Work

Generalizable Fall Detection via Fall-Specific Adaptation of a Skeleton Action Foundation Model

Year: 2026
Type: article
Abstract: Vision-based fall detection remains challenging when falls resemble routine daily activities and test environments differ from training conditions. We propose a fall-specific adaptation framework that extends a pretrained skeleton-based action recognizer while preserving its original pathway for classifying activities of daily living (ADL). RGB videos are converted into 3D skeleton sequences and encoded by a frozen Dense Spatio-Temporal Encoder (DSTE). A lightweight residual adapter refines the extracted features to distinguish among falls, transitions into a lying posture, lying postures, and other activities. To combine complementary supervision, we jointly train the adapter on SAFER-Activities and FU-Kinect-Fall using separate classification heads for four-class window-level and binary clip-level supervision, respectively. We then freeze the adapter and train a dedicated four-class classifier while leaving the original ADL pathway unchanged. Across five training seeds, the method achieves video-level F1-scores of 89.13±1.70% and 91.50±0.88% (mean ± standard deviation) on the unseen CAUCAFall and Le2i datasets, respectively. The corresponding mean improvements over a classifier trained on unadapted DSTE features are 2.98 and 0.20 percentage points. The method also achieves higher mean F1-scores than the dedicated fall detectors evaluated in this study. The framework provides a lightweight fall-specific extension to a pretrained skeleton-based ADL recognizer, producing four-class fall-related predictions alongside the unchanged original ADL classification pathway.
Source: Electronics
Institution: Dongguk University
Language: English
Open Access status: gold
Estimated APC paid: $2,896
OpenAlex ID: W7236441724
FWCI:
Cites: 26
Cited by:
Related to: 10