AI Paper Atlas

Research map / Detection and segmentation / Tracking

Toward Low-Cost yet Effective Temporal Learning for UAV Tracking

Chaocan Xue, Qihua Liang, Bineng Zhong, Yanting Zu, Yuanliang Xue, Haiying Xia, Shuxiang Song

CVPR 2026 · Detection and segmentation › Tracking · approach: Transformer-based video object tracking

Read the paper

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
use both attention and classification scores for token extraction instead of attention only (ablation)LETL token extractor · UAVTrack112_LAUC: 67.8 -> 68.2Improved
use both attention and classification scores instead of classification only (ablation)LETL token extractor · UAVTrack112_LAUC: 67.4 -> 68.2Improved
replace merged token value with more recent token instead of averaging (ablation)LETL token combiner · UAVTrack112_LAUC: 67.1 -> 68.2Improved
increase extracted token number K from 16 to 32 (ablation)LETL · UAVTrack112_LAUC: 68.2 -> 68.8 (PPF 55 -> 35)Mixed
reduce extracted tokens K from 16 to 8 (ablation)LETL · UAVTrack112_LAUC: 67.5 -> 65.2 (P=50%)Hurt
raise merging ratio P from 37.5% to 50% (ablation)LETL · UAVTrack112_LAUC: 68.2 -> 67.5Hurt
lower merging ratio P from 37.5% to 25% (ablation)LETL · UAVTrack112_LAUC: 68.2 -> 68.0Hurt
add LETL temporal module to baseline one-stream tracker (ablation)DeiT-Tiny one-stream baseline · UAVTrack112_Lprecision: +5.0 precision for +0.09 FLOPsImproved
add dense template sequence sampling (ODTrack-style) instead of LETL (ablation)DeiT-Tiny one-stream baseline · UAVTrack112_LPPF: +5.9 prec, +0.68 FLOPs, PPF 8.7Hurt
add dynamic template (MixFormer-style) instead of LETL (ablation)DeiT-Tiny one-stream baseline · UAVTrack112_Lprecision: +3.8 precision, +0.40 FLOPs, PPF 9.5Improved
add autoregressive queries (AQATrack-style) instead of LETL (ablation)DeiT-Tiny one-stream baseline · UAVTrack112_Lprecision: +4.3 precision, +0.51 FLOPs, PPF 8.4Improved

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