Similar Items: MMVIAD: Multi-view Multi-task Video Understanding for Industrial Anomaly Detection
- SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
- Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback
- MedHorizon: Towards Long-context Medical Video Understanding in the Wild
- CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection
- Relit-LiVE: Relight Video by Jointly Learning Environment Video
- Identity-Consistent Multi-Pose Generation of Contactless Fingerprints