# Multitask Learning and Multistage Fusion for Dimensional Audiovisual Emotion Recognition

arXiv: https://arxiv.org/abs/2002.11312 · HTML: https://mlsanity.com/paper/2002.11312/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2020.

## Built on by (most cited first, 9 of 9)

- [A Pre-trained Audio-Visual Transformer for Emotion Recognition](https://mlsanity.com/paper/2201.09165/) (2022)
- [A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition](https://mlsanity.com/paper/2111.02172/) (2021)
- [Estimating the Uncertainty in Emotion Attributes using Deep Evidential Regression](https://mlsanity.com/paper/2306.06760/) (2023)
- [End-to-End Continuous Speech Emotion Recognition in Real-life Customer Service Call Center Conversations](https://mlsanity.com/paper/2310.02281/) (2023)
- [Versatile audio-visual learning for emotion recognition](https://mlsanity.com/paper/2305.07216/) (2023)
- [Audio Representation Learning by Distilling Video as Privileged Information](https://mlsanity.com/paper/2302.02845/) (2023)
- [A Cross-Domain Approach for Continuous Impression Recognition from Dyadic Audio-Visual-Physio Signals](https://mlsanity.com/paper/2203.13932/) (2022)
- [United we stand, Divided we fall: Handling Weak Complementary Relationships for Audio-Visual Emotion Recognition in Valence-Arousal Space](https://mlsanity.com/paper/2503.12261/) (2025)
- [Emotion as a Distribution: Joint Valence-Arousal Probability Learning for Speaker-Independent Multimodal Emotion Recognition](https://mlsanity.com/paper/2609.05755/) (2026)

## Abstract (arXiv)

Due to its ability to accurately predict emotional state using multimodal features, audiovisual emotion recognition has recently gained more interest from researchers. This paper proposes two methods to predict emotional attributes from audio and visual data using a multitask learning and a fusion strategy. First, multitask learning is employed by adjusting three parameters for each attribute to improve the recognition rate. Second, a multistage fusion is proposed to combine results from various modalities' final prediction. Our approach used multitask learning, employed at unimodal and early fusion methods, shows improvement over single-task learning with an average CCC score of 0.431 compared to 0.297. A multistage method, employed at the late fusion approach, significantly improved the agreement score between true and predicted values on the development set of data (from [0.537, 0.565, 0.083] to [0.68, 0.656, 0.443]) for arousal, valence, and liking.