# AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts

arXiv: https://arxiv.org/abs/2403.13678 · HTML: https://mlsanity.com/paper/2403.13678/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 48 references that are in the map.
- First posted on arXiv 20 Mar 2024.

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

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [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)
- [Partial FC: Training 10 Million Identities on a Single Machine](https://mlsanity.com/paper/2010.05222/) (2020)
- [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)
- [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)
- [Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition](https://mlsanity.com/paper/2205.01782/) (2022)
- [The 6th Affective Behavior Analysis in-the-wild (ABAW) Competition](https://mlsanity.com/paper/2402.19344/) (2024)
- [Improved Residual Networks for Image and Video Recognition](https://mlsanity.com/paper/2004.04989/) (2020)
- [Leveraging TCN and Transformer for effective visual-audio fusion in continuous emotion recognition](https://mlsanity.com/paper/2303.08356/) (2023)
- [Affective Behaviour Analysis via Integrating Multi-Modal Knowledge](https://mlsanity.com/paper/2403.10825/) (2024)
- [Robust Light-Weight Facial Affective Behavior Recognition with CLIP](https://mlsanity.com/paper/2403.09915/) (2024)
- [A transformer-based approach to video frame-level prediction in Affective Behaviour Analysis In-the-wild](https://mlsanity.com/paper/2303.09293/) (2023)
- [Multi-modal Facial Action Unit Detection with Large Pre-trained Models for the 5th Competition on Affective Behavior Analysis in-the-wild](https://mlsanity.com/paper/2303.10590/) (2023)
- [HSEmotion Team at the 6th ABAW Competition: Facial Expressions, Valence-Arousal and Emotion Intensity Prediction](https://mlsanity.com/paper/2403.11590/) (2024)
- [EmotiEffNet Facial Features in Uni-task Emotion Recognition in Video at ABAW-5 competition](https://mlsanity.com/paper/2303.09162/) (2023)
- [Spatio-Temporal AU Relational Graph Representation Learning For Facial Action Units Detection](https://mlsanity.com/paper/2303.10644/) (2023)
- [Facial Affective Behavior Analysis Method for 5th ABAW Competition](https://mlsanity.com/paper/2303.09145/) (2023)
- [Boosting Continuous Emotion Recognition with Self-Pretraining using Masked Autoencoders, Temporal Convolutional Networks, and Transformers](https://mlsanity.com/paper/2403.11440/) (2024)
- [Local Region Perception and Relationship Learning Combined with Feature Fusion for Facial Action Unit Detection](https://mlsanity.com/paper/2303.08545/) (2023)

## Built on by (most cited first, 3 of 3)

- [7th ABAW Competition: Multi-Task Learning and Compound Expression Recognition](https://mlsanity.com/paper/2407.03835/) (2024)
- [Concept Drift Guided LayerNorm Tuning for Efficient Multimodal Metaphor Identification](https://mlsanity.com/paper/2505.11237/) (2025)
- [HSEmotion Team at ABAW-10 Competition: Facial Expression Recognition, Valence-Arousal Estimation, Action Unit Detection and Fine-Grained Violence Classification](https://mlsanity.com/paper/2603.12693/) (2026)

## Abstract (arXiv)

Leveraging the synergy of both audio data and visual data is essential for understanding human emotions and behaviors, especially in in-the-wild setting. Traditional methods for integrating such multimodal information often stumble, leading to less-than-ideal outcomes in the task of facial action unit detection. To overcome these shortcomings, we propose a novel approach utilizing audio-visual multimodal data. This method enhances audio feature extraction by leveraging Mel Frequency Cepstral Coefficients (MFCC) and Log-Mel spectrogram features alongside a pre-trained VGGish network. Moreover, this paper adaptively captures fusion features across modalities by modeling the temporal relationships, and ultilizes a pre-trained GPT-2 model for sophisticated context-aware fusion of multimodal information. Our method notably improves the accuracy of AU detection by understanding the temporal and contextual nuances of the data, showcasing significant advancements in the comprehension of intricate scenarios. These findings underscore the potential of integrating temporal dynamics and contextual interpretation, paving the way for future research endeavors.