AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification

Jianing Li, Shiliang Zhang

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 174 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 SAC (self-adaptive one-hot classification) to direct transfer (ablation)direct transfer model · DukeMTMC -> Market1501rank-1 accuracy: 42.1 -> 64.5Improved
add SAC to direct transfer (ablation)direct transfer model · Market1501 -> DukeMTMCrank-1 accuracy: 31.8 -> 59.4Improved
replace visual-only clustering with MTC (visual plus temporal consistency) (ablation)memory-bank baseline · DukeMTMC -> Market1501mAP: 46.6 -> 56.4Improved
replace visual-only clustering with MTC (ablation)memory-bank baseline · Market1501 -> DukeMTMCmAP: 43.6 -> 51.1Improved
combine SAC and MTC (JVTC) instead of the baseline (ablation)memory-bank baseline · DukeMTMC -> Market1501mAP: 46.6 -> 61.1Improved
add SAC to MTC (ablation)MTC · DukeMTMC -> Market1501mAP: 56.4 -> 61.1Improved
add SAC to MTC (ablation)MTC · Market1501 -> DukeMTMCrank-1 accuracy: 71.3 -> 75.0Improved
use joint visual-temporal similarity at test time (JVTC+) (ablation)JVTC · DukeMTMC -> Market1501mAP: 61.1 -> 67.2Improved
use joint similarity at test time (JVTC+) (ablation)JVTC · Market1501 -> DukeMTMCmAP: 56.2 -> 66.5Improved
use joint similarity at test time (JVTC+) (ablation)JVTC · MSMT17 (source DukeMTMC)rank-1 accuracy: 45.4 -> 52.9Improved
use SAC alone instead of the visual-only baselinememory-bank baseline · DukeMTMC -> Market1501rank-1 accuracy: 77.4 -> 64.5Hurt
add positive loss weights w1 and w2 for target losses (versus 0) (ablation)JVTC · Market1501 and DukeMTMC-reIDReID performanceImproved

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