Controlling Length in Image Captioning

Abstract

We develop and evaluate captioning models that allow control of caption length. Our models can leverage this control to generate captions of different style and descriptiveness.

References in corpus (4)

• Controlling Output Length in Neural Encoder-Decoders
• Controllable Abstractive Summarization
• Positional Encoding to Control Output Sequence Length
• Improving Reinforcement Learning Based Image Captioning with Natural Language Prior

Cited by in corpus (2)

• Self-Annotated Training for Controllable Image Captioning
• Denoising Large-Scale Image Captioning from Alt-text Data using Content Selection Models