SOURCE-LINKED INTELLIGENCE

What Do Interaction Representations Actually Measure? Pre-Event Separability in Weakly-Supervised Violence Detection

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Articulated human pose provides detailed body-configuration information beyond coarse spatial relationships, but whether this detail yields greater discriminative information when the downstream pipeline is held fixed remains unclear. We examine this through early violence detection. Holding the tracker, temporal head, supervision, folds, and evaluation fixed, we compare five interaction representations spanning coarse bounding-box geometry, a matched handcrafted pose analogue, enriched pose descriptors, and a matched-capacity encoder learned from raw joints, under video-level evaluation with

Read original source ↗ Open in workspace

recordType

paper

region

Global