Action Recognition in Videos using Stacked Optical Flow and HOGHOF features.
-
Updated
May 8, 2017 - Python
Action Recognition in Videos using Stacked Optical Flow and HOGHOF features.
Optical speech recognition system utilizing LRC neural networks
tensorflow live video object detection
State of the art object detection in real-time using YOLOV3 algorithm. Augmented with a process that allows easy training of the classifier as a plug & play solution . Provides alert if an item in an alert list is detected.
Exploration of different solutions to action recognition in video, using neural networks implemented in PyTorch.
In this time of Covid19, this project helps in detecting face masks with a score of 96% using deep learning
2019 term project for Machine Learning Practical course at the University of Edinburgh
[ECCV 2018] Temporal Relational Reasoning in Videos
[CVPR 2019] SlowFast Networks for Video Recognition
Educational project for video and speech recognition
Video Recognition using Mixed Convolutional Tube (MiCT) on PyTorch with a ResNet backbone
Official Pytorch implementation of "OmniNet: A unified architecture for multi-modal multi-task learning" | Authors: Subhojeet Pramanik, Priyanka Agrawal, Aman Hussain
[CVPR 2020] X3D: Expanding Architectures for Efficient Video Recognition
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
[CVPR 2018] Non-local Neural Networks
CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning
3D ResNets for Action Recognition (CVPR 2018)
[ECCV 2016] Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
An implementation of the X3D video recognition architecture in TensorFlow/Keras
PyTorch Implementation on Paper [CVPR2021]Distilling Audio-Visual Knowledge by Compositional Contrastive Learning
Add a description, image, and links to the video-recognition topic page so that developers can more easily learn about it.
To associate your repository with the video-recognition topic, visit your repo's landing page and select "manage topics."