HyperAI
HyperAI
Home
News
Latest Papers
Tutorials
Datasets
Wiki
SOTA
LLM Models
GPU Leaderboard
Events
Search
About
English
HyperAI
HyperAI
Toggle sidebar
Search the site…
⌘
K
Home
SOTA
Video Panoptic Segmentation
Video Panoptic Segmentation On Vipseg
Video Panoptic Segmentation On Vipseg
Metrics
STQ
VPQ
Results
Performance results of various models on this benchmark
Columns
Model Name
STQ
VPQ
Paper Title
Repository
TarViS (ResNet-50)
43.1
33.5
TarViS: A Unified Approach for Target-based Video Segmentation
-
CAVIS(VIT-L)
56.1
58.5
Context-Aware Video Instance Segmentation
-
UniVS(Swin-L)
58.2
49.3
UniVS: Unified and Universal Video Segmentation with Prompts as Queries
-
Tube-Link(Swin-base)
49.4
50.4
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation
-
DVIS(Swin-L)
55.3
57.6
DVIS: Decoupled Video Instance Segmentation Framework
-
DEVA (Mask2Former - SwinB)
52.2
55.0
Tracking Anything with Decoupled Video Segmentation
-
MaXTron (ConvNeXt-L)
-
57.1
A Simple Video Segmenter by Tracking Objects Along Axial Trajectories
-
MaXTron (ConvNeXtV2-L)
-
58.0
A Simple Video Segmenter by Tracking Objects Along Axial Trajectories
-
TarViS (Swin-L)
52.9
48.0
TarViS: A Unified Approach for Target-based Video Segmentation
-
DVIS++(VIT-L)
56.0
58.0
DVIS++: Improved Decoupled Framework for Universal Video Segmentation
-
MaXTron (ResNet-50)
-
46.7
A Simple Video Segmenter by Tracking Objects Along Axial Trajectories
-
TarViS (Swin-T)
45.3
35.8
TarViS: A Unified Approach for Target-based Video Segmentation
-
0 of 12 row(s) selected.
Previous
Next
Video Panoptic Segmentation On Vipseg | SOTA | HyperAI