Fine-tuning CLIP with LoRA and fusing its embeddings with an adapted face recognition network reduces equal error rate on the Historical Faces dataset to 9.9%.
Proto-early renaissance depictions, iconographic analysis and computerised facial similarity as- sessment connections: The 16th century mural paintings of st
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
ArtFace: Towards Historical Portrait Face Identification via Model Adaptation
Fine-tuning CLIP with LoRA and fusing its embeddings with an adapted face recognition network reduces equal error rate on the Historical Faces dataset to 9.9%.