AI Paper Atlas

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

ICCV 2019 · Probabilistic and scientific modeling › Molecules and proteins · approach: Sparse graphical and tensor models · 37 citations (OpenAlex)

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 changedWhereMeasuredEffect
add residual connections (ablation)manifold DCNN · UCF-11test accuracy: 0.809 -> 0.823Improved
use manifold DCNN instead of SPD-SRUsequence model · UCF-11test accuracy: 0.784 -> 0.823Improved
use manifold DCNN instead of SPD-SRUsequence model · UCF-11time per epoch (s): 76 -> 33Improved
use DCNN instead of TT-GRUsequence model · Moving MNIST (10 vs 15 degrees)test accuracy: 0.52 -> 1.00Improved
use DCNN instead of LSTMsequence model · Moving MNIST (10 vs 15 vs 20 degrees)test accuracy: 0.57 -> 0.95Improved
use DCNN instead of SPD-SRUsequence model · Moving MNIST (10 vs 15 degrees)test accuracy: 0.96 -> 1.00Improved
use DCNN instead of SPD-SRUsequence model · Moving MNIST (30 vs 60 degrees)test accuracy: 1.00 -> 1.00No clear effect
use DCNN instead of SPD-SRU for permutation testingsequence model · PiB+ vs PiB- fiber bundlespermutation testing time (days): 18 -> 3.5Improved
use DCNN instead of SPD-SRUsequence model · PiB+ vs PiB- fiber bundlessignificant fibers out of 18: 1 -> 2Improved
use DCNN instead of SPD-SRUsequence model · APOE+ vs APOE- fiber bundles (DTI)significant fibers out of 18: 1 -> 4Improved
use ODF data (sphere) instead of DTImanifold DCNN · APOE+ vs APOE- fiber bundlessignificant fibers out of 18: 4 -> 5No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy