HyperAI超神经

Semi Supervised Video Object Segmentation On 15

评估指标

EAO

评测结果

各个模型在此基准测试上的表现结果

模型名称
EAO
Paper TitleRepository
MCITrack-L3840.624Exploring Enhanced Contextual Information for Video-Level Object Tracking
SwinB-DeAOT-L0.622Decoupling Features in Hierarchical Propagation for Video Object Segmentation
SwinB-AOT-L0.586Associating Objects with Transformers for Video Object Segmentation
R50-DeAOT-L0.613Decoupling Features in Hierarchical Propagation for Video Object Segmentation
DeAOT-B0.571Decoupling Features in Hierarchical Propagation for Video Object Segmentation
ODTrack-B0.581ODTrack: Online Dense Temporal Token Learning for Visual Tracking
DeAOT-L0.591Decoupling Features in Hierarchical Propagation for Video Object Segmentation
AOT-S0.512Associating Objects with Transformers for Video Object Segmentation
RPT0.530RPT: Learning Point Set Representation for Siamese Visual Tracking-
DAM4SAM0.729A Distractor-Aware Memory for Visual Object Tracking with SAM2
ODTrack-L0.605ODTrack: Online Dense Temporal Token Learning for Visual Tracking
AOT-B0.541Associating Objects with Transformers for Video Object Segmentation
DeAOT-T0.472Decoupling Features in Hierarchical Propagation for Video Object Segmentation
DeAOT-S0.593Decoupling Features in Hierarchical Propagation for Video Object Segmentation
AlphaRef0.482Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation-
AOT-L0.574Associating Objects with Transformers for Video Object Segmentation
MCITrack-B2240.619Exploring Enhanced Contextual Information for Video-Level Object Tracking
R50-AOT-L0.569Associating Objects with Transformers for Video Object Segmentation
AOT-T0.435Associating Objects with Transformers for Video Object Segmentation
MixFormer-L0.555MixFormer: End-to-End Tracking with Iterative Mixed Attention
0 of 20 row(s) selected.