AI Paper Atlas

Research map / Video / Video generation

Adaptive Capacity Autoregressive Visual Tracking

Tong Lin, Yifan Bai, Shiyi Liang, Ruigang Niu, Xing Wei

CVPR 2026 · Video › Video generation · approach: Autoregressive long video generation

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
use adaptive capacity switching between accurate and efficient trackersARTrack-AC · LaSOTAUC (%) and GPU FPS: 60.2 AUC / 210 FPS (nano) and 69.4 / 65 FPS (ARTrackOT) -> 66.7 AUC / 191 FPSImproved
run efficient mode in parallel instead of sequentially (ablation)ARTrack-AC · LaSOTGPU FPS: 131 -> 191 FPS, AUC 66.5 -> 66.7Improved
use difficulty-aware switching instead of fixed-cycle switching (ablation)ARTrack-ACseq · LaSOTAUC (%): 65.8 -> 66.5Improved
use supervised cosine-distance signal instead of training-free stability signal (ablation)ARTrack-ACseq · LaSOTAUC (%): 66.5 -> 65.9Hurt
use diffusion trajectory predictor instead of regression (ablation)ARTrack-AC · LaSOTAUC (%): 53.9 -> 56.9Improved
use diffusion trajectories as final output instead of localization-based tracker (ablation)ARTrack-ACpara · LaSOTAUC (%): 66.7 -> 56.9 (refined), 38.5 (self-conditioned)Hurt
increase observation window from 5 to 10 (ablation)ARTrack-ACpara · LaSOTAUC (%) and GPU FPS: 66.7 AUC / 198 FPS -> 63.5 AUC / 291 FPSMixed
use predicted crop for parallel inference on all 5 frames (ablation)ARTrack-AC · LaSOTAUC (%) and GPU FPS: 66.5 -> 66.7 AUC; 134 -> 198 FPSImproved
raise accurate-mode capacity from ARTrackOT to ARTrackv2256 (ablation)ARTrack-ACseq · LaSOTAUC (%): 66.5 -> 67.8Improved
replace efficient mode with non-AR HiT-Tiny (ablation)ARTrack-ACseq · LaSOTAUC (%): 66.5 -> 57.1Hurt
run parallel inference at 10 FPS video (GOT-10k) (ablation)ARTrack-ACpara10 · GOT-10kAO (%): 74.3 -> 62.6Hurt
lower video frame rate for parallel variantARTrack-ACpara · NFS 240 fps vs 30 fpsAUC (%): 69.4 -> 64.8Hurt

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