#554 · Primary category： Computer Vision
siamese-fc
Arbitrary object tracking at 50-100 FPS with Fully Convolutional Siamese networks.
Project last updated：05/16/19
GitHub Stars
628
Forks
217
Contributors
4
License
MIT
Why we included this project
Video object tracking researchers will recognize this as the original SiamFC implementation, the fully convolutional Siamese network that tracked arbitrary objects at 50-100 FPS without online fine-tuning. The repo supports two workflows: plug in a pretrained network and run the tracker on your own sequences, or train from scratch using the ILSVRC15 curation scripts. It is MATLAB and MatConvNet based, so it fits people who want to reproduce the paper's experiments or extend the architecture in that stack. The authors themselves point newcomers to the newer CFNet repository, which is cleaner and gives slightly better results, so treat this as the historical baseline rather than the maintained code. Even so, it is the natural place to start if you want to understand the original SiamFC design or compare later trackers against it.
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)