AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

OmniFall: From Staged Through Synthetic to Wild, A Unified Multi-Domain Dataset for Robust Fall Detection

David Schneider, Zdravko Marinov, Moritz Mistol, Zeyun Zhong, Alexander Jaus, Rodi Düger, Rafael Baur, M. Saquib Sarfraz, Rainer Stiefelhagen

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Train on the unified OF-Staged instead of CMDFall alone (ablation)VideoMAE-K400 · OF-ItWFall F1: 52.3 -> 61.2Improved
Train on the unified OF-Staged instead of CMDFall alone (ablation)VideoMAE-K400 · OF-ItWFallen F1: 16.6 -> 39.4Improved
Train on synthetic OF-Syn instead of OF-Staged (ablation)VideoMAE-K400 · OF-ItWFallen F1: 39.4 -> 42.3Improved
Add OF-Syn to OF-Staged training (ablation)VideoMAE-K400 · OF-ItWFall F1: 64.2 -> 65.6Improved
Add OF-Staged to OF-Syn training (ablation)VideoMAE-K400 · OF-ItWFallen F1: 42.3 -> 41.0No clear effect
Add in-the-wild training data (OF-ItW) to OF-Staged+OF-Syn (ablation)VideoMAE-K400 · OF-ItWFall F1: 65.6 -> 76.0Improved
Train on synthetic OF-Syn only, test on staged CMDFall (ablation)VideoMAE-K400 · CMDFall CSBAcc: 83.3 -> 45.8Hurt
Test on in-the-wild instead of in-domain dataVideoMAE-K400 (Le2i-trained) · Fall F1F1: 100 -> 58.8Hurt
Use zero-shot 8B MLLM instead of small fine-tuned model for fall eventsQwen3-VL-8B / InternVL3.5-8B vs VideoMAE · OF-ItWFall F1: 67.8/68.0 vs 65.6No clear effect
Use fine-tuned VMAE trained on OF-Syn instead of zero-shot MLLMs for fallen stateVideoMAE-K400 · OF-ItWFallen F1: 29.2/31.0 -> 42.3Improved
Train timeline model on OF-Syn instead of OF-Staged (ablation)ASQuery · OF-ItWF1@50: 20.26 -> 27.60Improved
Combine OF-Staged and OF-Syn for timeline model (ablation)ASQuery · OF-ItWF1@50: 27.60 -> 28.61Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy