paper-with-me

홈 › Papers

Facial Affect Recognition based on Transformer Encoder and Audiovisual Fusion for the ABAW5 Challenge

2023-03-16 · Ziyang Zhang, Liuwei An, Zishun Cui, Ao Xu, Tengteng Dong, Yueqi Jiang, Jingyi Shi, Xin Liu, Xiao Sun, Meng Wang

In this paper, we present our solutions for the 5th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW), which includes four sub-challenges of Valence-Arousal (VA) Estimation, Expression (Expr) Classification, Action Unit (AU) Detection and Emotional Reaction Intensity (ERI) Estimation. The 5th ABAW competition focuses on facial affect recognition utilizing different modalities and datasets. In our work, we extract powerful audio and visual features using a large number of sota models. These features are fused by Transformer Encoder and TEMMA. Besides, to avoid the possible impact of large dimensional differences between various features, we design an Affine Module to align different features to the same dimension. Extensive experiments demonstrate that the superiority of the proposed method. For the VA Estimation sub-challenge, our method obtains the mean Concordance Correlation Coefficient (CCC) of 0.6066. For the Expression Classification sub-challenge, the average F1 Score is 0.4055. For the AU Detection sub-challenge, the average F1 Score is 0.5296. For the Emotional Reaction Intensity Estimation sub-challenge, the average pearson's correlations coefficient on the validation set is 0.3968. All of the results of four sub-challenges outperform the baseline with a large margin.

📄 PDF Abstract BibTeX arXiv:2303.09158

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Beyond the Mouth: Upper-Face Affective Cues in Audiovisual Sentence Recognition under Acoustic Uncertainty

2026-05-30 · Zhou Yang, Yueyi Yang arxiv

Face-to-face speech comprehension is inherently multimodal, integrating acoustic signals with visible articulation, facial expression, head motion, and other socially relevant cues. While audiovisual speech systems typic…

Social-MAE: A Transformer-Based Multimodal Autoencoder for Face and Voice

2025-08-24 · Hugo Bohy, Minh Tran, Kevin El Haddad, Thierry Dutoit 외 arxiv

Human social behaviors are inherently multimodal necessitating the development of powerful audiovisual models for their perception. In this paper, we present Social-MAE, our pre-trained audiovisual Masked Autoencoder bas…

Multimodal Emotion Recognition

A multimodal dynamical variational autoencoder for audiovisual speech representation learning

2023-05-05 · Samir Sadok, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda 외

In this paper, we present a multimodal and dynamical VAE (MDVAE) applied to unsupervised audio-visual speech representation learning. The latent space is structured to dissociate the latent dynamical factors that are sha…

DenoisingDisentanglementEmotion RecognitionImage Denoising+4

A vector quantized masked autoencoder for audiovisual speech emotion recognition

2023-05-05 · Samir Sadok, Simon Leglaive, Renaud Séguier

An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoe…

Contrastive LearningEmotion RecognitionRepresentation LearningSelf-Supervised Learning+1

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

2022-03-24 · Vincent Karas, Mani Kumar Tellamekala, Adria Mallol-Ragolta, Michel Valstar 외

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-wi…

Arousal EstimationEmotion RecognitionMultimodal Emotion Recognition