SST-EM is a weighted combination of VLM caption similarity, object-detection confidence, and ViT frame-similarity scores, fitted to human ratings to evaluate text-based video edits.
A deep learning framework for quality assessment and restoration in video endoscopy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SST-EM: Advanced Metrics for Evaluating Semantic, Spatial and Temporal Aspects in Video Editing
SST-EM is a weighted combination of VLM caption similarity, object-detection confidence, and ViT frame-similarity scores, fitted to human ratings to evaluate text-based video edits.