Human pose similarity matching with spatial verification outperforms standard content-based image retrieval for discovering composition transfers in art on a manually annotated dataset.
Recognizing image style
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
Self-supervised backbones such as DINO and CLIP provide consistent improvements over supervised models for artwork classification and retrieval tasks.
citing papers explorer
-
Linking Art through Human Poses
Human pose similarity matching with spatial verification outperforms standard content-based image retrieval for discovering composition transfers in art on a manually annotated dataset.
-
Harnessing Self-Supervised Features for Art Classification
Self-supervised backbones such as DINO and CLIP provide consistent improvements over supervised models for artwork classification and retrieval tasks.