VarDeepPCA is a sampling-free variational DNN plugin that learns anatomical geometry distributions from tiny ID training sets to refine OOD segmentations and estimate uncertainty.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
A two-stage alignment framework that first fuses visual modalities (RGB, flow, skeleton) then introduces text, achieving 21% SRCC improvement on a new clinical AQA dataset and gains on two public benchmarks.
citing papers explorer
-
Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation
VarDeepPCA is a sampling-free variational DNN plugin that learns anatomical geometry distributions from tiny ID training sets to refine OOD segmentations and estimate uncertainty.
-
Two-Stage Multi-Modal Fusion with Adaptive Alignment for Action Quality Assessment
A two-stage alignment framework that first fuses visual modalities (RGB, flow, skeleton) then introduces text, achieving 21% SRCC improvement on a new clinical AQA dataset and gains on two public benchmarks.