Real World Engagement Attention Dataset
(RWEAD)
Last updated 2026/10/25
RWEAD #1b is an indoor-behaviour dataset acquired in a 7.8 m × 6.6 m room configured as an Indoor-category exhibition stand within a building hall. It consisted of recording audience-action videos for an engagement (Eng.) study in a staged environment with five participants (P#1–P#5), with 2 points of interest (PoI): TV and model, and five camera viewpoints named Camera Model 1, Camera TV, Camera Environment 1, Camera Model 2, and Camera Environment 2, whose spatial positions were logged in a coordinate table. A ten-action recording script was followed, with each action assigned a numeric identifier (01–10) and, for each participant, entry/exit times and separate engagement (YES, NO) and emotion-sentiment annotations (e.g., POSIT, NEG, NO-no sentiment). The resulting 50 MP4 files were organised as five camera folders with ten action recordings per camera. The participant cohort is male-only and consists of amateur actors aged 20–30, all university students without formal acting training. Each participant received a script and was allotted five minutes for memorisation prior to data acquisition.
Layout of the room (AI rendering)
Environment Photos
Dataset Protocol
RWEAD #1b download available at OSF - https://doi.org/10.17605/OSF.IO/AD6GH
For RWEAD #1b cite (temporary):
Rodrigues, J. M. F., Lemos, M., El Afia, M., Solá, D., Walid, A., Santos, R., António, G., Cardoso, P. J. S., & Martins, J. A. (2026). MArtAE: A unified architecture for real-time audience experience analytics at live events. Accepted to the 8th International Conference on Soft Computing and its Engineering Applications (icSoftComp2026), Singapore.
ALGARVE 2030, Portugal 2030 and by the European Union, ALGARVE-FEDER-02964500, Ref. 24298 - Project AI.INSIGHTS
ALGARVE 2030, Portugal 2030 and by the European Union, ALGARVE-FEDER-01180500, Ref. 17325 - Project AI.EVENTI