A noise-aware contrastive loss derived from temporal structure in colonoscopy videos produces polyp tracklet representations that outperform prior self-supervised and supervised baselines on retrieval, re-identification, size estimation, and histology tasks.
In: Conference on Computer Vision and Pattern Recognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 2years
2026 2roles
method 1polarities
use method 1representative citing papers
PlaneCycle lifts pretrained 2D models to 3D by cyclically aggregating features across orthogonal planes throughout network depth, delivering strong performance on 3D benchmarks without any training or architectural changes.
citing papers explorer
-
Contrastive Learning under Noisy Temporal Self-Supervision for Colonoscopy Videos
A noise-aware contrastive loss derived from temporal structure in colonoscopy videos produces polyp tracklet representations that outperform prior self-supervised and supervised baselines on retrieval, re-identification, size estimation, and histology tasks.
-
PlaneCycle: Training-Free 2D-to-3D Lifting of Foundation Models Without Adapters
PlaneCycle lifts pretrained 2D models to 3D by cyclically aggregating features across orthogonal planes throughout network depth, delivering strong performance on 3D benchmarks without any training or architectural changes.