← Back to literature explorer
Weakly Supervised From survey PDF — verify links

LOP-VAD

LOP-VAD — Prompt-Enhanced MIL

Knowledge-Based Systems · 2025

Survey summary

Introduces dual affirmative/negative ("yes/no") text prompts for bidirectional vision-language alignment, addressing overlap between normal and abnormal visual patterns, paired with a temporal context attention module that captures dependencies CLIP's static representations miss.

Weakly Supervised

Weakly SupervisedPrompt-Enhanced MIL
Weakly SupervisedOpposite promptsPrompt learning