A single face-landmark model can train on multiple differently annotated datasets and output arbitrary queryable landmarks by representing each landmark as a normalized position along a face part contour.
Burgos-Artizzu, Pietro Perona, and Piotr Dollár
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
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Towards Unified Dynamic Face Landmark Detection
A single face-landmark model can train on multiple differently annotated datasets and output arbitrary queryable landmarks by representing each landmark as a normalized position along a face part contour.