search

dmlc / gluon-cv

Gluon CV Toolkit
http://gluon-cv.mxnet.io
Apache License 2.0
5.79k stars 1.21k forks source link

How to visualize action recognition? #1744

Closed 4lparslan closed 2 years ago

4lparslan commented 2 years ago

I get predicted class as an string but i want to see it with bounding box on video. Any idea?

bryanyzhu commented 2 years ago

For now, we only support action classification, not action detection. So the output will just be a string (class label). If you need bounding box on video, an (spatiotemporal) action detection model is the way to go.