An Ensemble Approach for Facial Expression Analysis in Video

Nguyen, Hong-Hai; Huynh, Van-Thong; Kim, Soo-Hyung

doi:10.48550/arxiv.2203.12891

Cited by 2 publications

(2 citation statements)

References 19 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et.al [29] utilized a cross-modal co-attention model for V-A estimation using visual-audiolinguistic information. A two-stage strategy proposed by Nguyen [25] was introdeced. This method extracted new features and used the ensamble approach.…”

Section: Related Work 21 V-a Estimationmentioning

confidence: 99%

Spatial-temporal Transformer for Affective Behavior Analysis

Zou¹,

Wang²,

Wen³

et al. 2023

Preprint

View full text Add to dashboard Cite

The in-the-wild affective behavior analysis has been an important study. In this paper, we submit our solutions for the 5th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW), which includes V-A Estimation, Facial Expression Classification and AU Detection Sub-challenges. We propose a Transformer Encoder with Multi-Head Attention framework to learn the distribution of both the spatial and temporal features. Besides, there are virious effective data augmentation strategies employed to alleviate the problems of sample imbalance during model training. The results fully demonstrate the effectiveness of our proposed model based on the Aff-Wild2 dataset.

show abstract

Section: Related Work 21 V-a Estimationmentioning

confidence: 99%

Spatial-temporal Transformer for Affective Behavior Analysis

Zou¹,

Wang²,

Wen³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…visual, audio and linguistic information). [26] combined local attention with GRU and used multimodal features to increase the performance of model. For expression classification, to address the problem that a single attention module cannot effectively capture the variations in different expression features, [30] proposed a novel attention mechanism to capture more local and complex feature.…”

Section: Related Workmentioning

confidence: 99%

Emotion Recognition based on Multi-Task Learning Framework in the ABAW4 Challenge

Zhang¹,

Liu²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper presents our submission to the Multi-Task Learning (MTL) Challenge of the 4th Affective Behavior Analysis in-the-wild (ABAW) competition. Based on visual feature representations, we utilize three types of temporal encoder to capture the temporal context information in the video, including the transformer based encoder, LSTM based encoder and GRU based encoder. With the temporal context-aware representations, we employ multi-task framework to predict the valence, arousal, expression and AU values of the images. In addition, smoothing processing is applied to refine the initial valence and arousal predictions, and a model ensemble strategy is used to combine multiple results from different model setups. Our system achieves the performance of 1.742 on MTL Challenge validation dataset.

show abstract

An Ensemble Approach for Facial Expression Analysis in Video

Cited by 2 publications

References 19 publications

Spatial-temporal Transformer for Affective Behavior Analysis

Spatial-temporal Transformer for Affective Behavior Analysis

Emotion Recognition based on Multi-Task Learning Framework in the ABAW4 Challenge

Contact Info

Product

Resources

About