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
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 time-space constraint and track information (ablation) | Baseline NN clustering · DaiCOFG | BCubed F-score: 78.47 -> 85.35 | Improved |
| add time-space constraint and track information (ablation) | Baseline NN clustering · IseCOFG | BCubed F-score: 85.40 -> 88.42 | Improved |
| add time-space constraint and track information (ablation) | Baseline NN clustering · DaiCOFG | time (s per 1000 queries): 46.61 -> 8.27 | Improved |
| add NN-M merge strategy (ablation) | TS · DaiCOFG | BCubed F-score: 85.35 -> 87.67 | Improved |
| add NN-M merge strategy (ablation) | TS · DaiCOFG | BCubed precision: 91.25 -> 91.22 | Hurt |
| replace cosine with vMF similarity in NN-A and NN-M (ablation) | TS-M · DaiCOFG | BCubed F-score: 87.67 -> 94.71 | Improved |
| replace cosine with vMF similarity in NN-A and NN-M (ablation) | TS-M · DaiCOFG | time (s per 1000 queries): 9.13 -> 11.06 | Hurt |
| add GCN with CSG (cosine) (ablation) | TS-M · DaiCOFG | BCubed F-score: 87.67 -> 96.60 | Improved |
| add GCN with CSG (cosine) (ablation) | TS-M · IseCOFG | BCubed F-score: 92.54 -> 97.32 | Improved |
| use vMF weight in CSG instead of cosine (ablation) | Cos-GCN · DaiCOFG | BCubed F-score: 96.60 -> 98.50 | Improved |
| use vMF weight in CSG instead of cosine (ablation) | Cos-GCN · IseCOFG | BCubed F-score: 97.32 -> 98.91 | Improved |
| use vMF weight in CSG instead of cosine (ablation) | Cos-GCN · DaiCOFG | time (s per 1000 queries): 11.81 -> 13.68 | Hurt |
Closest papers by meaning
- Efficient Parameter-Free Clustering Using First Neighbor Relations (CVPR 2019 · similarity 0.81)
- MVTec D2S: Densely Segmented Supermarket Dataset (ECCV 2018 · similarity 0.80)
- Efficient Constrained K-center Clustering with Background Knowledge (AAAI 2024 · similarity 0.79)
- Spatial-Temporal Knowledge Distillation for Takeaway Recommendation (AAAI 2025 · similarity 0.79)
- Optimizing Label Assignment for Weakly Supervised Person Search (AAAI 2025 · similarity 0.78)
- Competitively Consistent Clustering (ICML 2025 · similarity 0.78)
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.
