You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Lip reading using TensorFlow, OpenCV, and Keras involves training a deep learning model to recognize spoken words by analyzing lip movements from video frames. The process starts with OpenCV for capturing and preprocessing video frames, focusing on the speaker’s lips. These frames are then fed into a neural network built using Keras and TensorFlow.
Context Understanding from Videos analyzes video content by extracting frames and audio, then detecting objects, faces, emotions, and actions. It uses Python with OpenCV, MoviePy, and YOLO. Future plans include embedding models for improved context analysis.
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 result…
This repository contains my personal code for the paper Learning Spatiotemporal Features with 3D Convolutional Networks by Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, Manohar Paluri.
Real-Time Visual Speech and Emotion Recognition (ViSpEr) an end-to-end neural network for the low-resource visual speech and facial emotion recognition task, using 3D CNNs and LSTMs
My team partner and I did this project where we developed a feature in a company’s smart TV that can recognise five different predetermined gestures performed by the user, which will help users control the TV without using a remote.
Develop a cool feature in the smart-TV that can recognise five different gestures performed by the user which will help users control the TV without using a remote.
Imagine you are working as a data scientist at a home electronics company which manufactures state of the art smart televisions. You want to develop a cool feature in the smart-TV that can recognize five different gestures performed by the user which will help users control the TV without using a remote.