sudonto's repositories
20bn-something-something-label-hierarchies
Metadata for the Something-Something dataset
3D-ResNets-PyTorch
3D ResNets for Action Recognition (CVPR 2018)
ActionRecognition
Explore Action Recognition
cnn_lstm
Action recognition by CNN and LSTM
convolution-visualizer
Convolution visualizations
five-video-classification-methods
Code that accompanies my blog post outlining five video classification methods in Keras and TensorFlow
Keras-Classification-Models
Collection of Keras models used for classification
keras-video-classifier
Keras implementation of video classifier
mixture-of-experts
Mixture of experts layers for Keras
pre-trained-keras-example
Example on how to use pre trained networks on new classification problems.
predictive-coding
Research of a deep predictive coding model for unsupervised representation learning from video and audio data.
tea-action-recognition
The Pytorch code of the TEA module (Temporal Excitation and Aggregation for Action Recognition)
temporal-shift-module
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
two-stream-action-recognition-keras
Two-stream cnn models for action recognition on the UCF-101 dataset
Video-Classification-2-Stream-CNN
Video Classification using 2 stream CNN
Video-Classification-CNN-and-LSTM-
To classify video into various classes using keras library with tensorflow as back-end.
video2tfrecord
Easily convert RGB video data (e.g. .avi) to the TensorFlow tfrecords file format for training e.g. a NN in TensorFlow. This implementation allows to limit the number of frames per video to be stored in the tfrecords.