Proposes the SFR framework and InfoSqueeze module to resolve Interest Entanglement by decoupling regression and perceptual objectives in image super-resolution through shared feature representations.
A 3Lign-DFER: Pioneering comprehensive dynamic affective alignment for dynamic facial expression recognition with clip
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
citing papers explorer
-
Interest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization
Proposes the SFR framework and InfoSqueeze module to resolve Interest Entanglement by decoupling regression and perceptual objectives in image super-resolution through shared feature representations.
- Bidirectional Learning of Facial Action Units and Expressions via Structured Semantic Mapping across Heterogeneous Datasets