3D Convolutional Neural Networks with Optical Flow Regularization for Video Recognition

Name: kjchavez/cnn-project
Brand: kjchavez/cnn-project
SKU: project/kjchavez/cnn-project
Rating: 4.43 (30 reviews)

Proposed idea

Infuse the 3D CNN model with the assumptions used in optical flow computaitons in a soft way through a special regularization on the filters.

We test the merit of this idea by training ConvNets from scratch on the UCF101 Human Action Recognition data set using Theano. See the report.

Project Name	Stars	Most Recent Commit	Total Releases	Latest Release	Open Issues	License	Language
Sparseconvnet	1,781	2 months ago	2	July 10, 2019	50	other	C++
Submanifold sparse convolutional networks
Meshcnn	1,211	a year ago			76	mit	Python
Convolutional Neural Network for 3D meshes in PyTorch
Medicaldetectiontoolkit	1,167	4 months ago			43	apache-2.0	Python
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
Learning Deep Learning	800	5 days ago			1		Jupyter Notebook
Paper reading notes on Deep Learning and Machine Learning
3d Convolutional Speaker Recognition	634	3 years ago			7	apache-2.0	Python
:speaker: Deep Learning & 3D Convolutional Neural Networks for Speaker Verification
Stereo Rcnn	517	3 years ago			29	mit	Python
Code for 'Stereo R-CNN based 3D Object Detection for Autonomous Driving' (CVPR 2019)
Video Classification	498	2 years ago			26		Jupyter Notebook
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
Lifting From The Deep Release	391	3 years ago				gpl-3.0	Python
Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"
Awesome Local Global Descriptor	386	2 years ago
My personal note about local and global descriptor
Pointconv	351	3 years ago			17	other	Python