PiercingEye: Dual-Space Video Violence Detection with Hyperbolic Vision-Language Guidance
This addresses fine-grained violence detection for video surveillance and content moderation, representing an incremental improvement over existing methods.
The paper tackles the problem of weakly supervised video violence detection by proposing PiercingEye, a dual-space learning framework that combines Euclidean and hyperbolic geometries to better distinguish visually similar but semantically distinct events, achieving state-of-the-art performance on XD-Violence and UCF-Crime benchmarks with strong results on ambiguous event subsets.
Existing weakly supervised video violence detection (VVD) methods primarily rely on Euclidean representation learning, which often struggles to distinguish visually similar yet semantically distinct events due to limited hierarchical modeling and insufficient ambiguous training samples. To address this challenge, we propose PiercingEye, a novel dual-space learning framework that synergizes Euclidean and hyperbolic geometries to enhance discriminative feature representation. Specifically, PiercingEye introduces a layer-sensitive hyperbolic aggregation strategy with hyperbolic Dirichlet energy constraints to progressively model event hierarchies, and a cross-space attention mechanism to facilitate complementary feature interactions between Euclidean and hyperbolic spaces. Furthermore, to mitigate the scarcity of ambiguous samples, we leverage large language models to generate logic-guided ambiguous event descriptions, enabling explicit supervision through a hyperbolic vision-language contrastive loss that prioritizes high-confusion samples via dynamic similarity-aware weighting. Extensive experiments on XD-Violence and UCF-Crime benchmarks demonstrate that PiercingEye achieves state-of-the-art performance, with particularly strong results on a newly curated ambiguous event subset, validating its superior capability in fine-grained violence detection.