AI Paper Atlas

Research map / Detection and segmentation / Tracking

Learning Dynamic Siamese Network for Visual Object Tracking

Qing Guo, Wei Feng, Ce Zhou, Rui Huang, Liang Wan, Song Wang

ICCV 2017 · Detection and segmentation › Tracking · approach: Siamese network tracking · 907 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 online target-variation and background-suppression transformations to static SiamFC (DSiam, conv5 only)SiamFC · OTB-2013AUC of success plot: 5.6% relative improvement over SiamFCImproved
add elementwise multi-layer fusion of conv4 and conv5 (DSiamM vs DSiam)DSiam · OTB-2013AUC of success plot: 5.6% -> 7.9% relative improvement over SiamFCImproved
add elementwise multi-layer fusion (DSiamM vs DSiam)DSiam · VOT-2015overlap: 0.2804 -> 0.2927Improved
add elementwise multi-layer fusion (DSiamM vs DSiam)DSiam · VOT-2015accuracy: 0.5414 -> 0.5566Improved
add the target appearance variation transformation (VT) (ablation)DSiamM · OTB-2013tracking accuracyImproved
add the background suppression transformation (BS) (ablation)DSiamM · OTB-2013tracking accuracyImproved
add elementwise multi-layer fusion (Multi) (ablation)DSiamM · OTB-2013tracking accuracyImproved
learn variation transformation instead of simply updating the template O1 to Ot-1 (ablation)DSiamM · OTB-2013tracking accuracyImproved
use offline-learned elementwise fusion weights instead of fixed fusion weights (ablation)DSiamM · OTB-2013tracking accuracyImproved
use DSiamM instead of the retrained MDNetR-MDNet · OTB-2013AUC of success plot: 6% relative improvementImproved
use DSiamM instead of HCFHCF · OTB-2013AUC of success plot: 8.4% relative improvementImproved

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