Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Video Object Segmentation On Davis 2017 Val

Metrics

F-measure

Jaccard

Mean Jaccard u0026 F-Measure

Results

Performance results of various models on this benchmark

Model Name	F-measure	Jaccard	Mean Jaccard u0026 F-Measure	Paper Title	Repository
TransVOS	86.4	81.4	83.9	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
XMem	89.5	82.9	86.2	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
AOT	87.5	82.3	84.9	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
CFBI	84.5	79.3	81.9	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
UniVS(Swin-L)	79.5	72.8	76.2	UniVS: Unified and Universal Video Segmentation with Prompts as Queries
RMN	86	81	83.5	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
STM	84.3	79.2	-	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
LWL	84.1	79.1	81.6	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
BATMAN	89.3	-	86.2	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
SST	85.1	79.9	82.5	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
CFBI+	85.7	80.1	82.9	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
STCN	88.6	82.2	85.4	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
LCM	86.5	80.5	-	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
RPCMVOS	-	81.3	83.7	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
KMN	85.6	80	82.8	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-
XMem (BLK30K, MS)	92.6	86.3	89.5	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
AFB-URR	76.1	73	74.6	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation	-

0 of 17 row(s) selected.