A new orthogonal projection module for video anomaly detection suppresses facial attributes via weak face-presence signals and cosine alignment while preserving anomaly-relevant features like pose and motion.
International conference on machine learning , pages=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
LeJEPA derives an optimal isotropic Gaussian target for embeddings and enforces it via sketched regularization to deliver scalable, heuristics-free self-supervised pretraining with 79% ImageNet linear accuracy on ViT-H/14.
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
Task-aware pruning improves OOD performance by removing layers that distort task-adapted representation profiles, realigning OOD inputs with the geometry observed on ID data.
SplAttN uses Gaussian soft splatting and attention to avoid sparse projection collapse in point cloud completion, achieving SOTA results and demonstrating genuine visual cue reliance on KITTI.
A tractable estimator for functional KL divergence provides a coherent way to compare trajectory inference methods and reveal discrepancies in inferred dynamics from snapshot data.
citing papers explorer
-
Privacy-Aware Video Anomaly Detection through Orthogonal Subspace Projection
A new orthogonal projection module for video anomaly detection suppresses facial attributes via weak face-presence signals and cosine alignment while preserving anomaly-relevant features like pose and motion.
-
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
LeJEPA derives an optimal isotropic Gaussian target for embeddings and enforces it via sketched regularization to deliver scalable, heuristics-free self-supervised pretraining with 79% ImageNet linear accuracy on ViT-H/14.
-
DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
-
TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability
Task-aware pruning improves OOD performance by removing layers that distort task-adapted representation profiles, realigning OOD inputs with the geometry observed on ID data.
-
SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion
SplAttN uses Gaussian soft splatting and attention to avoid sparse projection collapse in point cloud completion, achieving SOTA results and demonstrating genuine visual cue reliance on KITTI.
-
Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference
A tractable estimator for functional KL divergence provides a coherent way to compare trajectory inference methods and reveal discrepancies in inferred dynamics from snapshot data.