FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos
The following repository contains pretrained models for FusionSeg video object segementation method.
Please visit our project page for the paper and visual results.
If you use this in your research, please cite the following papers:
@article{pixelobjectness,
Author = {Jain, Suyog and Xiong, Bo and Grauman, Kristen},
Journal = {arXiv preprint arXiv:1701.05349},
Title = {Pixel Objectness},
Year = {2017}
}@article{fusionseg,
Author = {Jain, Suyog and Xiong, Bo and Grauman, Kristen},
Journal = {CVPR},
Title = {FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos},
Year = {2017}
}These models are freely available for research and academic purposes. However it's patent pending, so please contact us for any commercial use.
This repository contains both matlab and python implementations for fusionseg using caffe. It is highly recommended to use the python implementation. It is self contained with models for appearance, motion and joint stream.
Please refer to the README files inside matlab and python folders for more details.