atlas

Research map / Image generation / Autoregressive and latent generation

Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification

CVPR 2019 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 105 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use UED instead of RED to fuse B2, B3, and B4ModelNet40 retrieval · ModelNet40AUC: 86.48 -> 88.05Helped
Use UED instead of RED to fuse B2, B3, and B4ModelNet40 retrieval · ModelNet40mAP: 85.71 -> 87.30Helped
Use UED instead of RED to fuse B1, B2, and B3ModelNet10 retrieval · ModelNet10AUC: 93.20 -> 93.37Helped
Use UED instead of RED to fuse B1, B3, and B4ModelNet10 retrieval · ModelNet10mAP: 92.17 -> 92.08Hurt
Use UED instead of RED to fuse all four baseline similaritiesHolidays retrieval · HolidaysmAP: 93.32 -> 93.56Helped
Use UED instead of RED with B1, B2, and B3Holidays retrieval · HolidaysmAP: 93.32 -> 93.31No clear effect
Use UED instead of RED with the same baseline similaritiesMarket-1501 re-identification · Market-1501rank-1 accuracy: 94.74 -> 95.90Helped
Use UED instead of RED with the same baseline similaritiesMarket-1501 re-identification · Market-1501mAP: 91.00 -> 92.75Helped

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