metadata
license: gpl-3.0
tags:
- emotion
- emotion-recognition
- sentiment-analysis
- roberta
language:
- en
pipeline_tag: text-classification
FacialMMT
This repo contains the data and pretrained models for FacialMMT, a framework that uses facial sequences of real speaker to help multimodal emotion recognition.
The model performance on MELD test set is:
| Release | W-F1(%) |
|---|---|
| 23-07-10 | 66.73 |
It is currently ranked third on paperswithcode.
If you're interested, please check out this repo for more in-detail explanation of how to use our model.
Paper: A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion Recognition in Multi-party Conversations. In Proceedings of ACL 2023 (Main Conference), pp. 15445–15459.
Authors: Wenjie Zheng, Jianfei Yu, Rui Xia, and Shijin Wang