Introduces OR-Action benchmark for multi-role fine-grained actions in OR videos and a vision-only temporal model with multi-to-single view alignment that outperforms graph-based approaches.
arXiv preprint arXiv:2511.06549 (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
OR-Action: Multi-Role Video Understanding with Fine-Grained Actions
Introduces OR-Action benchmark for multi-role fine-grained actions in OR videos and a vision-only temporal model with multi-to-single view alignment that outperforms graph-based approaches.