Research map / Video / Action recognition
Affective Processes: Stochastic Modelling of Temporal Context for Emotion and Facial Expression Recognition
Enrique Sanchez, Mani Kumar Tellamekala, Michel Valstar, Georgios Tzimiropoulos
Check 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 |
|---|---|---|---|
| Add stochastic temporal context modelling with Affective Processes | Backbone emotion recognition · SEWA test | CCC (mean): 0.65 -> 0.69 | Improved |
| Add Affective Processes temporal context modelling | Backbone emotion recognition · Aff-Wild2 validation | CCC (mean): 0.422 -> 0.468 | Improved |
| Add Affective Processes temporal context modelling | Backbone AU intensity estimation · DISFA | ICC (average): 0.56 -> 0.58 | Improved |
| Add Affective Processes temporal context modelling | Backbone AU intensity estimation · BP4D test | ICC (average): 0.67 -> 0.74 | Improved |
| Add task-specific backbone predictions as pseudo-labels to context inputs (ablation) | Affective Processes · SEWA validation | CCC (mean): 0.527 -> 0.635 | Improved |
| Add a sampled global latent variable instead of a deterministic representation (ablation) | Affective Processes · SEWA validation | CCC (mean): 0.613 -> 0.635 | Improved |
| Use negative log-likelihood plus regularization, without KL loss (ablation) | Affective Processes · SEWA validation | CCC (mean): 0.635 -> 0.662 | Improved |
| Add KL loss to negative log-likelihood and regularization (ablation) | Affective Processes · SEWA validation | CCC (mean): 0.662 -> 0.635 | Hurt |
| Add a deterministic layer to Affective Processes (ablation) | Affective Processes · SEWA validation | CCC (mean): 0.635 -> 0.652 | No clear effect |
| Add self-attention to AP + Det. (ablation) | Affective Processes · SEWA validation | CCC (mean): 0.652 -> 0.667 | Improved |
Closest papers by meaning
- FEEL: Quantifying Heterogeneity in Physiological Signals for Generalizable Emotion Recognition (NeurIPS 2025 · similarity 0.89)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.88)
- AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition (NeurIPS 2026 · similarity 0.87)
- Robust Emotion Recognition in Context Debiasing (CVPR 2024 · similarity 0.86)
- OUS: Bridging Scene Context and Facial Features to Overcome the Rigid Cognitive Problem (AAAI 2025 · similarity 0.86)
- OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition (ICML 2025 · 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.
