A feedback fine-tuning method adds detector-based pose, interaction, identity, and gaze losses, time-gated by noise level, to SSR-Encoder, reporting modest gains on HICO-DET, GazeFollow, and Concept101.
Svdiff: Compact parameter space for diffusion fine-tuning
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
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Improving Personalized Image Generation through Social Context Feedback
A feedback fine-tuning method adds detector-based pose, interaction, identity, and gaze losses, time-gated by noise level, to SSR-Encoder, reporting modest gains on HICO-DET, GazeFollow, and Concept101.