Home
AI Tools
AI Models
MCP
AI NEWS
EN
Model Selection
Tags
Multi-frame Mask Prediction
# Multi-frame Mask Prediction
Video Mask2former Swin Small Youtubevis 2021 Instance
MIT
Video Mask2Former model trained on the YouTubeVIS-2021 dataset for video instance segmentation tasks, using Swin Transformer as the backbone network.
Image Segmentation
Transformers
V
shivalikasingh
18
0
Featured Recommended AI Models
Empowering the Future, Your AI Solution Knowledge Base
English
简体中文
繁體中文
にほんご
© 2025
AIbase