DavidHuang's repositories
awesome-deep-vision
A curated list of deep learning resources for computer vision
binary_net
experimental binary net implementation in chainer
caffe-googlenet-bn
re-implementation of googlenet batch normalization
caffe-rta
Modified caffe distribution to provide real-time augmentation
deep-landmark
Predict facial landmarks with Deep CNNs powered by Caffe.
Deep-Semi-NMF
Theano-based implementation of Deep Semi-NMF.
EnsembleSVM
A Library for Ensemble Learning Using Support Vector Machines
finegrained-cvpr2014
Nonparametric part-transfer for fine-grained recognition
impHumanDetectionAndTracking
A C/C++ implementation of pedestrian detection and tracking.
k-poselets
k-poselets CVPR2014 code
lpo
Implementation of the CVPR 2015 paper: Learning to propose objects
MDPM
Mid-level Deep Pattern Mining
part_constellation_models
Code for the ICCV 2015 paper "Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks."
PartDetectorDisovery
Code of the paper "Part Detector Discovery in Deep Convolutional Neural Networks" by Marcel Simon, Erik Rodner and Joachim Denzler
PartsBasedDetector
C++ implementation of Deva Ramanan's "Articulated Pose Estimation with Flexible Mixtures of Parts"
PedestrianDetector
C++ re-implementation of Piotr Dollar's pedestrian detection library for matlab
PyReID
Flexible and extensible Framework for Person Re-identification problem, built with Python and OpenCV.
rcnn
R-CNN: Regions with Convolutional Neural Network Features
SparseConvNet
Spatially-sparse convolutional networks. Allows processing of sparse 2, 3 and 4 dimensional data.Build CNNs on the square/cubic/hypercubic or triangular/tetrahedral/hyper-tetrahedral lattices.
Tracking-Pose-by-Particle-Filter
HPE in video by using Particle Filter
transformer_network
Spatial Transformer network
video-splitter
Simple Python script to split video into equal length chunks
voc-dpm
Object detection system using deformable part models (DPMs) and latent SVM (voc-release5). You may want to use the latest tarball on my website. The github code may include code changes that have not been tested as thoroughly and will not necessarily reproduce the results on the website.