Research map / Graph learning / Knowledge and temporal graphs
Dynamic Probabilistic Graph Convolution for Facial Action Unit Intensity Estimation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add temporal LSTM modeling (ablation) | ResNet50 AU estimator · FERA 2015 | ICC(3,1), average: .68 -> .69 | Helped |
| add temporal LSTM modeling (ablation) | ResNet50 AU estimator · FERA 2015 | MAE, average: .64 -> .62 | Helped |
| add temporal LSTM modeling (ablation) | ResNet50 AU estimator · DISFA | ICC(3,1), average: .51 -> .52 | Helped |
| add temporal LSTM modeling (ablation) | ResNet50 AU estimator · DISFA | MAE, average: .35 -> .27 | Helped |
| use probabilistic graph convolution instead of a maximum-posterior graph (ablation) | DPG · FERA 2015 | ICC(3,1), average: .70 -> .72 | Helped |
| use probabilistic graph convolution instead of a maximum-posterior graph (ablation) | DPG · FERA 2015 | MAE, average: .58 -> .57 | Helped |
| use probabilistic graph convolution instead of a maximum-posterior graph (ablation) | DPG · DISFA | ICC(3,1), average: .53 -> .56 | Helped |
| use probabilistic graph convolution instead of a maximum-posterior graph (ablation) | DPG · DISFA | MAE, average: .26 -> .22 | Helped |
| use probabilistic graph convolution instead of a deterministic prior-knowledge graph (ablation) | DPG · FERA 2015 | ICC(3,1), average: .70 -> .72 | Helped |
| use probabilistic graph convolution instead of a deterministic prior-knowledge graph (ablation) | DPG · FERA 2015 | MAE, average: .59 -> .57 | Helped |
| use probabilistic graph convolution instead of a deterministic prior-knowledge graph (ablation) | DPG · DISFA | ICC(3,1), average: .54 -> .56 | Helped |
| use probabilistic graph convolution instead of a deterministic prior-knowledge graph (ablation) | DPG · DISFA | MAE, average: .26 -> .22 | Helped |
Closest papers by meaning
- Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation (CVPR 2018 · similarity 0.92)
- Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution (AAAI 2020 · similarity 0.92)
- Uncertain Graph Neural Networks for Facial Action Unit Detection (AAAI 2021 · similarity 0.90)
- Deep Structured Learning for Facial Action Unit Intensity Estimation (CVPR 2017 · similarity 0.89)
- Trend-Aware Supervision: On Learning Invariance for Semi-supervised Facial Action Unit Intensity Estimation (AAAI 2024 · similarity 0.87)
- AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement (CVPR 2024 · similarity 0.87)
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.