A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection

arXiv:2608.21244 · cs.CV · Submitted 2026-08-21 · Read on arXiv

cs.CV

Submitted: 2026-08-21

Updated: 2026-09-26

Terminology

• Benchmark — 104× in this paper · explained in 2 episodes
• AUC — 28× in this paper · explained in 2 episodes
• Computer Vision and Pattern Recognition — 7× in this paper
• Decode — 4× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Tokenization — 2× in this paper · explained in 2 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cross-Model Transfer — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Bounding-Box Trajectories Matter for Video Anomaly Detection
• Instance-Aligned Captions for Explainable Video Anomaly Detection
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models