Person Re Identification On Prid2011

Métriques

Rank-1

Rank-20

Rank-5

Résultats

Résultats de performance de divers modèles sur ce benchmark

				Paper Title
B-BOT + Attention and CL loss*	96.6	-	-	Video Person Re-ID: Fantastic Techniques and Where to Find Them
FGReID	96.1	100	99.1	Fine-Grained Re-Identification
AGRL	93.1	99.8	-	Adaptive Graph Representation Learning for Video Person Re-identification
Snippet (Supervised)	93.0	100.0	99.3	Video Person Re-Identification With Competitive Snippet-Similarity Aggregation and Co-Attentive Snippet Embedding
uPMnet	92.0	100.0	97.7	Exploiting Robust Unsupervised Video Person Re-identification
DAL	85.3	99.6	97.0	Deep Association Learning for Unsupervised Video Person Re-identification
SMP*	80.9	99.4	95.6	Stepwise Metric Promotion for Unsupervised Video Person Re-Identification
DGM+MLAPG+	73.1	99.0	92.5	Dynamic Label Graph Matching for Unsupervised Video Re-Identification
DGM+IDE+	56.4	96.4	81.3	Dynamic Label Graph Matching for Unsupervised Video Re-Identification
UTAL	54.7	96.2	83.1	Unsupervised Tracklet Person Re-Identification
RACE+	50.6	91.8	79.4	Robust Anchor Embedding for Unsupervised Video Person Re-Identification in the Wild
TAUDL	49.4	98.9	78.7	Unsupervised Person Re-identification by Deep Learning Tracklet Association
DASy*	43.0	-	-	Domain Adaptation through Synthesis for Unsupervised Person Re-identification

0 of 13 row(s) selected.

Person Re Identification On Prid2011 | SOTA | HyperAI