Object detection, scene graph generation and region captioning, which are three scene
understanding tasks at different semantic levels, are tied together: scene graphs are …

We introduce the dense captioning task, which requires a computer vision system to both
localize and describe salient regions in images in natural language. The dense captioning …

Chinese image description generation tasks usually have some challenges, such as single-
feature extraction, lack of global information, and lack of detailed description of the image …

We propose a new generative language model for sentences that first samples a prototype
sentence from the training corpus and then edits it into a new sentence. Compared to …

In this work we focus on the problem of image caption generation. We propose an extension
of the long short term memory (LSTM) model, which we coin gLSTM for short. In particular …

As the intermediate level task connecting image captioning and object detection, visual
relationship detection started to catch researchers' attention because of its descriptive power …

Automatically describing the content of an image has been attracting considerable research
attention in the multimedia field. To represent the content of an image, many approaches …

In recent years, considerable research has been dedicated to the application of neural
models in the field of natural language generation (NLG). The primary objective is to …

For the task of generating complex outputs such as source code, editing existing outputs can
be easier than generating complex outputs from scratch. With this motivation, we propose an …

This paper explores image caption generation using conditional variational auto-encoders
(CVAEs). Standard CVAEs with a fixed Gaussian prior yield descriptions with too little …