Jun 3, 2021 · A recent corpus analysis of real-world captions reveals that machine figure captioning systems should start by generating accurate caption units.
In this work, we aim to generate accurate caption units of a wide variety of caption types, including title, figure type, count, label name, min/max, ...
Data and supplementary materials for the Web Conference 2021 paper "Generating Accurate Caption Units For Figure Captioning".
This paper introduces SCICAP, a large-scale figure-caption dataset based on computer science arXiv papers published between 2010 and 2020.
People also ask
How do you make a good figure caption?
What are the elements of a good figure caption?
When providing a caption for a figure where is the caption placed?
How long should a figure caption be?
We implement ECR using the optimized ICICD dataset, a subset of the sensor-oriented Flickr30K-EE dataset containing comprehensive inference chain information.
This work crawled, annotated, and analyzed a corpus of real-world human-written figure captions, showing that real- world captions usually consist of a finite ...
One method to design captions is to use a font size one or two sizes smaller than for the report itself. This example from [4-SUNG] shows that practice, wherein ...
In this paper, we argue that figure captioning in scientific documents can be more effectively tack- led as a text-summarization task: The caption can be ...
Jun 30, 2023 · A new tool helps scientists develop machine-learning models that generate richer, more detailed captions for charts, and vary the level of complexity of a ...
Oct 25, 2021 · In this paper, we propose an end-to-end neural framework to automatically generate informa- tive, high-quality captions for scientific figures.