AI Paper Atlas

Research map / Detection and segmentation / CNN features

RCAA: Relational Context-Aware Agents for Person Search

Xiaojun Chang, Po-Yao Huang, Yi-Dong Shen, Xiaodan Liang, Yi Yang, Alexander G. Hauptmann

ECCV 2018 · Detection and segmentation › CNN features · approach: Pedestrian and crowd detection · 128 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 relational spatial and temporal context (ablation)RCAA · Person search benchmarkmAP (%): 69.8 -> 79.3Improved
add relational spatial context to temporal-only agent (ablation)RCAA · Person search benchmarkmAP (%): 71.4 -> 79.3Improved
add relational spatial context to temporal-only agent (ablation)RCAA · Person search benchmarkCMC top-1 (%): 74.8 -> 81.3Improved
use relational context feature instead of global context feature (ablation)RCAA · Person search benchmarkmAP (%): 76.7 -> 79.3Improved
use relational context feature instead of global context feature (ablation)RCAA · Person search benchmarkCMC top-1 (%): 78.9 -> 81.3Improved
add global context plus temporal context over no spatial context (ablation)RCAA · Person search benchmarkmAP (%): 69.8 -> 76.7Improved
use RCAA instead of Joint Detection and Identificationperson search · Person search benchmark (CNN detector)mAP (%): 75.7 -> 79.3Improved
use RCAA instead of Joint Detection and Identification with ground-truth boxesperson search · Person search benchmarkmAP (%): 77.9 -> 79.3Improved
use off-the-shelf CCF detector instead of perfect GT detectorDSIFT + Euclidean · Person search benchmarkCMC top-1 (%): 45.9 -> 11.7Hurt
add more gallery images (increase gallery size from 50 to 6,978)all compared methods · Person search benchmarkCMC top-1 and mAP: performance decreases as gallery size increasesHurt

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