AI Paper Atlas

Research map / Detection and segmentation / Tracking

TGTrack: Temporal Generative Learning for Unified Single Object Tracking

Wanting Geng, Xin Chen, Chuanyu Sun, Jie Zhao, Ben Kang, Dong Wang, Huchuan Lu

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

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 the temporal generative decoder (ablation)TGTrack-B256 · 5 benchmarks average (ablation)average AUC change: -1.50 when removedImproved
add the time token embedding (ablation)TGTrack-B256 · 5 benchmarks average (ablation)average AUC change: -0.44 when removedImproved
add both decoder and time token embedding (ablation)TGTrack-B256 · 5 benchmarks average (ablation)average AUC change: -2.36 when both removedImproved
add gated fusion module in the decoder (ablation)TGTrack-B256 · 5 benchmarks average (ablation)average AUC change: -0.84 when removedImproved
make time token learnable (ablation)TGTrack-B256 · 5 benchmarks average (ablation)average AUC change: -0.58 when non-learnableImproved
predict next frame instead of current frame (ablation)TGTrack-B256 · 5 benchmarks average (ablation)average AUC change: -0.90 when predicting current frameImproved
vary generative decoder depth (4, 6, 10 vs 8 blocks) (ablation)TGTrack-B256 · 5 benchmarks average (ablation)average AUC change: -0.32 (4), -0.08 (6), -0.20 (10)Mixed
vary video clip length (3, 4, 6 vs 5 frames) (ablation)TGTrack-B256 · 5 benchmarks average (ablation)average AUC change: -0.36 (3), -0.10 (4), -0.06 (6)Mixed
vary generative loss weight (0.01, 0.5, 1.0 vs 0.1) (ablation)TGTrack-B256 · 5 benchmarks average (ablation)average AUC change: -0.08 (0.01), -0.06 (0.5), -0.20 (1.0)Mixed
temporal generative learning in unified tracker (vs SUTrack-B384)TGTrack-B384 · LaSOTAUC: 74.4 -> 75.3Improved
scale backbone from B384 to L384TGTrack · LaSOTAUC: 75.3 -> 76.4Improved
use generative decoder only in training (disabled at inference)TGTrack · inference costoverheadNo clear effect

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