AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

An Efficient Person Clustering Algorithm for Open Checkout-Free Groceries

Junde Wu, Yu Zhang, Rao Fu, Yuanpei Liu, Jing Gao

ECCV 2022 · Graph learning › Graph algorithms and clustering · approach: Neural and local graph clustering · 2 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 time-space constraint and track information (ablation)Baseline NN clustering · DaiCOFGBCubed F-score: 78.47 -> 85.35Improved
add time-space constraint and track information (ablation)Baseline NN clustering · IseCOFGBCubed F-score: 85.40 -> 88.42Improved
add time-space constraint and track information (ablation)Baseline NN clustering · DaiCOFGtime (s per 1000 queries): 46.61 -> 8.27Improved
add NN-M merge strategy (ablation)TS · DaiCOFGBCubed F-score: 85.35 -> 87.67Improved
add NN-M merge strategy (ablation)TS · DaiCOFGBCubed precision: 91.25 -> 91.22Hurt
replace cosine with vMF similarity in NN-A and NN-M (ablation)TS-M · DaiCOFGBCubed F-score: 87.67 -> 94.71Improved
replace cosine with vMF similarity in NN-A and NN-M (ablation)TS-M · DaiCOFGtime (s per 1000 queries): 9.13 -> 11.06Hurt
add GCN with CSG (cosine) (ablation)TS-M · DaiCOFGBCubed F-score: 87.67 -> 96.60Improved
add GCN with CSG (cosine) (ablation)TS-M · IseCOFGBCubed F-score: 92.54 -> 97.32Improved
use vMF weight in CSG instead of cosine (ablation)Cos-GCN · DaiCOFGBCubed F-score: 96.60 -> 98.50Improved
use vMF weight in CSG instead of cosine (ablation)Cos-GCN · IseCOFGBCubed F-score: 97.32 -> 98.91Improved
use vMF weight in CSG instead of cosine (ablation)Cos-GCN · DaiCOFGtime (s per 1000 queries): 11.81 -> 13.68Hurt

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