#424 · Primary category： Computer Vision
STCN
[NeurIPS 2021] Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
Project last updated：03/15/24
GitHub Stars
567
Forks
73
Contributors
1
License
MIT
Why we included this project
STCN is a research codebase for semi-supervised video object segmentation. You draw a mask around the object in the first frame, and the network carries that segmentation through the rest of the clip. It runs at 20+ FPS on a single consumer GPU, faster with mixed precision, while still posting top results on DAVIS and YouTubeVOS. The repo ships pretrained models, inference scripts, and training code that reproduces the paper's numbers on two 11GB GPUs, so it is usable, not just a paper artifact. Teams that need to track a specific object across frames, whether for video editing, surveillance, or content analysis, will find the memory-coverage design a good place to start, and the interactive GUI makes it easy to try the model on your own footage.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)