Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection
This work addresses the challenge of detecting ambiguous violence in videos for surveillance and content moderation, representing an incremental advance by integrating hyperbolic space into existing Euclidean-based methods.
The paper tackles the problem of weakly supervised video violence detection by proposing a dual-space representation learning method that combines Euclidean and hyperbolic geometries to enhance feature discrimination, achieving state-of-the-art results on benchmark datasets with improvements in accuracy and F1-score.
While numerous Video Violence Detection (VVD) methods have focused on representation learning in Euclidean space, they struggle to learn sufficiently discriminative features, leading to weaknesses in recognizing normal events that are visually similar to violent events (\emph{i.e.}, ambiguous violence). In contrast, hyperbolic representation learning, renowned for its ability to model hierarchical and complex relationships between events, has the potential to amplify the discrimination between visually similar events. Inspired by these, we develop a novel Dual-Space Representation Learning (DSRL) method for weakly supervised VVD to utilize the strength of both Euclidean and hyperbolic geometries, capturing the visual features of events while also exploring the intrinsic relations between events, thereby enhancing the discriminative capacity of the features. DSRL employs a novel information aggregation strategy to progressively learn event context in hyperbolic spaces, which selects aggregation nodes through layer-sensitive hyperbolic association degrees constrained by hyperbolic Dirichlet energy. Furthermore, DSRL attempts to break the cyber-balkanization of different spaces, utilizing cross-space attention to facilitate information interactions between Euclidean and hyperbolic space to capture better discriminative features for final violence detection. Comprehensive experiments demonstrate the effectiveness of our proposed DSRL.