Human Reaction Intensity Estimation with Ensemble of Multi-task Networks

JiYeon Oh, Daun Kim, Jae-Yeop Jeong, Yeong-Gi Hong, Jin-Woo Jeong
3/16/2023
cs.CV

No confident code implementation found for this paper.

Abstract

Facial expression in-the-wild is essential for various interactive computing domains. Especially, "Emotional Reaction Intensity" (ERI) is an important topic in the facial expression recognition task. In this paper, we propose a multi-emotional task learning-based approach and present preliminary results for the ERI challenge introduced in the 5th affective behavior analysis in-the-wild (ABAW) competition. Our method achieved the mean PCC score of 0.3254.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Learning from Synthetic Data: Facial Expression Classification based on Ensemble of Multi-task Networks

96% match2022

Affective Behavior Analysis using Action Unit Relation Graph and Multi-task Cross Attention

88% match2022

Multi-Task Learning for Emotion Descriptors Estimation at the fourth ABAW Challenge

88% match2022

Affective Behaviour Analysis via Progressive Learning

87% match1 repo52024

Feature-Based Dual Visual Feature Extraction Model for Compound Multimodal Emotion Recognition

83% match2025

EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning

83% match1 repo82024

Cite this paper

@article{oh2023human,
  title  = {Human Reaction Intensity Estimation with Ensemble of Multi-task Networks},
  author = {JiYeon Oh and Daun Kim and Jae-Yeop Jeong and Yeong-Gi Hong and Jin-Woo Jeong},
  year   = {2023},
  eprint = {2303.09240},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.09240v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.09240.svg)](https://codeofpaper.com/paper/2303.09240)

Discussion