Research map / Video / Video segmentation and tracking
StressID: a Multimodal Dataset for Stress Identification
Hava Chaptoukaev, Valeriya Strizhkova, Michele Panariello, Bianca Dalpaos, Aglind Reka, Valeria Manera, Susanne Thummler, Esma ISMAILOVA, Nicholas Evans, Francois Bremond, Massimiliano Todisco, Maria A Zuluaga and 1 more
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 |
|---|---|---|---|
| decision-level fusion (SVM + average rule) of three modalities instead of best unimodal | stress classifiers · StressID 2-class, 370 tasks | weighted F1: 0.67 ± 0.03 -> 0.72 ± 0.05 | Improved |
| decision-level fusion (SVM + average rule) instead of best unimodal | stress classifiers · StressID 3-class, 370 tasks | weighted F1: 0.58 ± 0.05 -> 0.63 ± 0.05 | Improved |
| feature-level fusion with DBN instead of unimodal | stress classifiers · StressID 3-class, 370 tasks | weighted F1: 0.58 ± 0.05 -> 0.30 ± 0.09 | Hurt |
| feature-level fusion with SVM instead of best unimodal | stress classifiers · StressID 2-class, 370 tasks | weighted F1: 0.67 ± 0.04 -> 0.64 ± 0.09 | No clear effect |
| feature-level fusion with MLP instead of best unimodal | stress classifiers · StressID 2-class, 370 tasks | weighted F1: 0.67 ± 0.04 -> 0.66 ± 0.04 | No clear effect |
| use RF instead of MLP on physiological handcrafted features | physiological baseline · StressID 2-class | weighted F1: 0.70 ± 0.03 -> 0.73 ± 0.02 | No clear effect |
| use W2V 2.0 embeddings instead of handcrafted audio features with SVM | audio baseline · StressID 2-class | weighted F1: 0.61 ± 0.06 -> 0.70 ± 0.02 | Improved |
Closest papers by meaning
- FEEL: Quantifying Heterogeneity in Physiological Signals for Generalizable Emotion Recognition (NeurIPS 2025 · similarity 0.84)
- EEVR: A Dataset of Paired Physiological Signals and Textual Descriptions for Joint Emotion Representation Learning (NeurIPS 2024 · similarity 0.83)
- Thousand Voices of Trauma: A Large-Scale Synthetic Dataset for Modeling Prolonged Exposure Therapy Conversations (NeurIPS 2025 · similarity 0.83)
- Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing (NeurIPS 2025 · similarity 0.82)
- Unraveling Pain Levels: A Data-Uncertainty Guided Approach for Effective Pain Assessment (AAAI 2024 · similarity 0.81)
- CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models (ICML 2025 · similarity 0.81)
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.
