HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Video Object Segmentation On Davis 2017 Val

评估指标

F-measure
Jaccard
Mean Jaccard u0026 F-Measure

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
Jaccard
Mean Jaccard u0026 F-Measure
Paper TitleRepository
TransVOS86.481.483.9BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
XMem89.582.986.2XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
AOT87.582.384.9BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
CFBI84.579.381.9BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
UniVS(Swin-L)79.572.876.2UniVS: Unified and Universal Video Segmentation with Prompts as Queries
RMN868183.5BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
STM84.379.2-BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
LWL84.179.181.6BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
BATMAN89.3-86.2BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
SST85.179.982.5BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
CFBI+85.780.182.9BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
STCN88.682.285.4BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
LCM86.580.5-BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
RPCMVOS-81.383.7BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
KMN85.68082.8BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
XMem (BLK30K, MS)92.686.389.5XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
AFB-URR76.17374.6BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation-
0 of 17 row(s) selected.