Visual Object Tracking On Davis 2016

评估指标

F-measure (Decay)

F-measure (Mean)

F-measure (Recall)

Ju0026F

Jaccard (Decay)

Jaccard (Mean)

Jaccard (Recall)

评测结果

各个模型在此基准测试上的表现结果

								Paper Title	Repository
ISVOS (BL30K, MS)	-	94.2	-	93.4	-	92.5	-	Look Before You Match: Instance Understanding Matters in Video Object Segmentation	-
XMem (BL30K, MS)	-	94.4	-	93.3	-	92.2	-	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
SwinB-AOST (L'=3, MS)	-	94.5	-	93.0	-	91.5	-	Scalable Video Object Segmentation with Identification Mechanism
SwinB-AOTv2-L (MS)	-	94.4	-	93.0	-	91.6	-	Scalable Video Object Segmentation with Identification Mechanism
SwinB-DeAOT-L	-	94.7	-	92.9	-	91.1	-	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
XMem (MS)	-	93.5	-	92.7	-	92.0	-	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
SwinB-AOTv2-L	-	94.1	-	92.4	-	90.6	-	Scalable Video Object Segmentation with Identification Mechanism
SwinB-AOST (L'=3)	-	94.2	-	92.4	-	90.5	-	Scalable Video Object Segmentation with Identification Mechanism
R50-DeAOT-L	-	94.0	-	92.3	-	90.5	-	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
R50-AOST (L'=3)	-	93.6	-	92.1	-	90.6	-	Scalable Video Object Segmentation with Identification Mechanism
SwinB-AOT-L	-	93.3	-	92.0	-	90.7	-	Associating Objects with Transformers for Video Object Segmentation
DeAOT-L	-	93.7	-	92.0	-	90.3	-	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
XMem (BL30K)	-	93.2	-	92.0	-	90.7	-	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
QDMN	-	93.2	-	92.0	-	90.7	-	Learning Quality-aware Dynamic Memory for Video Object Segmentation
R50-AOST (L'=2)	-	93.4	-	92.0	-	90.5	-	Scalable Video Object Segmentation with Identification Mechanism
STCN + TrickVOS (PT)	-	93.1	-	91.8	-	90.5	-	TrickVOS: A Bag of Tricks for Video Object Segmentation	-
RAVOS	-	92.6	-	91.7	-	90.8	-	Region Aware Video Object Segmentation with Deep Motion Modeling	-
STCN	4.3	93.0	97.1	91.7	4.1	90.4	98.1	Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
XMem	-	92.7	-	91.5	-	90.4	-	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
MobileVOS (BL30K)	-	92.6	-	91.4	-	90.3	-	MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation	-

0 of 78 row(s) selected.