AI Paper Atlas

Research map / Video / Video segmentation and tracking

Spatial-Temporal Graph Mamba for Music-Guided Dance Video Synthesis

Hao Tang, Ling Shao, Zhenyu Zhang, Luc Van Gool, Nicu Sebe

TPAMI 2025 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 7 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
add SG-SSM (spatial graph SSM) (ablation)MDVS-style baseline · Music-to-skeleton (k-pop/ballet/popping)PFD: 653.8 -> 428.3Improved
add TGF-SSM (temporal forward SSM) (ablation)MDVS-style baseline · Music-to-skeleton (k-pop/ballet/popping)PFD: 653.8 -> 326.9Improved
add TGB-SSM (temporal backward SSM) (ablation)MDVS-style baseline · Music-to-skeleton (k-pop/ballet/popping)PFD: 653.8 -> 318.6Improved
add TGB-SSM to TGF-SSM (bidirectional temporal modeling) (ablation)MDVS-style baseline · Music-to-skeleton (k-pop/ballet/popping)PFD: 326.9 -> 130.7Improved
add SG-SSM to bidirectional temporal SSMs (ablation)STG-Mamba · Music-to-skeleton (k-pop/ballet/popping)PFD: 130.7 -> 86.2Improved
add SG-SSM to bidirectional temporal SSMs (ablation)STG-Mamba · Music-to-skeleton (k-pop/ballet/popping)BC: 0.629 -> 0.684Improved
add SG-SSM to bidirectional temporal SSMs (ablation)STG-Mamba · Music-to-skeleton (k-pop/ballet/popping)PVar: 0.761 -> 0.875Improved
add forward self-supervised regularization (FSR) (ablation)Vid2Vid baseline · Skeleton-to-video (collected dataset)FVD: 81.5 -> 57.3Improved
add backward self-supervised regularization (BSR) (ablation)Vid2Vid baseline · Skeleton-to-video (collected dataset)FVD: 81.5 -> 55.2Improved
add BSR to FSR (ablation)Vid2Vid baseline · Skeleton-to-video (collected dataset)FID: 42.89 -> 35.17Improved
add BSR to FSR (ablation)Vid2Vid baseline · Skeleton-to-video (collected dataset)LPIPS: 0.1785 -> 0.1529Improved
use Mamba-based STGM blocks instead of Transformer (EDGE)STG-Mamba · Music-to-skeleton (k-pop/ballet/popping)Inference time (s): 4.8 -> 2.2Improved

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