Accueil Actualités Articles de recherche récents Tutoriels Ensembles de données Wiki SOTA Modèles LLM Classement GPU Événements

Français

Video Object Segmentation On Youtube Vos 2019 2

Métriques

Jaccard (Seen)

Jaccard (Unseen)

Mean Jaccard u0026 F-Measure

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Jaccard (Seen)	Jaccard (Unseen)	Mean Jaccard u0026 F-Measure	Paper Title	Repository
SST	80.9	76.6	81.8	SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation
XMem	84.3	80.3	85.5	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
BATMAN	84.5	79	85	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
RPCMVOS	82.6	79.1	83.9	Reliable Propagation-Correction Modulation for Video Object Segmentation
CFBI	80.6	75.2	81	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
CFBI+	81.7	77.1	82.6	Collaborative Video Object Segmentation by Foreground-Background Integration
MobileVOS	83.2	76.9	83.3	MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation	-
AOT	83.5	78.4	84.1	Associating Objects with Transformers for Video Object Segmentation
STCN	81.1	78.2	82.7	Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
XMem (BL30K,MS)	85.5	81.8	86.8	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

0 of 10 row(s) selected.