AI Paper Atlas

Research map / Detection and segmentation / Tracking

Joint Representation and Truncated Inference Learning for Correlation Filter based Tracking

Yingjie Yao, Xiaohe Wu, Lei Zhang, Shiguang Shan, Wangmeng Zuo

ECCV 2018 · Detection and segmentation › Tracking · approach: Siamese network tracking · 50 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 truncated inference learning (updater network) to fixed VGG-M features (ablation)BACF-VGGM · OTB-2015AUC: 63.1 -> 66.5Improved
add joint feature representation learning to RTINet-VGGM (ablation)RTINet-VGGM · OTB-2015AUC: 66.5 -> 68.2Improved
add learned representation to BACF with VGG-M (ablation)BACF-VGGM · OTB-2015AUC: 63.1 -> 64.0Improved
replace HOG features with VGG-M features in BACF (ablation)BACF · OTB-2015AUC: 61.5 -> 63.1Improved
use RTINet-learned features in CFNet (ablation)CFNet · OTB-2015AUC: 56.8 -> 58.0Improved
use RTINet-learned features in CFNet-conv1 (ablation)CFNet-conv1 · OTB-2015AUC: 53.6 -> 54.8Improved
integrate BACF unrolled ADMM inference and joint learning in place of CFNet (ablation)CFNet · OTB-2015AUC: 56.8 -> 68.2Improved
use three conv layers instead of conv1 only in RTINet (ablation)RTINet-conv1 · OTB-2015AUC: 64.3 -> 68.2Improved
increase stages from one to two (ablation)RTINet · OTB-2015AUC: 59.6 -> 68.2Improved
increase stages beyond two (up to ten) (ablation)RTINet · OTB-2015AUC: 68.2 -> 66.2Hurt
train RTINet with a fixed stage count of 10 versus train small K directly (ablation)RTINet · OTB-2015AUCHurt
RTINet versus ECO on VOT2016 accuracy and robustnessRTINet · VOT2016accuracy / robustness: 0.57 vs 0.54 accuracy; 1.07 vs 0.72 robustnessMixed

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