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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add part classification branch (ablation) | Trident person search network · PRW multi-view detection | AP: 93.22 -> 94.54 | Improved |
| add part classification branch (ablation) | Trident person search network · PRW multi-view detection | Recall: 97.02 -> 97.49 | Improved |
| add part classification branch (ablation) | Trident person search network · PRW multi-view re-id | mAP: 46.52 -> 48.04 | Improved |
| add part classification branch (ablation) | Trident person search network · PRW multi-view re-id | Top-1: 72.19 -> 73.21 | Improved |
| add AGWF (ablation) | Trident person search network · PRW multi-view detection | AP: 92.30 -> 94.54 | Improved |
| add AGWF (ablation) | Trident person search network · PRW multi-view detection | Recall: 95.20 -> 97.49 | Improved |
| add AGWF (ablation) | Trident person search network · PRW multi-view re-id | mAP: 46.87 -> 48.04 | Improved |
| add AGWF (ablation) | Trident person search network · PRW multi-view re-id | Top-1: 72.92 -> 73.21 | Improved |
| add part classification without AGWF (ablation) | Trident person search network · PRW multi-view detection | AP: 92.67 -> 92.30 | Hurt |
| add AGWF when part classification is absent (ablation) | Trident person search network · PRW multi-view re-id | Top-1: 70.24 -> 72.19 | Improved |
| add Lbin and Lun losses (ablation) | Trident person search network · PRW | mAP: 47.44 -> 48.04 | Improved |
| add Lbin and Lun losses (ablation) | Trident person search network · PRW | Top-1: 71.85 -> 73.21 | Improved |
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.
- TCTS — TCTS: A Task-Consistent Two-Stage Framework for Person Search (CVPR 2020) · better on 2 of 4 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
- Diverse Knowledge Distillation for End-to-End Person Search (AAAI 2021 · similarity 0.88)
- Divide and Conquer: Hybrid Pre-training for Person Search (AAAI 2024 · similarity 0.87)
- Sequential End-to-end Network for Efficient Person Search (AAAI 2021 · similarity 0.87)
- End-to-End Thorough Body Perception for Person Search (AAAI 2020 · similarity 0.87)
- Domain Generalizable Person Search Using Unreal Dataset (AAAI 2024 · similarity 0.85)
- Mixture of Submodules for Domain Adaptive Person Search (CVPR 2025 · similarity 0.84)
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.
