ColonTCN achieves the best weighted F1 on a new 60-video colonoscopy temporal segmentation benchmark, though the gain over ASFormer is small and based on single runs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Temporal Convolutional Network-Based Approach and a Benchmark Dataset for Colonoscopy Video Temporal Segmentation
ColonTCN achieves the best weighted F1 on a new 60-video colonoscopy temporal segmentation benchmark, though the gain over ASFormer is small and based on single runs.