Visual Object Tracking On Davis 2017

评估指标

F-measure (Mean)

Ju0026F

Jaccard (Mean)

Params(M)

Speed (FPS)

评测结果

各个模型在此基准测试上的表现结果

模型名称	F-measure (Mean)	Ju0026F	Jaccard (Mean)	Params(M)	Speed (FPS)	Paper Title	Repository
DeAOT-S	83.8	80.8	77.8	10.2	49.2	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
DeAOT-L	87.1	84.1	81.0	13.2	28.5	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
AOT-S	83.9	81.3	78.7	7.0	40.0	Associating Objects with Transformers for Video Object Segmentation
XMem (MS)	91.0	88.2	85.4	-	-	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
MuG-W	58.0	56.05	54.1	-	-	Learning Video Object Segmentation from Unlabeled Videos
SwinB-AOST (L'=3, MS)	89.5	86.7	83.8	65.6	1.3	Scalable Video Object Segmentation with Identification Mechanism
TVOS	74.7	72.3	69.9	-	-	A Transductive Approach for Video Object Segmentation
RPCMVOS	86	83.7	81.3	-	-	Reliable Propagation-Correction Modulation for Video Object Segmentation
R50-AOST (L'=1)	86.1	83.7	81.2	12.5	37.4	Scalable Video Object Segmentation with Identification Mechanism
SwinB-AOT-L	88.4	85.4	82.4	65.4	12.1	Associating Objects with Transformers for Video Object Segmentation
SwinB-AOTv2-L	89.4	86.3	83.1	65.6	12.0	Scalable Video Object Segmentation with Identification Mechanism
SwinB-AOTv2-L (MS)	89.8	87.0	84.2	65.6	1.3	Scalable Video Object Segmentation with Identification Mechanism
JOINT	81.2	78.6	76.0	-	-	Joint Inductive and Transductive Learning for Video Object Segmentation
UVC	61.3	59.5	57.7	-	-	Joint-task Self-supervised Learning for Temporal Correspondence
XMem (BL30K, MS)	92.6	89.5	86.3	-	-	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
OSVOS-S	71.3	68	64.7	-	-	Video Object Segmentation Without Temporal Information	-
DEVA	91.0	87.6	84.2	-	25.3	Tracking Anything with Decoupled Video Segmentation
Spatiotemporal CNN	64.6	61.65	58.7	-	-	Spatiotemporal CNN for Video Object Segmentation
XMem (DAVIS only)	79.3	76.7	74.1	-	22.6	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
MAMP	71.2	69.7	68.3	-	-	Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation

0 of 82 row(s) selected.