AI Paper Atlas

Research map / Detection and segmentation / Tracking

Motion-Aware Object Tracking via Motion and Geometry-Aware Cues

Hongtao Yang, Bineng Zhong, Qihua Liang, Xiantao Hu, Yufei Tan, Haiying Xia, Shuxiang Song

AAAI 2026 · Detection and segmentation › Tracking · approach: Transformer-based video object tracking · 3 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
fuse geometric (depth) priors in layer 7 (ablation)MoDTrack256 · LaSOTAUC: 71.1 -> 71.3Improved
fuse geometric priors in layers 3 and 7 (ablation)MoDTrack256 · LaSOTAUC: 71.1 -> 71.7Improved
add motion pattern dictionary of size 100 (ablation)MoDTrack256 · LaSOTAUC: 71.1 -> 72.2Improved
increase dictionary size from 100 to 400 (ablation)MoDTrack256 · LaSOTAUC: 72.2 -> 72.6Improved
use attention-matrix matching instead of nearest neighbor (ablation)MoDTrack256 · LaSOTAUC: 72.6 -> 72.9Improved
add all modules (full MoDTrack256 vs baseline) (ablation)MoDTrack256 · LaSOTAUC: 71.1 -> 72.9Improved
use MoDTrack384 vs best prior trackerMoDTrack384 · LaSOTAUC: 73.2 -> 74.4Improved
MoDTrack384 vs TemTrack384MoDTrack384 · LaSOTextAUC: 53.4 vs 53.2Hurt
MoDTrack256 vs TemTrack256MoDTrack256 · LaSOTextAUC: 52.4 -> 52.4No clear effect
MoDTrack384 vs MambaLCTMoDTrack384 · GOT-10kSR0.5: 86.7 vs 86.4Hurt
MoDTrack256 vs MoDTrack384 resolutionMoDTrack · LaSOTAUC: 72.9 -> 74.4Improved

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