A unified spatial-relational-temporal model improves surgical triplet recognition AP_IVT by 5.1% and 7.8% relative on CholecT45 and ProstaTD, and proposes a new TCER metric for triplet consistency.
Uniformerv2: Unlocking the po- tential of image vits for video understanding
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
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
TRCoRSurg: Temporal-Relational Co-Reasoning for Surgical Video Triplet Recognition
A unified spatial-relational-temporal model improves surgical triplet recognition AP_IVT by 5.1% and 7.8% relative on CholecT45 and ProstaTD, and proposes a new TCER metric for triplet consistency.