STBP computes exact closed-form bounds for the first convolutional layer of spatio-temporal networks and propagates scalable approximations through the rest to certify robustness under subset-frame or patch perturbations.
CoRRabs/2110.14795(2021), https://arxiv.org/abs/2110.14795
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
VI-EDL reformulates evidential deep learning via variational inference to derive an ELBO that limits excessive evidence and a generalization bound that justifies setting Dirichlet parameters to e+1.
citing papers explorer
-
Variational Inference for Evidential Deep Learning
VI-EDL reformulates evidential deep learning via variational inference to derive an ELBO that limits excessive evidence and a generalization bound that justifies setting Dirichlet parameters to e+1.