# Robust Facial Reactions Generation: An Emotion-Aware Framework with Modality Compensation

arXiv: https://arxiv.org/abs/2407.15798 · HTML: https://mlsanity.com/paper/2407.15798/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 62 references that are in the map.
- First posted on arXiv 22 Jul 2024.

## Builds on (most cited first, 30 of 34)

- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace](https://mlsanity.com/paper/1910.04855/) (2019)
- [Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond](https://mlsanity.com/paper/1804.10938/) (2018)
- [Analysing Affective Behavior in the First ABAW 2020 Competition](https://mlsanity.com/paper/2001.11409/) (2020)
- [Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework](https://mlsanity.com/paper/2103.15792/) (2021)
- [Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study](https://mlsanity.com/paper/2105.03790/) (2021)
- [Analysing Affective Behavior in the second ABAW2 Competition](https://mlsanity.com/paper/2106.15318/) (2021)
- [Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling](https://mlsanity.com/paper/2307.14126/) (2023)
- [Face Behavior a la carte: Expressions, Affect and Action Units in a Single Network](https://mlsanity.com/paper/1910.11111/) (2019)
- [Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion](https://mlsanity.com/paper/2204.08451/) (2022)
- [ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges](https://mlsanity.com/paper/2303.01498/) (2023)
- [Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders](https://mlsanity.com/paper/2108.06720/) (2021)
- [MoEL: Mixture of Empathetic Listeners](https://mlsanity.com/paper/1908.07687/) (2019)
- [Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation](https://mlsanity.com/paper/2309.04946/) (2023)
- [The 6th Affective Behavior Analysis in-the-wild (ABAW) Competition](https://mlsanity.com/paper/2402.19344/) (2024)
- [Responsive Listening Head Generation: A Benchmark Dataset and Baseline](https://mlsanity.com/paper/2112.13548/) (2021)
- [Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond](https://mlsanity.com/paper/2401.01219/) (2024)
- [7th ABAW Competition: Multi-Task Learning and Compound Expression Recognition](https://mlsanity.com/paper/2407.03835/) (2024)
- [Exploiting multi-CNN features in CNN-RNN based Dimensional Emotion Recognition on the OMG in-the-wild Dataset](https://mlsanity.com/paper/1910.01417/) (2019)
- [A Deep Neural Architecture for Harmonizing 3-D Input Data Analysis and Decision Making in Medical Imaging](https://mlsanity.com/paper/2303.00175/) (2023)
- [High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning](https://mlsanity.com/paper/2305.02572/) (2023)
- [Photorealistic Facial Synthesis in the Dimensional Affect Space](https://mlsanity.com/paper/1811.08004/) (2018)
- [MixAugment & Mixup: Augmentation Methods for Facial Expression Recognition](https://mlsanity.com/paper/2205.04442/) (2022)
- [Domain adaptation, Explainability & Fairness in AI for Medical Image Analysis: Diagnosis of COVID-19 based on 3-D Chest CT-scans](https://mlsanity.com/paper/2403.02192/) (2024)
- [COVID-19 Computer-aided Diagnosis through AI-assisted CT Imaging Analysis: Deploying a Medical AI System](https://mlsanity.com/paper/2403.06242/) (2024)
- [BTDNet: a Multi-Modal Approach for Brain Tumor Radiogenomic Classification](https://mlsanity.com/paper/2310.03485/) (2023)
- [Emotional Listener Portrait: Neural Listener Head Generation with Emotion](https://mlsanity.com/paper/2310.00068/) (2023)
- [Multiple Appropriate Facial Reaction Generation in Dyadic Interaction Settings: What, Why and How?](https://mlsanity.com/paper/2302.06514/) (2023)
- [REACT 2024: the Second Multiple Appropriate Facial Reaction Generation Challenge](https://mlsanity.com/paper/2401.05166/) (2024)
- [Uncertainty-guided Contrastive Learning for Single Source Domain Generalisation](https://mlsanity.com/paper/2403.07514/) (2024)

## Built on by (most cited first, 4 of 4)

- [REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challenge](https://mlsanity.com/paper/2505.17223/) (2025)
- [Grounding Emotion Recognition with Visual Prototypes: VEGA -- Revisiting CLIP in MERC](https://mlsanity.com/paper/2508.06564/) (2025)
- [REACT 2026: The Fourth Multiple Appropriate Facial Reaction Generation Challenge: Personalised MAFRG and Appropriate EEG Reaction Prediction](https://mlsanity.com/paper/2606.07935/) (2026)
- [Emo-DVS: A Multimodal Benchmark for Privacy-Aware Emotion Recognition with Event Cameras](https://mlsanity.com/paper/2609.06928/) (2026)

## Abstract (arXiv)

The objective of the Multiple Appropriate Facial Reaction Generation (MAFRG) task is to produce contextually appropriate and diverse listener facial behavioural responses based on the multimodal behavioural data of the conversational partner (i.e., the speaker). Current methodologies typically assume continuous availability of speech and facial modality data, neglecting real-world scenarios where these data may be intermittently unavailable, which often results in model failures. Furthermore, despite utilising advanced deep learning models to extract information from the speaker's multimodal inputs, these models fail to adequately leverage the speaker's emotional context, which is vital for eliciting appropriate facial reactions from human listeners. To address these limitations, we propose an Emotion-aware Modality Compensatory (EMC) framework. This versatile solution can be seamlessly integrated into existing models, thereby preserving their advantages while significantly enhancing performance and robustness in scenarios with missing modalities. Our framework ensures resilience when faced with missing modality data through the Compensatory Modality Alignment (CMA) module. It also generates more appropriate emotion-aware reactions via the Emotion-aware Attention (EA) module, which incorporates the speaker's emotional information throughout the entire encoding and decoding process. Experimental results demonstrate that our framework improves the appropriateness metric FRCorr by an average of 57.2% compared to the original model structure. In scenarios where speech modality data is missing, the performance of appropriate generation shows an improvement, and when facial data is missing, it only exhibits minimal degradation.