AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

MotionChain: Conversational Motion Controllers via Multimodal Prompts

Biao Jiang, Xin Chen, Chi Zhang, Fukun Yin, Zhuoyuan Li, Gang Yu, Jiayuan Fan

ECCV 2024 · Vision-language and multimodal › Human and embodied modeling · approach: Text-driven human motion generation · 20 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
decode concatenated motion tokens jointly instead of independent per-turn decoding (ablation)MotionChain multi-turn composition · HumanML3D motion compositionMPJPE: 350.79 -> 108.77Improved
use joint token decoding instead of past-condition decoding (ablation)MotionChain · HumanML3D motion compositionMPJPE: 232.46 -> 108.77Improved
joint token decoding versus independent decoding on diversity (ablation)MotionChain · HumanML3D motion compositionDiversity: 6.47 -> 5.56Hurt
use linear projection instead of Q-former or perceiver vision tokenizer (ablation)MotionChain · BEDLAM first-frameMPJPE: 195.49 / 185.61 -> 144.37Improved
linear versus Q-former on last-frame condition (ablation)MotionChain · BEDLAM last-frameMPJPE: 134.73 -> 133.73No clear effect
do not share motion codes across quantizer layers (separate tokens per layer) (ablation)MotionChain · HumanML3D text-to-motionFID: 0.291 -> 0.248Improved
increase codebook dimension d from 128 to 1024 (ablation)motion VQ-VAE · HumanML3DFID: 1.698 -> 0.014Improved
increase residual quantizer layers from 2 to 8 or 16 (ablation)motion VQ-VAE · HumanML3DMPJPE: 79.7 -> 49.7Improved
use multimodal motion-aware model instead of text-only LLMs for motion reasoningMotionChain · Motion reasoningBleu@4: 7.39 -> 19.19Improved
use MotionChain versus MotionGPT for motion predictionMotionChain · AMASS motion predictionFID: FID 0.905 -> 1.053; ADE 4.745 -> 4.388Mixed
use MotionChain versus T2M-GPT for text-to-motion FIDMotionChain · HumanML3D text-to-motionFID: 0.116 -> 0.248Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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