AI Research
SCOUT: Sim-to-Real Text-Based Person Retrieval by Embedding-Space Prediction over Frozen Video Features
Leveraging frozen encoders to bridge the sim-to-real gap in person retrieval without costly fine-tuning.
Text-based person retrieval under a sim-to-real gap (synthetic training data, a real-image gallery) is usually tackled with costly fine-tuned cross-encoders. We ask whether a frozen-encoder system can compete. We present SCOUT, which casts cross-modal retrieval as prediction in e...
AC
ArXiv CS.CV
Source
2 min
ArXiv CS.CV
AI Analysis
Generated insight by OnAirToday AI
SCOUT demonstrates that high-performance cross-modal retrieval is possible without expensive fine-tuning by leveraging frozen feature spaces. This approach significantly reduces the computational overhead for deploying vision-language models in real-world surveillance scenarios.
Powered by AI • Not a substitute for human analysisMore Insights →
Share
Filed under:AI Research
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.