Research map / Video / Video segmentation and tracking
A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction
Moitreya Chatterjee, Narendra Ahuja, Anoop Cherian
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use gamma hyperprior instead of Uniform[0,1] prior (ablation) | NUQ · SMMNIST (2,000 training samples) | SSIM at convergence: 0.8523 -> 0.8948 | Improved |
| add variance encoder-decoder for uncertainty instead of estimating b_t from the decoder (ablation) | NUQ · SMMNIST (2,000 training samples) | SSIM at convergence: 0.7828 -> 0.8948 | Improved |
| add variance encoder-decoder (not deterministic mapping from latent variance) (ablation) | NUQ · SMMNIST (2,000 training samples) | SSIM at convergence: 0.7648 -> 0.8948 | Improved |
| add adversarial discriminator (ablation) | NUQ · SMMNIST (2,000 training samples) | SSIM at convergence: 0.8929 -> 0.8948 | No clear effect |
| add adversarial discriminator (ablation) | NUQ · SMMNIST (2,000 training samples) | LPIPS at convergence: 0.1967 -> 0.1803 | Improved |
| add explicit uncertainty modeling (NUQ) vs Denton and Fergus | Denton and Fergus · SMMNIST (2,000 training samples) | SSIM after 1 epoch: 0.8145 -> 0.8686 | Improved |
| add NUQ vs Castrejon et al. with full BAIR training set | Castrejon et al. · BAIR Push (43,264) | PSNR at convergence: 19.59 -> 19.31 | Hurt |
| add NUQ vs Castrejon et al. on KTH | Castrejon et al. · KTH Action | SSIM at convergence: 0.8510 -> 0.8448 | Hurt |
| add NUQ vs Denton and Fergus with 2,000 training samples | Denton and Fergus · BAIR Push (2,000) | PSNR at convergence: 18.49 -> 19.26 | Improved |
| add NUQ vs Hsieh et al. on KTH | Hsieh et al. · KTH Action | SSIM at convergence: 0.7057 -> 0.8448 | Improved |
Closest papers by meaning
- Stochastic Variational Video Prediction (ICLR 2018 · similarity 0.88)
- Probabilistic Video Prediction From Noisy Data With a Posterior Confidence (CVPR 2020 · similarity 0.87)
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (NeurIPS 2017 · similarity 0.87)
- Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows (NeurIPS 2025 · similarity 0.87)
- Uncertainty Quantification with the Empirical Neural Tangent Kernel (NeurIPS 2025 · similarity 0.85)
- SURE: SUrvey REcipes for building reliable and robust deep networks (CVPR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
