HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

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

Paper Title
AOC-MF (val)94.7-88.5Towards Robust Video Object Segmentation with Adaptive Object Calibration
XMem (BL30K, MS)94.493.392.2XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
ISVOS (BL30K, MS)94.293.492.5Look Before You Match: Instance Understanding Matters in Video Object Segmentation
BATMAN (val)94.292.590.7BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
RPCMVOS (val)9490.687.1BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
XMem92.791.590.4XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
MobileVOS (val)92.691.490.3MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation
STCN (val)92.591.690.8BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
AOT (val)92.191.190.1BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
KMN (val)91.590.589.5BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
LCM (val)91.490.789.9BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
TransVOS (val)91.290.589.8BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
CFBI+ (val)91.189.988.7BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
CFBI (val)90.589.488.3BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
ViTAE-T-Stage90.489.889.2ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias
STM (val)89.9-88.7BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
RMN (val)88.788.888.9BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
3DC-Seg84.7-84.3Making a Case for 3D Convolutions for Object Segmentation in Videos
DFNet81.8--Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation
VOSwL (Language)---Video Object Segmentation with Language Referring Expressions
0 of 24 row(s) selected.
Video Object Segmentation On Davis 2016 | SOTA | HyperAI超神经