search

karolzak / conv3d-video-action-recognition

My experimentation around action recognition in videos. Contains Keras implementation for C3D network based on original paper "Learning Spatiotemporal Features with 3D Convolutional Networks", Tran et al. and it includes video processing pipelines coded using mPyPl package. Model is being benchmarked on popular UCF101 dataset and achieves results similar to those reported by authors
MIT License
53 stars 10 forks source link

About feature extraction #7

Closed h1manshus1ngh closed 2 years ago

h1manshus1ngh commented 2 years ago

How do you had extracted the features

karolzak commented 2 years ago

I used C3D model to extract feature vectors.
You can find the full pipeline used in this notebook: https://github.com/karolzak/conv3d-video-action-recognition/blob/master/notebooks/kz-ucf101-action-recognition-with-c3d-svm.ipynb