AI Paper Atlas

Research map / Detection and segmentation / Tracking

AerialMind: Towards Referring Multi-Object Tracking in UAV Scenarios

Chenglizhao Chen, Shaofeng Liang, Runwei Guan, Xiaolou Sun, Haocheng Zhao, Haiyun Jiang, Tao Huang, Henghui Ding, Qing-Long Han

AAAI 2026 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 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 CFE and SACR (ablation)HETrack · AerialMind in-domainHOTA: 26.41 -> 31.46Improved
add co-evolutionary fusion encoder (CFE) (ablation)HETrack · AerialMind in-domainHOTA: 28.27 -> 31.46Improved
add scale adaptive contextual refinement (SACR) (ablation)HETrack · AerialMind in-domainHOTA: 29.89 -> 31.46Improved
use full semantic guidance module instead of concatenation (ablation)HETrack · AerialMind in-domainHOTA: 28.88 -> 31.46Improved
use full semantic guidance instead of cross-attention with Ts (ablation)HETrack · AerialMind in-domainHOTA: 30.52 -> 31.46Improved
use full semantic guidance instead of cross-attention with Ts (ablation)HETrack · AerialMind in-domainAssA: 48.82 -> 46.23Hurt
use full semantic guidance instead of addition (ablation)HETrack · AerialMind in-domainAssA: 46.65 -> 46.23Hurt
HETrack vs best prior method on in-domain testHETrack vs MGLT · AerialMind in-domainHOTA: 26.16 -> 31.46Improved
HETrack vs TempRMOT on associationHETrack vs TempRMOT · AerialMind in-domainAssA: 53.22 -> 46.23Hurt
HETrack vs TransRMOT on localizationHETrack vs TransRMOT · AerialMind in-domainLocA: 83.47 -> 82.77Hurt
evaluate HETrack on cross-domain UAVDTHETrack · AerialMind cross-domain (UAVDT)HOTA: 27.58 -> 31.60Improved
HETrack on ground-level Refer-KITTI-V2HETrack · Refer-KITTI-V2HOTA: 36.18 vs 35.40No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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