# Integrating Holistic and Local Information to Estimate Emotional Reaction Intensity

arXiv: https://arxiv.org/abs/2305.05534 · HTML: https://mlsanity.com/paper/2305.05534/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 9 May 2023.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild](https://mlsanity.com/paper/1708.03985/) (2017)
- [Py-Feat: Python Facial Expression Analysis Toolbox](https://mlsanity.com/paper/2104.03509/) (2021)
- [The MuSe 2022 Multimodal Sentiment Analysis Challenge: Humor, Emotional Reactions, and Stress](https://mlsanity.com/paper/2207.05691/) (2022)
- [MMA-MRNNet: Harnessing Multiple Models of Affect and Dynamic Masked RNN for Precise Facial Expression Intensity Estimation](https://mlsanity.com/paper/2303.00180/) (2023)
- [Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis](https://mlsanity.com/paper/2208.03051/) (2022)

## Built on by (most cited first, 1 of 1)

- [End-to-End Facial Expression Detection in Long Videos](https://mlsanity.com/paper/2504.07660/) (2025)

## Abstract (arXiv)

Video-based Emotional Reaction Intensity (ERI) estimation measures the intensity of subjects' reactions to stimuli along several emotional dimensions from videos of the subject as they view the stimuli. We propose a multi-modal architecture for video-based ERI combining video and audio information. Video input is encoded spatially first, frame-by-frame, combining features encoding holistic aspects of the subjects' facial expressions and features encoding spatially localized aspects of their expressions. Input is then combined across time: from frame-to-frame using gated recurrent units (GRUs), then globally by a transformer. We handle variable video length with a regression token that accumulates information from all frames into a fixed-dimensional vector independent of video length. Audio information is handled similarly: spectral information extracted within each frame is integrated across time by a cascade of GRUs and a transformer with regression token. The video and audio regression tokens' outputs are merged by concatenation, then input to a final fully connected layer producing intensity estimates. Our architecture achieved excellent performance on the Hume-Reaction dataset in the ERI Esimation Challenge of the Fifth Competition on Affective Behavior Analysis in-the-Wild (ABAW5). The Pearson Correlation Coefficients between estimated and subject self-reported scores, averaged across all emotions, were 0.455 on the validation dataset and 0.4547 on the test dataset, well above the baselines. The transformer's self-attention mechanism enables our architecture to focus on the most critical video frames regardless of length. Ablation experiments establish the advantages of combining holistic/local features and of multi-modal integration. Code available at https://github.com/HKUST-NISL/ABAW5.