Best algorithm for real-time instance segmentation in videos?

I want to do object detection in real-time (meaning localization and classification) on videos (25 FPS), but with the added constraint that my training data is labelled using binary masks, rather than bounding boxes. I think it might be worthwhile to also output contours rather than bounding boxes. Since I’m fairly new to the field of computer vision I’m figuring out what’s currently the best way to do this. I found that YOLO is more or less the go-to tool for real-time object detection, but their tutorials don’t show anything regarding segmentation. Google results on this topic are also sparse and lack any hands-on examples.

Maybe YOLO is simply not the right tool for this job, hence my question.