PL-Stitch
Self-supervised learning of procedure-aware video representations through probabilistic listwise temporal ranking.
Research
LEMON
A large-scale open-access surgical video dataset and foundation model for transferable surgical visual representation learning.
SurgLIME
Scalable surgical vision-language pre-training with LLM-generated text and confidence-aware alignment.
Back to the Feature
Explaining video classifiers through feature-level video counterfactual explanations.