AI Paper Atlas

Research map / Video / Video segmentation and tracking

MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics

Xinchen Yan, Akash Rastogi, Ruben Villegas, Kalyan Sunkavalli, Eli Shechtman, Sunil Hadap, Ersin Yumer, Honglak Lee

ECCV 2018 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 153 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
use additive transformation instead of vector concatenationMT-VAE · Aff-Wild (facial expression)R-MSE test: 0.73 -> 0.47Improved
use additive transformation instead of vector concatenationMT-VAE · Aff-Wild (facial expression)Test CLL: 2.817 -> 3.147Improved
use additive transformation instead of vector concatenationMT-VAE · Human3.6M (64-step 2D joints)S-MSE test: 2.84 -> 2.87No clear effect
add motion coherence objective (ablation)MT-VAE (add) · Human3.6M (64-step 2D joints)R-MSE test: 1.01 -> 0.75Improved
add motion coherence objective (ablation)MT-VAE (add) · Human3.6M (64-step 2D joints)Test CLL: 1.012 -> 1.141Improved
add cycle consistency objective (ablation)MT-VAE (add) · Human3.6M (64-step 2D joints)R-MSE test: 1.18 -> 0.75Improved
add cycle consistency objective (ablation)MT-VAE (add) · Human3.6M (64-step 2D joints)S-MSE test: 2.71 -> 2.87Hurt
add cycle consistency objective (ablation)MT-VAE (add) · Human3.6M (64-step 2D joints)Test CLL: 0.927 -> 1.141Improved
condition transformation vector on input feature (vs context-free) (ablation)MT-VAE (add) · Human3.6M (64-step 2D joints)S-MSE test: 4.05 -> 2.87Improved
condition transformation vector on input feature (vs context-free) (ablation)MT-VAE (add) · Human3.6M (64-step 2D joints)R-MSE test: 0.31 -> 0.75Hurt
add latent variable model (MT-VAE add) over deterministic Prediction LSTMPrediction LSTM · Human3.6M (64-step 2D joints)Test CLL: 0.602 -> 1.141Improved
use MT-VAE (add) instead of Vanilla VAEVanilla VAE · Human3.6M (64-step 2D joints)S-MSE test: 3.88 -> 2.87Improved

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