English

VEMOCLAP: A video emotion classification web application

Computer Vision and Pattern Recognition 2024-10-30 v1 Artificial Intelligence Machine Learning Multimedia Image and Video Processing

Abstract

We introduce VEMOCLAP: Video EMOtion Classifier using Pretrained features, the first readily available and open-source web application that analyzes the emotional content of any user-provided video. We improve our previous work, which exploits open-source pretrained models that work on video frames and audio, and then efficiently fuse the resulting pretrained features using multi-head cross-attention. Our approach increases the state-of-the-art classification accuracy on the Ekman-6 video emotion dataset by 4.3% and offers an online application for users to run our model on their own videos or YouTube videos. We invite the readers to try our application at serkansulun.com/app.

Cite

@article{arxiv.2410.21303,
  title  = {VEMOCLAP: A video emotion classification web application},
  author = {Serkan Sulun and Paula Viana and Matthew E. P. Davies},
  journal= {arXiv preprint arXiv:2410.21303},
  year   = {2024}
}

Comments

Accepted to 2024 IEEE International Symposium on Multimedia (ISM), Tokyo, Japan

R2 v1 2026-06-28T19:38:28.497Z