MEDN splits micro-expression video features into an Action-Unit-supervised motion branch and a sparse-attention emotion branch, then fuses them, reporting improved SAMM and CAS(ME)3 results—but the decoupling loss is mathematically flawed.
Can we get rid of handcrafted feature extractors? sparsevit: Nonsemantics- centered, parameter-efficient image manipulation localization through spare-coding transformer
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
-
MEDN: Motion-Emotion Feature Decoupling Network for Micro-Expression Recognition
MEDN splits micro-expression video features into an Action-Unit-supervised motion branch and a sparse-attention emotion branch, then fuses them, reporting improved SAMM and CAS(ME)3 results—but the decoupling loss is mathematically flawed.
- The Courtroom Trial of Pixels: Robust Image Manipulation Localization via Adversarial Evidence and Reinforcement Learning Judgment