# FUSE: Frame-Unified Stress Estimation from Facial Video

arXiv: https://arxiv.org/abs/2608.10442 · HTML: https://mlsanity.com/paper/2608.10442/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Twins-PainViT: Towards a Modality-Agnostic Vision Transformer Framework for Multimodal Automatic Pain Assessment using Facial Videos and fNIRS](https://mlsanity.com/paper/2407.19809/) (2024)
- [A Full Transformer-based Framework for Automatic Pain Estimation using Videos](https://mlsanity.com/paper/2412.15095/) (2024)
- [Efficient Pain Recognition via Respiration Signals: A Single Cross-Attention Transformer Multi-Window Fusion Pipeline](https://mlsanity.com/paper/2507.21886/) (2025)
- [PainFormer: a Vision Foundation Model for Automatic Pain Assessment](https://mlsanity.com/paper/2505.01571/) (2025)
- [Multi-Representation Diagrams for Pain Recognition: Integrating Various Electrodermal Activity Signals into a Single Image](https://mlsanity.com/paper/2507.21881/) (2025)
- [Tiny-BioMoE: a Lightweight Embedding Model for Biosignal Analysis](https://mlsanity.com/paper/2507.21875/) (2025)
- [ReFace: Reorganizing Facial Spatiotemporal Representations for Improved Pain Assessment](https://mlsanity.com/paper/2607.19722/) (2026)
- [Explainable graph attention network for stress recognition (StressGAT) via differential action units](https://mlsanity.com/paper/2607.20819/) (2026)
- [Towards a Unified Modality-Agnostic Multimodal Framework for Cognitive Workload Assessment](https://mlsanity.com/paper/2609.20199/) (2026)
- [Combining Facial Videos and Biosignals for Stress Estimation During Driving](https://mlsanity.com/paper/2601.04376/) (2026)
- [Beyond the Raw Waveform: Fusing Visual Representations of EDA for Stress Detection](https://mlsanity.com/paper/2609.22095/) (2026)
- [A Multi-Scale Temporal Framework with Dynamic Fusion for EEG-Based Emotion Recognition](https://mlsanity.com/paper/2608.09088/) (2026)

## Abstract (arXiv)

Automatic stress detection from facial video offers a practical path to non-intrusive affect monitoring, yet existing video-based approaches commonly decompose full recordings into short temporal windows before classification. This design introduces additional choices regarding window length, overlap, and aggregation, while limiting direct analysis of temporal information across the entire recording. In this study, we present FUSE (Frame-Unified Stress Estimation), a facial-video stress detection framework that processes complete recordings as a single input without temporal windowing or external segmentation. The name reflects the defining operation of the method: rather than dividing a recording into short clips, all frames are fused into one unified two-dimensional representation from which the stress state is estimated. This unification is realized by folding the temporal dimension into the channel dimension of the spatial representation, and the resulting high-dimensional input is processed using a unified asymmetric-attention architecture. At a temporal stride of t = 1, FUSE retains the full 120-second recording as one input, corresponding to 3,600 frames at 30 fps. Experiments on a 58-subject stress dataset using a stratified subject-level protocol evaluate seven temporal-stride configurations, ranging from full-frame input to sparse subsampling. FUSE achieves the highest test accuracy of 69.44% at t = 15, while the full-frame configuration remains competitive at 69.03%. Across the stride range, computational cost varies from 12.48 to 348.78 GFLOPs, showing the trade-off between temporal density and efficiency. These results demonstrate that temporal windowing is not required for effective facial-video stress detection in this setting, and that complete-recording inference can be achieved within a single unified architecture.