MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.
DOC : Deep Open Classification of Text Documents
2 Pith papers cite this work, alongside 325 external citations. Polarity classification is still indexing.
2
Pith papers citing it
325
external citations · OpenAlex
representative citing papers
Introduces OW-SED paradigm and WOOT framework with deformable attention for detecting known and unseen sound events in open-world settings.
citing papers explorer
-
Demystifying CLIP Data
MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.
-
Towards Open World Sound Event Detection
Introduces OW-SED paradigm and WOOT framework with deformable attention for detecting known and unseen sound events in open-world settings.