2025-01-22: LOKI is accepted to ICLR 2025. 2024-11: The source code and Datasets are released. Our evaluation framework supports over 20+ mainstream foundation models. Please see here for full model ...
This repository implements real-time image captioning using the BLIP (Bootstrapped Language-Image Pretraining) model. The system captures live video from your webcam, generates descriptive captions ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback