ECCV 2026

SAFER‑Activities

A Dataset for Smart Assessment of Fall Events and Routine Activities

1KU Leuven  ·  2Asian Institute of Technology
A participant falling, across multiple camera views A participant falling, across multiple camera views A participant falling, across multiple camera views A wheelchair user falling, across multiple camera views

Overview

SAFER‑Activities is a dataset for fall detection and physical activity monitoring, with frame-level annotations over long, untrimmed, multi-camera videos and a dedicated subset for wheelchair users. We benchmark 2D/3D skeleton models, frozen RGB foundation-model features, and multimodal fusion for action recognition and fall detection across in-lab, out-of-distribution, wheelchair, and cross-dataset settings: skeleton models generalize best under domain shift, while RGB features help in-domain but degrade sharply out of distribution.

What's Inside

Detecting Falls in the Wild

Models trained on SAFER‑Activities detect falls in public videos far outside the training distribution, including wheelchair users.

Real-world fall detected Real-world fall detected Real-world fall detected Real-world wheelchair fall detected

Sources: non-wheelchair falls from FailArmy; wheelchair fall from regor09.