Research map / Probabilistic and scientific modeling / Molecules and proteins
Dilated Convolutional Neural Networks for Sequential Manifold-Valued Data
Xingjian Zhen, Rudrasis Chakraborty, Nicholas Vogt, Barbara B. Bendlin, Vikas Singh
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 |
|---|---|---|---|
| add residual connections (ablation) | manifold DCNN · UCF-11 | test accuracy: 0.809 -> 0.823 | Improved |
| use manifold DCNN instead of SPD-SRU | sequence model · UCF-11 | test accuracy: 0.784 -> 0.823 | Improved |
| use manifold DCNN instead of SPD-SRU | sequence model · UCF-11 | time per epoch (s): 76 -> 33 | Improved |
| use DCNN instead of TT-GRU | sequence model · Moving MNIST (10 vs 15 degrees) | test accuracy: 0.52 -> 1.00 | Improved |
| use DCNN instead of LSTM | sequence model · Moving MNIST (10 vs 15 vs 20 degrees) | test accuracy: 0.57 -> 0.95 | Improved |
| use DCNN instead of SPD-SRU | sequence model · Moving MNIST (10 vs 15 degrees) | test accuracy: 0.96 -> 1.00 | Improved |
| use DCNN instead of SPD-SRU | sequence model · Moving MNIST (30 vs 60 degrees) | test accuracy: 1.00 -> 1.00 | No clear effect |
| use DCNN instead of SPD-SRU for permutation testing | sequence model · PiB+ vs PiB- fiber bundles | permutation testing time (days): 18 -> 3.5 | Improved |
| use DCNN instead of SPD-SRU | sequence model · PiB+ vs PiB- fiber bundles | significant fibers out of 18: 1 -> 2 | Improved |
| use DCNN instead of SPD-SRU | sequence model · APOE+ vs APOE- fiber bundles (DTI) | significant fibers out of 18: 1 -> 4 | Improved |
| use ODF data (sphere) instead of DTI | manifold DCNN · APOE+ vs APOE- fiber bundles | significant fibers out of 18: 4 -> 5 | No clear effect |
Closest papers by meaning
- ManifoldNet: A Deep Neural Network for Manifold-Valued Data With Applications (TPAMI 2020 · similarity 0.90)
- A Statistical Recurrent Model on the Manifold of Symmetric Positive Definite Matrices (NeurIPS 2018 · similarity 0.90)
- Learning Weighted Submanifolds With Variational Autoencoders and Riemannian Variational Autoencoders (CVPR 2020 · similarity 0.89)
- Matrix Manifold Neural Networks++ (ICLR 2024 · similarity 0.85)
- MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation (NeurIPS 2026 · similarity 0.85)
- Geometry-Aware Similarity Metrics for Neural Representations on Riemannian and Statistical Manifolds (NeurIPS 2026 · similarity 0.85)
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.
