EEVR: A Virtual Reality-Based Emotion Dataset Featuring Paired Physiological Signals and Textual Descriptions
EEVR (Emotion Elicitation in Virtual Reality) is a novel dataset specifically designed for language supervision-based pre-training and emotion recognition tasks, such as valence and arousal classification.
Link for pre-trained models: https://huggingface.co/Pragya/EEVR
More details about EEVR can be found on our website: https://melangelabiiitd.github.io/EEVR/. To download EEVR, please visit our website.
EEVR is accepted at NeurIPS 2024 Dataset & Benchmarking Track. Link for NeurIPS 2024 Event Page: https://nips.cc/virtual/2024/poster/97493
BibTeX: @inproceedings{ singh2024eevr, title={{EEVR}: A Dataset of Paired Physiological Signals and Textual Descriptions for Joint Emotion Representation Learning}, author={Pragya Singh and Ritvik Budhiraja and Ankush Gupta and Anshul Goswami and Mohan Kumar and Pushpendra Singh}, booktitle={The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track}, year={2024}, url={https://openreview.net/forum?id=qgzdGyQcDt} }
This code is released under the MIT license. Please see the license file for details.
pip install -r requirements.txt