Pre-gen metrics: Predicting caption quality metrics without generating captions

10/12/2018
by   Marc Tanti, et al.
0

Image caption generation systems are typically evaluated against reference outputs. We show that it is possible to predict output quality without generating the captions, based on the probability assigned by the neural model to the reference captions. Such pre-gen metrics are strongly correlated to standard evaluation metrics.

READ FULL TEXT
research
07/31/2023

Guiding Image Captioning Models Toward More Specific Captions

Image captioning is conventionally formulated as the task of generating ...
research
07/13/2021

Between Flexibility and Consistency: Joint Generation of Captions and Subtitles

Speech translation (ST) has lately received growing interest for the gen...
research
12/01/2016

Improved Image Captioning via Policy Gradient optimization of SPIDEr

Current image captioning methods are usually trained via (penalized) max...
research
06/26/2015

Humor in Collective Discourse: Unsupervised Funniness Detection in the New Yorker Cartoon Caption Contest

The New Yorker publishes a weekly captionless cartoon. More than 5,000 r...
research
07/29/2016

SPICE: Semantic Propositional Image Caption Evaluation

There is considerable interest in the task of automatically generating i...
research
10/22/2022

On the Limitations of Reference-Free Evaluations of Generated Text

There is significant interest in developing evaluation metrics which acc...
research
07/31/2020

Evaluating Automatically Generated Phoneme Captions for Images

Image2Speech is the relatively new task of generating a spoken descripti...

Please sign up or login with your details

Forgot password? Click here to reset