AI Paper Atlas

Research map / Detection and segmentation / Tracking

LIMMT: Less Is More for Motion Tracking

Yu Guan, Zekun Qi, Chenghuai Lin, Xuchuan Chen, Wenyao Zhang, Jilong Wang, XinQiang Yu, He Wang, Li Yi

ICML 2026 · Detection and segmentation › Tracking · approach: Transformer-based video object tracking · 0 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
train on GQS-curated 3% of AMASS instead of the full datasetAny2Track · AMASS testSuccess Rate: 0.942 -> 0.956Improved
train on GQS-curated 3% of AMASS instead of the full datasetTWIST2 · AMASS testSuccess Rate: 0.825 -> 0.861Improved
random 3% subsampling instead of GQS selection (ablation)Any2Track · AMASS testSuccess Rate: 0.942 -> 0.838Hurt
random 3% subsampling instead of GQS selection (ablation)TWIST2 · AMASS testSuccess Rate: 0.825 -> 0.649Hurt
add physics filtering at 100% data scale (ablation)Any2Track · AMASS testSuccess Rate: 94.2% -> 95.4%Improved
add physics filter before embedding-based selection at 3% data (ablation)GQS · AMASS test, 3% dataSuccess Rate: 0.911 -> 0.956Improved
add diversity-based FPS to complexity-only selection (ablation)GQS · AMASS test, 3% dataSuccess Rate: 0.934 -> 0.956Improved
add complexity weighting to vanilla FPS (ablation)GQS · AMASS test, 3% dataSuccess Rate: 0.946 -> 0.956Improved
raise data ratio from 10% to 90% of GQS selection (ablation)Any2Track+GQS · AMASS testSuccess RateNo clear effect
train on top physical-score slice only versus mid-score slice (ablation)Any2Track · AMASS physical score percentile slicesSuccess Rate: 94.6% (0-10%) vs 96.3% (60-70%) vs 92.2% (90-100%)Mixed
filter out high-velocity or high-jerk motions (ablation)motion data curation · AMASS sensitivity analysistracking performanceHurt
filter out floating and foot-sliding motions (ablation)motion data curation · AMASS sensitivity analysistracking performance: Impact +2.6 floating, +1.0 foot slideImproved

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