AI Paper Atlas

Research map / Video / Video generation

"Plan, Posture and Go: Towards Open-vocabulary Text-to-Motion Generation"

Jinpeng Liu, Wenxun Dai, Chunyu Wang, Yiji Cheng, Yansong Tang, Xin Tong

ECCV 2024 · Video › Video generation · approach: Text-to-motion diffusion · 11 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
decompose text into LLM-generated pose scripts then pose then motion (PRO-Motion) instead of CLIP-based alignmentPRO-Motion · IDEA-400 ood368FID: 2.2275 -> 1.4886Improved
PRO-Motion vs AvatarCLIP on kungfu subsetPRO-Motion · Motion-X kungfuFID: 1.9667 -> 4.1242Hurt
PRO-Motion on kungfu retrieval metricsPRO-Motion · Motion-X kungfuR@10: 15.62 -> 20.31Improved
use LLM-described localized body part scripts for pose generation (posture-denoiser) instead of PoseScript baselineposture-denoiser · PoseScript-AFID: 0.48 -> 0.24Improved
posture-denoiser vs PoseScript on human captionsposture-denoiser · PoseScript-HmRecall (R/G): 18.23 -> 24.40Improved
use Go-Denoiser with key poses as discrete tokens instead of MLP regression (ablation)Go-Denoiser · AMASS keypose-to-motionAPE root joint: 5.8786 -> 0.3653Improved
treat key poses as discrete tokens instead of a motion-encoder feature condition (ablation)Go-Denoiser · AMASS keypose-to-motionAPE mean local: 0.1839 -> 0.1287Improved
use LLM description (CLIP matching vs LLM-described poses) for text-to-pose (ablation)posture-denoiser · qualitative text-to-posepose precisionImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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