AI Paper Atlas

Research map / Video / Video generation

BAMM: Bidirectional Autoregressive Motion Model

Ekkasit Pinyoanuntapong, Muhammad Usama Saleem, Pu Wang, Minwoo Lee, Srijan Das, Chen Chen

ECCV 2024 · Video › Video generation · approach: Text-to-motion diffusion · 58 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 bidirectional autoregressive refinement (second iteration) after unidirectional decoding (ablation)BAMM · HumanML3DFID: 0.064 -> 0.055Improved
add a third decoding iteration (ablation)BAMM · HumanML3DFID: 0.055 -> 0.055No clear effect
mask every other token instead of low-confidence tokens in refinement (ablation)BAMM · HumanML3DFID: 0.065 -> 0.055Improved
use suffix masking instead of every-other-token masking (ablation)BAMM · HumanML3DR-Precision Top-1: 0.525 -> 0.519Hurt
raise first-iteration CFG scale from 2 to 4 (ablation)BAMM · HumanML3DFID: 0.105 -> 0.055Improved
raise first-iteration CFG scale from 4 to 5 (ablation)BAMM · HumanML3Dmixed: FID 0.055 -> 0.052; Top-1 0.525 -> 0.522Mixed
use predicted instead of ground-truth length for MoMaskMoMask · HumanML3DFID: 0.045 -> 0.090Hurt
use predicted instead of ground-truth length for MMMMMM · HumanML3DR-Precision Top-1: 0.515 -> 0.504Hurt
sample length multinomially instead of top-1 from a separate length estimatorMoMask · HumanML3DFID: 0.090 -> 0.120Hurt
sample length multinomially instead of top-1MMM · HumanML3DFID: 0.080 -> 0.099Hurt
use BAMM bidirectional autoregressive model instead of MoMask for editingtemporal editing · HumanML3D prefix/suffixR-Precision Top-1: prefix 0.536 vs 0.532; suffix 0.532 vs 0.527No clear effect
use BAMM instead of MDM for temporal editingtemporal editing · HumanML3D inpaintingFID: 2.362 -> 0.056Improved

Later papers that compared with this method

6 later accepted papers report BAMM as a baseline in their results tables; 5 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