VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection

Documenti analoghi

• Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning
  di: Deng, Huilin, et al.
  Pubblicazione: (2025)
• Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models
  di: Xu, Jiacong, et al.
  Pubblicazione: (2025)
• Bidirectional Progressive Transformer for Interaction Intention Anticipation
  di: Zhang, Zichen, et al.
  Pubblicazione: (2024)
• PEAR: Phrase-Based Hand-Object Interaction Anticipation
  di: Zhang, Zichen, et al.
  Pubblicazione: (2024)
• Global-Regularized Neighborhood Regression for Efficient Zero-Shot Texture Anomaly Detection
  di: Yao, Haiming, et al.
  Pubblicazione: (2024)