Papers with USPL

1 papers
Unsupervised Sounding Pixel Learning (2023.emnlp-main)

Copied to clipboard

Challenge: Sounding source localization is a challenging task due to the difficulty of cross-modal alignment.
Approach: They propose an unsupervised method which enables pixel-level sounding source localization in unsupervised paradigm.
Outcome: The proposed method achieves pixel-level sounding source localization without annotations.

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