Papers with relationship based attention

1 papers
Building Joint Relationship Attention Network for Image-Text Generation (2022.coling-1)

Copied to clipboard

Challenge: et al., 2017) focus on visual features individually, while ignoring relationship information among image features that provides important guidance for generating sentences.
Approach: They propose a joint relationship attention network that explores the relationships among image features.
Outcome: The proposed method achieves state-of-the-art performance on large-scale datasets and on Flickr30k datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations