AI Paper Atlas

Research map / Video / Video segmentation and tracking

Video-Based Person Re-Identification With Spatial and Temporal Memory Networks

Chanho Eom, Geon Lee, Junghyup Lee, Bumsub Ham

ICCV 2021 · Video › Video segmentation and tracking · approach: Spatial-temporal video person re-identification · 124 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 spatial memory to refine frame features (ablation)video re-ID baseline · MARSrank-1 / mAP: 87.3 -> 89.3 rank-1, 79.1 -> 82.5 mAPImproved
add spatial memory to refine frame features (ablation)video re-ID baseline · LS-VIDrank-1 / mAP: 71.6 -> 79.6 rank-1, 55.9 -> 65.8 mAPImproved
add spatial memory to refine frame features (ablation)video re-ID baseline · DukeMTMC-VideoReIDrank-1 / mAP: 95.0 -> 96.2 rank-1, 92.7 -> 94.2 mAPImproved
add temporal memory to aggregate frame features (ablation)video re-ID baseline · MARSrank-1 / mAP: 87.3 -> 89.5 rank-1, 79.1 -> 82.0 mAPImproved
add temporal memory to aggregate frame features (ablation)video re-ID baseline · LS-VIDrank-1 / mAP: 71.6 -> 78.9 rank-1, 55.9 -> 64.4 mAPImproved
add temporal memory to aggregate frame features (ablation)video re-ID baseline · DukeMTMC-VideoReIDrank-1 / mAP: 95.0 -> 95.4 rank-1, 92.7 -> 93.7 mAPImproved
add temporal memory on top of spatial memory (ablation)spatial memory model · MARSrank-1 / mAP: 89.3 -> 89.9 rank-1, 82.5 -> 83.7 mAPImproved
add temporal memory on top of spatial memory (ablation)spatial memory model · LS-VIDrank-1 / mAP: 79.6 -> 80.6 rank-1, 65.8 -> 66.6 mAPImproved
add memory spread loss to both memories (ablation)STMN · MARSrank-1 / mAP: 89.1 -> 89.9 rank-1, 81.9 -> 83.7 mAPImproved
add memory spread loss to both memories (ablation)STMN · LS-VIDrank-1 / mAP: 79.9 -> 80.6 rank-1, 65.4 -> 66.6 mAPImproved
add memory spread loss to the spatial memory only (ablation)baseline + spatial memory · MARSrank-1 / mAP: 88.7 -> 89.3 rank-1, 81.6 -> 82.5 mAPImproved
add memory spread loss to the temporal memory only (ablation)baseline + temporal memory · MARSrank-1 / mAP: 88.5 -> 89.5 rank-1, 81.9 -> 82.0 mAPMixed

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