AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Temporal Model Adaptation for Person Re-identification

Niki Martinel, Abir Das, Christian Micheloni, Amit K. Roy-Chowdhury

ECCV 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 99 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 incremental model updates (TMA1 to TMA4)TMA · VIPeRrank-1 accuracy (%): 35.13 -> 41.46Improved
add incremental model updates (TMA1 to TMA4)TMA · PRID450Srank-1 accuracy (%): 45.33 -> 52.89Improved
add incremental model updates (TMA1 to TMA4)TMA with BoW · Market-1501rank-1 accuracy (%): 28.77 -> 44.74Improved
train on all data in one batch (TMA0) instead of 4 incremental updates (ablation)TMA · VIPeRrank-1 accuracy (%): 41.46 -> 43.83Mixed
fuse TMA0 scores with LADF scoresTMA0 · VIPeRrank-1 accuracy (%): 43.83 -> 48.19Improved
replace BoW features with LOMO features (ablation)TMA4 · Market-1501rank-1 accuracy (%): 44.74 -> 47.92Improved
add similarity measure to dissimilarity-only learning (ablation)TMA · VIPeRrank-1 accuracy (%): 7% at rank 1Improved
add l2,1 norm regularizers on projections (ablation)TMA · VIPeRrank-1 accuracy (%): degradation of 3% when removedImproved
probe relevant set threshold epsilon 0.01 instead of 0.1 (ablation)TMA4 · VIPeRrank-1 accuracy (%): 41.46 -> 37.97Hurt
probe relevant set threshold epsilon 0.5 instead of 0.1 (ablation)TMA4 · VIPeRrank-1 accuracy (%): 41.46 -> 38.61Hurt
use graph-based relevant set selection instead of full supervised labeling (ablation)TMA4 · VIPeRrank-1 accuracy (%): 39.87 -> 41.46Improved
use unsupervised or semi-supervised pair labeling instead of selected human labeling (ablation)TMA incremental updates · VIPeRrank-1 accuracyHurt

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