AI Paper Atlas

Research map / Video / Video generation

TEMOS: Generating Diverse Human Motions from Textual Descriptions

Mathis Petrovich, Michael J. Black, Gül Varol

ECCV 2022 · Video › Video generation · approach: Text-to-motion diffusion · 438 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 non-autoregressive Transformers instead of GRUs (ablation)TEMOS · KIT Motion-Language testAPE root joint: 1.443 -> 0.963Improved
add motion encoder (second KL loss) (ablation)TEMOS · KIT Motion-Language testAPE root joint: 1.178 -> 0.963Improved
add cross-modal embedding loss (ablation)TEMOS · KIT Motion-Language testAPE root joint: 1.091 -> 0.963Improved
add Gaussian priors (ablation)TEMOS · KIT Motion-Language testAPE root joint: 1.049 -> 0.963Improved
add cross-modal KL losses (ablation)TEMOS · KIT Motion-Language testAPE root joint: 0.993 -> 0.963Improved
make model variational (VAE sampling) instead of deterministic (ablation)TEMOS · KIT Motion-Language testAPE root joint: 1.175 -> 0.963Improved
sample best of 10 latent vectors instead of one random (ablation)TEMOS · KIT Motion-Language testAPE root joint: 0.963 -> 0.784Improved
average over 10 random samples instead of one (ablation)TEMOS · KIT Motion-Language testAPE root joint: 0.963 -> 1.001No clear effect
freeze DistilBERT instead of finetuning (ablation)TEMOS · KIT Motion-Language testAPE root joint: 1.402 -> 0.963Improved
use larger language models (BERT, RoBERTa) instead of DistilBERT (ablation)TEMOS · KIT Motion-Language testAPE root joint: 0.963 -> 0.986No clear effect
batch size 32 or 8 instead of 16 or 24 (ablation)TEMOS · KIT Motion-Language testAPE root joint: 1.260 -> 0.963Mixed
loss weights 1e-5 instead of 1e-3 (ablation)TEMOS · KIT Motion-Language testAPE root joint: 1.219 -> 0.963Improved

Later papers that compared with this method

6 later accepted papers report TEMOS as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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