About

Bitbox is an easy-to-use computational toolbox to fill the gap between engineering advances in AI and their accessibility by behavioral scientists for quantifying nonverbal human behavior. While numerous successful computational approaches for quantifying human behavior from videos exist, their use is nearly always restricted to specialized engineers, rendering computational behavior analysis out of reach for those most interested in studying human behavior— behavioral, social, and medical scientists. The main goal of Bitbox is to provide computational tools that researchers with no engineering background can use and interpret, to democratize computational behavior analysis and significantly advance science in this area. The sophisticated design of Bitbox, as well as its state-of-the-art algorithms, make it a valuable tool for engineers and computer vision researchers as well. Moreover, its modular architecture makes it easy for developers to contribute their algorithms.

Team

Bitbox is being developed at Children’s Hospital Philadelphia and the University of Pennsylvania. The core development team consists of computational scientists and engineers, psychologists and behavioral scientists, and software developers, who design, develop, implement, test, and document all tools in collaboration.

Our Funding Resources

The development of Bitbox is supported by the National Institutes of Health (NIH) Office of the Director (OD) and by the National Institute of Mental Health (NIMH) of the US, under the grant R01MH122599.

Citations

If you utilize Bitbox in your research or projects, kindly acknowledge the creators by citing the following key papers in your publication. Proper citation is crucial for the continued acknowledgment of the creators' work and ensures the traceability, reproducibility, and validation of scientific knowledge.

Main Bitbox publication:

Coming soon

If you use 3DI:

@article{
author={Evangelos Sariyanidi and Casey J. Zampella and Robert T. Schultz and Birkan Tunç},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Inequality-Constrained 3D Morphable Face Model Fitting},
year={2024},
volume={46},
number={2},
pages={1305-1318},
doi={10.1109/TPAMI.2023.3334948}}

If you use 3DI-lite or Facial Basis (localized expression units):

@inproceedings{
author = {Evangelos Sariyanidi and Lisa Yankowitz and Robert T. Schultz and John D. Herrington and Birkan Tunç and Jeffrey Cohn},
title = {Beyond FACS: Data-driven facial expression dictionaries, with application to predicting autism},
booktitle = {Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition (FG)},
year = {2025},
volume = {19},
pages = {1--10},
doi = {10.48550/arXiv.2505.24679},
}