CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection
Paper
•
2311.00453
•
Published
HAOYANG
Lewandofski
AI & ML interests
CV, AD
Recent Activity
new activity
about 12 hours ago
Lewandofski/OpenVE-3M:Missing data for Multi-Shot Camera Edit and Creative Edit tasks when downloading via huggingface-cli
new activity
about 13 hours ago
Lewandofski/OpenVE-3M:video order in background_change csv seems to be incorrect
liked
a dataset
3 days ago
Lewandofski/OpenVE-3M
Organizations
authored
5
papers
10 months ago
LLaVA-KD: A Framework of Distilling Multimodal Large Language Models
Paper
•
2410.16236
•
Published
MobileMamba: Lightweight Multi-Receptive Visual Mamba Network
Paper
•
2411.15941
•
Published
•
2
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
Paper
•
2404.06564
•
Published
Learning Multi-view Anomaly Detection
Paper
•
2407.11935
•
Published
•
1