Skip to content

Latest commit

 

History

History
39 lines (24 loc) · 800 Bytes

File metadata and controls

39 lines (24 loc) · 800 Bytes

mica-context-emotion-recognition

This repository contains the codebase for "Contextually-rich human affect perception using multimodal scene information" accepted at ICASSP 2023.

Repository for context based emotion recognition

Environment creation

Create a conda environment

conda create -n context-emotion-recognition python=3.7

Install torch 1.11.0

conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 cudatoolkit=10.2 -c pytorch

Install required packages

pip install -r requirements.txt

Install transformers package using the following:

pip install transformers

TODOS

  • Add instructions for caption extraction using OFA Large model
  • Add model file links
  • Add facenet extraction instructions