amna-ai's starred repositories
WLASL-Recognition-and-Translation
World Level American Sign Language Recognition and Translation to Spoken Language
keras-data-generator
Template for data generator in Keras
Deep-Neural-Networks-for-Video-Classification
Deep Neural Networks for Video Classification
Video-Classification
Classify chunks of videos into respective classes.
C3D-tensorflow
Action recognition with C3D network implemented in tensorflow
deepfakes_video_classification
Deepfakes Video classification via CNN, LSTM, C3D and triplets [IWBF'20]
sign-language
Sign Language Recognition for Deaf People
Optical-Flow-Guided-Feature
Implementation Code of the paper Optical Flow Guided Feature, CVPR 2018
Tutorial-about-3D-convolutional-network
Tutorial about 3D convolutional network
Video-Classification-CNN-and-LSTM-
To classify video into various classes using keras library with tensorflow as back-end.
Speak-Budy
This repostiroy holds the android portion of the speak-buddy an app which helps non signers to commmunicate with signers.
Action-Recognition
recognize actions from videos using machine learning classifier(s) and suitable features. You will use UCF sports action data set here http://crcv.ucf.edu/data/ucf_sports_actions.zip. UCF Sports dataset consists of a set of actions collected from various sports which are typically featured on broadcast television channels such as the BBC and ESPN. The video sequences were obtained from a wide range of stock footage websites including BBC Motion gallery and GettyImages. The dataset includes a total of 150 sequences with the resolution of 720 x 480. The collection represents a natural pool of actions featured in a wide range of scenes and viewpoints. By releasing the data set we hope to encourage further research into this class of action recognition in unconstrained environments. Since its introduction, the dataset has been used for numerous applications such as: action recognition, action localization, and saliency detection. The dataset includes the following 10 actions. The figure above shows the a sample frame of all ten actions, along with their bounding box annotations of the humans shown in yellow.
Real-Time-Action-Recognition
Real-time pose estimation and action recognition
two-stream-action-recognition-keras
Two-stream CNNs for video action recognition implemented in Keras