http://learnandshare645.blogspot.hk/2016/06/3d-cnn-in-keras-action-recognition.html

🔈 Deep Learning & 3D Convolutional Neural Networks for Speaker Verification

A multi-object tracking component. Works in the conditions where identification and classical object trackers don't (e.g. shaky/unstable camera footage, occlusions, motion blur, covered faces, etc.…

apricot implements submodular selection for the purpose of selecting subsets of massive data sets to train machine learning models quickly.

Attention Branch Network (CIFAR100, ImageNet models)

Live input Web Audio effects

A paper list of awesome Image Tagging

Sample code and CloudFormation scripts for automating Video on Demand workflows on AWS

This Pytorch repo uses BiConvLSTM in a Spatiotemporal Encoder to detect violence in Videos. Three benchmark datasets namely Hockey, Movies and Violent Flows were used in this work.

Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Caffe Framework for Triplet Network Ranking

Use CNNs to generate images

CNNImageRetrieval: Training and evaluating CNNs for Image Retrieval

Non-Uniform Subset Selection for Active Learning in Structured Data

Deep neural network framework (C++/OpenCV).

PyTorch implementation of Attentive Recurrent Comparators

Deep Speaker: an End-to-End Neural Speaker Embedding System https://arxiv.org/pdf/1705.02304.pdf

deep face recognition algorithm

Practise of DeepID for Face Classification

Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to …

Deep learning based one class classification code targeting one class image classification. Tests carried out on Abnormal image detection, Novel image detection and Active Authentication reported s…

Simple Online Realtime Tracking with a Deep Association Metric

Capture a sequence of images with different focus settings, use these images to find the depth for each pixel in the scene, and then use this depth map to estimate an all-in focus image

Deep Learning Studio is a GUI based deep learning platform for designing, training and evaluating artificial neural networks without programming skills.

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)

The final project of ECBM-4040-Neural Networks and Deep Learning in Columbia University. Learning-based EM image segmentation (based on PyraMid-LSTM)

Diagrams for draw.io

Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution

Implementation about EDRAM by tensorflow