Research map / Probabilistic and scientific modeling / Variational and generative sampling
DeepCoder: Semi-Parametric Variational Autoencoders for Automatic Facial Action Coding
Dieu Linh Tran, Robert Walecki, Ognjen (Oggi) Rudovic, Stefanos Eleftheriadis, Bjorn Schuller, Maja Pantic
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace the parametric top layer with a GP (VO-GPAE) bottom layer (semi-parametric 2DC vs DCp) (ablation) | DeepCoder · DISFA (12 AUs, avg) | ICC: .43 -> .50 | Improved |
| replace the parametric top layer with a GP (VO-GPAE) bottom layer (semi-parametric 2DC vs DCp) (ablation) | DeepCoder · FERA2015 (5 AUs, avg) | ICC: .63 -> .66 | Improved |
| replace the parametric top layer with a GP (VO-GPAE) bottom layer (semi-parametric 2DC vs DCp) (ablation) | DeepCoder · DISFA (12 AUs, avg) | MSE: .40 -> .37 | Improved |
| replace the parametric top layer with a GP (VO-GPAE) bottom layer (semi-parametric 2DC vs DCp) (ablation) | DeepCoder · FERA2015 (5 AUs, avg) | MSE: 1.05 -> .95 | Improved |
| use ordinal one-binary-classifier-per-level head (OR-CNN) instead of the plain CNN head | CNN · DISFA (12 AUs, avg) | ICC: .44 -> .36 | Hurt |
| add the warming strategy for the variational lower bound (ablation) | DeepCoder VO-GPAE · FERA2015 | variational lower bound | Improved |
| replace GP on deep features with the semi-parametric DeepCoder | GP (deep features) · DISFA (12 AUs, avg) | ICC: .28 -> .50 | Improved |
Closest papers by meaning
- Deep Structured Learning for Facial Action Unit Intensity Estimation (CVPR 2017 · similarity 0.90)
- Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation (CVPR 2018 · similarity 0.89)
- Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation (CVPR 2019 · similarity 0.89)
- Deep Facial Action Unit Recognition From Partially Labeled Data (ICCV 2017 · similarity 0.88)
- Dual Semi-Supervised Learning for Facial Action Unit Recognition (AAAI 2019 · similarity 0.88)
- AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
