Video Object Segmentation On Davis 2016

评估指标

F-Score

Ju0026F

Jaccard (Mean)

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-Score	Ju0026F	Jaccard (Mean)	Paper Title	Repository
ISVOS (BL30K, MS)	94.2	93.4	92.5	Look Before You Match: Instance Understanding Matters in Video Object Segmentation	-
KMN (val)	91.5	90.5	89.5	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
ViTAE-T-Stage	90.4	89.8	89.2	ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias
AOT (val)	92.1	91.1	90.1	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
RMN (val)	88.7	88.8	88.9	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
DFNet	81.8	-	-	Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation	-
CFBI (val)	90.5	89.4	88.3	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
XMem (BL30K, MS)	94.4	93.3	92.2	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
AOC-MF (val)	94.7	-	88.5	Towards Robust Video Object Segmentation with Adaptive Object Calibration
STCN (val)	92.5	91.6	90.8	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
VOSwL (Language)	-	-	-	Video Object Segmentation with Language Referring Expressions	-
STM (val)	89.9	-	88.7	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
LOCATE	-	-	-	LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training
LCM (val)	91.4	90.7	89.9	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
Ours	-	-	83.4	Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation	-
3DC-Seg	84.7	-	84.3	Making a Case for 3D Convolutions for Object Segmentation in Videos
FODVid	-	-	-	FODVid: Flow-guided Object Discovery in Videos	-
CFBI+ (val)	91.1	89.9	88.7	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
TransVOS (val)	91.2	90.5	89.8	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
BATMAN (val)	94.2	92.5	90.7	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-

0 of 24 row(s) selected.