OSMO: Open-vocabulary Self-eMOtion Tracking
OSMO introduces egocentric self-emotion tracking with a large-scale dataset, a multi-task benchmark, and OSIRIS, a multimodal model for coherent emotion timelines.
mohamed-abdelfattah
OSMO introduces egocentric self-emotion tracking with a large-scale dataset, a multi-task benchmark, and OSIRIS, a multimodal model for coherent emotion timelines.
We take a step towards computer-aided waste detection and present the first in-the-wild industrial-grade waste detection and segmentation dataset, ZeroWaste.
This paper introduces ArtELingo, a new benchmark and dataset, designed to encourage work on diversity across languages and cultures.
A computer-vision pipeline using conventional 2D sleep-lab cameras to automatically detect iRBD from REM movement dynamics with up to 91.9% accuracy.