# Continuous-Time Audiovisual Fusion with Recurrence vs. Attention for In-The-Wild Affect Recognition

arXiv: https://arxiv.org/abs/2203.13285 · HTML: https://mlsanity.com/paper/2203.13285/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 47 references that are in the map.
- First posted on arXiv 24 Mar 2022.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [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)
- [MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices](https://mlsanity.com/paper/1804.07573/) (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)
- [ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challenges](https://mlsanity.com/paper/2202.10659/) (2022)
- [Face Behavior a la carte: Expressions, Affect and Action Units in a Single Network](https://mlsanity.com/paper/1910.11111/) (2019)
- [AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and Cross-Cultural Affect Recognition](https://mlsanity.com/paper/1907.11510/) (2019)
- [Two-Stream Aural-Visual Affect Analysis in the Wild](https://mlsanity.com/paper/2002.03399/) (2020)
- [Human Sentence Processing: Recurrence or Attention?](https://mlsanity.com/paper/2005.09471/) (2020)
- [Multitask Emotion Recognition with Incomplete Labels](https://mlsanity.com/paper/2002.03557/) (2020)
- [Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition](https://mlsanity.com/paper/2108.04228/) (2021)
- [Is Cross-Attention Preferable to Self-Attention for Multi-Modal Emotion Recognition?](https://mlsanity.com/paper/2202.09263/) (2022)
- [Continuous Emotion Recognition with Audio-visual Leader-follower Attentive Fusion](https://mlsanity.com/paper/2107.01175/) (2021)
- [M3T: Multi-Modal Continuous Valence-Arousal Estimation in the Wild](https://mlsanity.com/paper/2002.02957/) (2020)
- [End2You -- The Imperial Toolkit for Multimodal Profiling by End-to-End Learning](https://mlsanity.com/paper/1802.01115/) (2018)
- [An audiovisual and contextual approach for categorical and continuous emotion recognition in-the-wild](https://mlsanity.com/paper/2107.03465/) (2021)
- [A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition](https://mlsanity.com/paper/2111.02172/) (2021)
- [Affective Expression Analysis in-the-wild using Multi-Task Temporal Statistical Deep Learning Model](https://mlsanity.com/paper/2002.09120/) (2020)
- [Hybrid Mutimodal Fusion for Dimensional Emotion Recognition](https://mlsanity.com/paper/2110.08495/) (2021)
- [Untangling tradeoffs between recurrence and self-attention in neural networks](https://mlsanity.com/paper/2006.09471/) (2020)

## Built on by (most cited first, 7 of 7)

- [ABAW: Learning from Synthetic Data & Multi-Task Learning Challenges](https://mlsanity.com/paper/2207.01138/) (2022)
- [ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges](https://mlsanity.com/paper/2303.01498/) (2023)
- [The 6th Affective Behavior Analysis in-the-wild (ABAW) Competition](https://mlsanity.com/paper/2402.19344/) (2024)
- [7th ABAW Competition: Multi-Task Learning and Compound Expression Recognition](https://mlsanity.com/paper/2407.03835/) (2024)
- [A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition](https://mlsanity.com/paper/2203.14779/) (2022)
- [Multi-modal Facial Affective Analysis based on Masked Autoencoder](https://mlsanity.com/paper/2303.10849/) (2023)
- [Joint Multimodal Transformer for Emotion Recognition in the Wild](https://mlsanity.com/paper/2403.10488/) (2024)

## Abstract (arXiv)

In this paper, we present our submission to 3rd Affective Behavior Analysis in-the-wild (ABAW) challenge. Learningcomplex interactions among multimodal sequences is critical to recognise dimensional affect from in-the-wild audiovisual data. Recurrence and attention are the two widely used sequence modelling mechanisms in the literature. To clearly understand the performance differences between recurrent and attention models in audiovisual affect recognition, we present a comprehensive evaluation of fusion models based on LSTM-RNNs, self-attention and cross-modal attention, trained for valence and arousal estimation. Particularly, we study the impact of some key design choices: the modelling complexity of CNN backbones that provide features to the the temporal models, with and without end-to-end learning. We trained the audiovisual affect recognition models on in-the-wild ABAW corpus by systematically tuning the hyper-parameters involved in the network architecture design and training optimisation. Our extensive evaluation of the audiovisual fusion models shows that LSTM-RNNs can outperform the attention models when coupled with low-complex CNN backbones and trained in an end-to-end fashion, implying that attention models may not necessarily be the optimal choice for continuous-time multimodal emotion recognition.