AI Paper Atlas

Research map / Detection and segmentation / Tracking

Towards Real-World Visual Tracking With Temporal Contexts

Ziang Cao, Ziyuan Huang, Liang Pan, Shiwei Zhang, Ziwei Liu, Changhong Fu

TPAMI 2023 · Detection and segmentation › Tracking · approach: Transformer-based video object tracking · 120 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 temporal information filter to AT-Trans (single-frame training) (ablation)Transformer · UAV123 overallsuccess: 0.550 -> 0.573Improved
add temporal information filter to AT-Trans (multi-frame training) (ablation)Transformer · UAV123 overallsuccess: 0.508 -> 0.604Improved
multi-frame training without filtering invalid information (ablation)Transformer · UAV123 overallsuccess: 0.550 -> 0.508Hurt
use convolutional (first-frame) init instead of random init of temporal prior (ablation)AT-Trans · UAV123 overallsuccess: 0.586 -> 0.604Improved
use previous-frame refined map as query instead of current feature map F_t (ablation)AT-Trans · UAV123 overallsuccess: 0.580 -> 0.604Improved
increase training video length from 1 to 4 with online TAdaConv+AT-Trans (ablation)TCTrack · OTB100 offlinesuccess: 0.601 -> 0.624Improved
replace online TAdaConv with attention-based ATT-TAdaConv (ablation)TCTrack · OTB100 offlinesuccess: 0.624 -> 0.642Improved
add curriculum learning (video length 2->4) (ablation)ATT-TAdaConv+AT-Trans · GOT-10K onlineAO: 0.333 -> 0.375Improved
add curriculum learning (video length 2->4) (ablation)ATT-TAdaConv+AT-Trans · OTB100 onlinesuccess: 0.510 -> 0.543Improved
add feature-level temporal context with video length 2 or 3 (ablation)Online TAdaConv+AT-Trans · GOT-10K onlineAO: 0.281 -> 0.274Hurt
add temporal modeling at both feature and similarity levels (full TCTrack++) (ablation)spatial backbone baseline · GOT-10K onlineAO: 0.278 -> 0.375Improved
use ResNet50 instead of AlexNet backbone (ablation)TCTrack++ · UAV123online success: 0.519 -> 0.472Hurt

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