AI Paper Atlas

Research map / Detection and segmentation / Tracking

Robust Object Tracking Based on Temporal and Spatial Deep Networks

Zhu Teng, Junliang Xing, Qiang Wang, Congyan Lang, Songhe Feng, Yi Jin

ICCV 2017 · Detection and segmentation › Tracking · approach: Siamese network tracking · 62 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 Net (ablation)TSN tracker · VOT2014EAO: 0.26 -> 0.32Improved
add Temporal Net (ablation)TSN tracker · VOT2014robustness (Rav, lower better): 1.36 -> 0.75Improved
add Spatial Net (ablation)TSN tracker · VOT2014robustness (Rav, lower better): 1.35 -> 0.75Improved
add Spatial Net (ablation)TSN tracker · VOT2014EAO: 0.30 -> 0.32Improved
add Spatial Net (ablation)TSN tracker · VOT2014accuracy (Aav): 0.61 -> 0.64Improved
use L1 loss instead of L2 loss in Temporal Net (ablation)TSN tracker · VOT2014EAO: 0.29 -> 0.32Improved
use L1 loss instead of L2 loss in Temporal Net (ablation)TSN tracker · VOT2014accuracy (Aav): 0.62 -> 0.64No clear effect
use L1 loss instead of L2 loss in Temporal Net (ablation)TSN tracker · VOT2014robustness (Rav, lower better): 1.07 -> 0.75Improved
compare TSN (no tracking pre-training) with MDNet pre-trained on tracking videosTSN · OTB100AP: 0.909 -> 0.868Hurt
compare TSN with DeepSRDCFTSN · OTB100AP: 0.851 -> 0.868Improved

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