AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Motion-aware Sparse Pipeline for Lightweight Object Tracking

Qingmao Wei, Fagui Liu, Dengke Zhang, Qingze He, Quan Tang

ECCV 2026 · Architectures and efficiency › Attention and transformers · approach: Transformer block and depth design · 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
add Gaussian motion prior to attention-based early pruning (ablation)MaST-tiny · LaSOTAUC: 60.5 -> 63.8Improved
replace attention scores with MLP predictor for pruning (ablation)MaST-tiny · LaSOTAUC: 60.5 -> 59.4Hurt
use motion window alone instead of attention + motion (ablation)MaST-tiny · LaSOTAUC: 63.8 -> 62.6Hurt
one-shot token sparsification vs dense (ablation)MaST-tiny · LaSOTAUC: 64.0 -> 63.8No clear effect
sparsify at layer 1 instead of later layers (ablation)MaST-tiny · LaSOTAUC: 63.82 vs 63.96 (layer 6)No clear effect
use sparse MLP head instead of dense MLP head (ablation)MaST-tiny · LaSOTAUC: 64.0 -> 63.8No clear effect
use sparse MLP head instead of 3x3 conv head (ablation)MaST-tiny · LaSOTRPi FPS: 13.8 -> 23.2Improved
use sparse global localization heads (Loc Tokens) (ablation)MaST-tiny · LaSOTAUC: 59.0 -> 57.9Hurt
one-shot token pruning vs resolution reductionMaST-tiny · LaSOTAUC: 58.5 -> 63.8Improved
one-shot token pruning vs layer pruningMaST-tiny · LaSOTAUC: 59.1 -> 63.8Improved
make Gaussian window dynamic with previous box size (ablation)MaST · GOT-10k valAUC: 79.5 -> 79.9Improved
remove motion window (importance score only) (ablation)MaST · GOT-10k valAUC: 79.9 -> 76.9Hurt

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