AI Paper Atlas

Research map / Detection and segmentation / CNN features

End-to-End Trainable Trident Person Search Network Using Adaptive Gradient Propagation

Byeong-Ju Han, Kuhyeun Ko, Jae-Young Sim

ICCV 2021 · Detection and segmentation › CNN features · approach: Pedestrian and crowd detection · 42 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 part classification branch (ablation)Trident person search network · PRW multi-view detectionAP: 93.22 -> 94.54Improved
add part classification branch (ablation)Trident person search network · PRW multi-view detectionRecall: 97.02 -> 97.49Improved
add part classification branch (ablation)Trident person search network · PRW multi-view re-idmAP: 46.52 -> 48.04Improved
add part classification branch (ablation)Trident person search network · PRW multi-view re-idTop-1: 72.19 -> 73.21Improved
add AGWF (ablation)Trident person search network · PRW multi-view detectionAP: 92.30 -> 94.54Improved
add AGWF (ablation)Trident person search network · PRW multi-view detectionRecall: 95.20 -> 97.49Improved
add AGWF (ablation)Trident person search network · PRW multi-view re-idmAP: 46.87 -> 48.04Improved
add AGWF (ablation)Trident person search network · PRW multi-view re-idTop-1: 72.92 -> 73.21Improved
add part classification without AGWF (ablation)Trident person search network · PRW multi-view detectionAP: 92.67 -> 92.30Hurt
add AGWF when part classification is absent (ablation)Trident person search network · PRW multi-view re-idTop-1: 70.24 -> 72.19Improved
add Lbin and Lun losses (ablation)Trident person search network · PRWmAP: 47.44 -> 48.04Improved
add Lbin and Lun losses (ablation)Trident person search network · PRWTop-1: 71.85 -> 73.21Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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