X-Cluster discovers multiple natural language clustering criteria from unstructured images and groups them accordingly, evaluated on new benchmarks COCO-4C and Food-4C with applications to bias detection and image virality.
If LLMs can discover topics from documents and organize them, then by converting images into text, we can similarly use LLMs to organize unstruc- tured images
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Organizing Unstructured Image Collections using Natural Language
X-Cluster discovers multiple natural language clustering criteria from unstructured images and groups them accordingly, evaluated on new benchmarks COCO-4C and Food-4C with applications to bias detection and image virality.