Skip to content
프로젝트

tzirakis/Multimodal-Emotion-Recognition

GitHub에서 보기

tzirakis/Multimodal-Emotion-Recognition has 252 GitHub stars and 75 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-22 04:43 UTC. Last push 2021-01-22.

이 수치를 측정하는 방법

측정된 스타 증가

in 24h
0
in 7 days
0
in 15 days
기록 수집 중
in 1 month
기록 수집 중

서로 겹치는 기간의 순증가량이며 일별 합계가 아닙니다. 측정값이 없으면 비워 둡니다. 스타는 관심도를 나타내며 품질을 보장하지 않습니다.

소개

This repository contains the code for the paper `End-to-End Multimodal Emotion Recognition using Deep Neural Networks`.

머신러닝

README.md

Original

End-to-End Multimodal Emotion Recognition using Deep Neural Networks

This package provides training and evaluation code for the end-to-end multimodal emotion recognition paper. If you use this codebase in your experiments please cite:

P. Tzirakis, G. Trigeorgis, M. A. Nicolaou, B. Schuller and S. Zafeiriou, "End-to-End Multimodal Emotion Recognition using Deep Neural Networks," in IEEE Journal of Selected Topics in Signal Processing, vol. PP, no. 99, pp. 1-1. (http://ieeexplore.ieee.org/document/8070966/)

UPDATE

Implementation of this method in PyTorch (along with pretrain models) can be found in our End2You toolkit

Requirements

Below are listed the required modules to run the code.

  • Python <= 2.7
  • NumPy >= 1.11.1
  • TensorFlow <= 0.12
  • Menpo >= 0.6.2
  • MoviePy >= 0.2.2.11

Content

This repository contains the files:

  • model.py: contains the audio and video networks.
  • emotion_train.py: is in charge of training.
  • emotion_eval.py: is in charge of evaluating.
  • data_provider.py: provides the data.
  • data_generator.py: creates the tfrecords from '.wav' files
  • metrics.py: contains the concordance metric used for evaluation.
  • losses.py: contains the loss function of the training.
  • inception_processing.py: provides functions for visual regularization.

The multimodal model can be downloaded from here : https://www.doc.ic.ac.uk/~pt511/emotion_recognition_model.zip

관련 프로젝트 살펴보기

불러오는 중…