Video Anomaly Detection On Hr Shanghaitech
Metriken
AUC
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | AUC |
|---|---|
| bipoco-bi-directional-trajectory-prediction | 74.9 |
| regularity-learning-via-explicit-distribution | 84.3 |
| holistic-representation-learning-for | 77.9 |
| contracting-skeletal-kinematic-embeddings-for | 77.1 |
| multimodal-motion-conditioned-diffusion-model | 77.6 |
| an-exploratory-study-on-human-centric-video | 81.77 |
| graph-embedded-pose-clustering-for-anomaly | 74.8 |
| learning-temporal-regularity-in-video | 69.8 |
| learning-regularity-in-skeleton-trajectories | 75.4 |
| future-frame-prediction-for-anomaly-detection | 72.7 |
| multi-timescale-trajectory-prediction-for | 77.0 |
| contracting-skeletal-kinematic-embeddings-for | 75.2 |
| posewatch-a-transformer-based-architecture | 87.23 |
| contracting-skeletal-kinematic-embeddings-for | 75.6 |