FaceInsight, an MLLM with segmentation inputs, correlation priors, and logic rules, reports higher face-attribute, age/gender/race, and expression accuracy than nine general MLLMs across six benchmarks.
Visual instruction tuning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FaceInsight: A Multimodal Large Language Model for Face Perception
FaceInsight, an MLLM with segmentation inputs, correlation priors, and logic rules, reports higher face-attribute, age/gender/race, and expression accuracy than nine general MLLMs across six benchmarks.