How to Describe Images in a More Funny Way? Towards a Modular Approach to Cross-Modal Sarcasm Generation.

Jie Ruan Yue Wu Xiaojun Wan Yuesheng Zhu

Published in: CoRR (2022)

Keyphrases

cross modal
image data
image retrieval
image database
multi modal
object recognition
image features
visual data
test images
image set
image collections
perceptual information
image understanding
content based retrieval
similarity measure
spatial information
multimedia retrieval
visual similarity
image regions