A skeleton-based zero-shot VAD method distills LLM knowledge for action typicality during training and performs test-time context uniqueness analysis to derive scene-adaptive normality boundaries, claiming SOTA results on four datasets with over 100 unseen scenes.
AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
Forensic examination of a high-profile photograph reveals multiple technical anomalies consistent with digital compositing from unrelated source images.
citing papers explorer
-
Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detection
A skeleton-based zero-shot VAD method distills LLM knowledge for action typicality during training and performs test-time context uniqueness analysis to derive scene-adaptive normality boundaries, claiming SOTA results on four datasets with over 100 unseen scenes.
-
Constructed Realities? Technical and Contextual Anomalies in a High-Profile Image
Forensic examination of a high-profile photograph reveals multiple technical anomalies consistent with digital compositing from unrelated source images.