2025/05/26 by David Schneider, Schneider, David, Zdravko Marinov +10
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Benchmark (surveying) #Context-Aware Activity Recognition Systems #Detector #Gait Recognition and Analysis #Protocol (science) #Robustness (evolution) #Synthetic data #Timeline
paper · pdf · doi:10.48550/arxiv.2505.19889
published in ArXiv.org
openalex publication_date 2025/05/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Visual fall detection models are usually trained on small, staged datasets. Their real-world utility remains unclear; such data lacks diversity and evaluation protocols differ from paper to paper. We propose OmniFall, a unified benchmark of 15k videos (80 hours) with frame-level annotations in a single 16-class taxonomy. It spans three domains: OF-Staged unifies eight staged datasets with cross-subject and cross-view splits; OF-Synthetic adds 12k videos (17 h) with controlled demographic and environmental diversity; and OF-In-the-Wild provides a test-only set of genuine accident videos. We evaluate fine-tuned models as well as much larger zero-shot multimodal LLMs. On in-the-wild fall events, both do comparably well. The clinically critical fallen state is where they part: zero-shot models keep confusing fallen with lying, whereas models fine-tuned on synthetic data with explicit fallen-state scenes do substantially better. We release the unified annotations, the synthetic data, and the in-the-wild test set to foster the development of fall and fallen-state detectors for uncontrolled environments. Dataset: https://hf.co/datasets/simplexsigil2/omnifall