We introduce InterAct, a new multi-modal MoCap dataset composed of 241 motion sequences where two people perform a realistic and coherent scenario for one minute or longer over a complete interaction. We simultaneously model two people's activities, and target objective-driven, dynamic, and semantically consistent interactions which often span longer duration and cover bigger space. The speech audios, body motions, and facial expressions of both persons are captured. Most previous works either only consider one person or solely focus on conversational gestures of two people, assuming the body orientation and/or position of each actor are constant or barely change over each interaction. Our work is the first to capture and model such long-term and dynamic interactions between two people. To facilitate further research, the data and code will be made public upon acceptance.
Relationship
Emotion
Gender
The InterAct dataset is made available under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
@article{ho2025interact,
title={InterAct: A Large-Scale Dataset of Dynamic, Expressive and Interactive Activities between Two People in Daily Scenarios},
author={Ho, Leo and Huang, Yinghao and Qin, Dafei and Shi, Mingyi and Tse, Wangpok and Liu, Wei and Yamagishi, Junichi and Komura, Taku},
journal={Proceedings of the ACM on Computer Graphics and Interactive Techniques},
volume={8},
number={4},
pages={1--27},
year={2025},
publisher={ACM New York, NY}
doi={10.1145/3747871}
}