1,w2,...,wT }, … t of the visual LSTM, we apply a neural network to normalize attention weights: …

… Our goal here is to optimize the text generation module of the image captioning model. We
used the RNN architecture as our text generation module and our goal here is to optimize the …