Papers with cross-modal transformer architecture

1 papers
Joint Multimedia Event Extraction from Video and Article (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to extract multimedia events from video and text are limited to video and images.
Approach: They propose a task to jointly extract events from video and text documents . they propose 'self-supervised' cross-modal event coreference model and cross-mod transformer architecture .
Outcome: The proposed method achieves 6.0% and 5.8% absolute F-score gain on video-article pairs . the proposed method can resolve coreference and extract multimodal event frames more accurately than existing methods.

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