API of DouYin for Humans used to Crawl Popular Videos and Musics

3D ResNets for Action Recognition (CVPR 2018)

Audio To Body Dynamics, CVPR 2018

Video-based Person ReID Method Implementations on MARS

This is a pix2pix demo that learns from pose and translates this into a human. A webcam-enabled application is also provided that translates your pose to the trained pose. Everybody dance now !

The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"

Tensorflow implementation of the ICML 2017 paper: Learning to Generate Long-term Future via Hierarchical Prediction

Human-detection-and-Tracking

Implementation of Everybody Dance Now by pytorch

pytorch version of pseudo-3d-residual-networks(P-3D), pretrained model is supported

Sequence modeling benchmarks and temporal convolutional networks

An (re-)implementation of DeepLab v2 (ResNet-101) in TensorFlow for semantic image segmentation on the PASCAL VOC 2012 dataset.

attention-based LSTM/Dense implemented by Keras

Now I'm trying to calculate the 3d pose from the 2d keypoints of cpm (convolutional pose machine)

Implementation of Sequence Generative Adversarial Nets with Policy Gradient

Dynamic time warping for audio matching and alignment

Transfer Learning Shootout for PyTorch's model zoo (torchvision)

Dynamic Image Networks for Action Recognition

A tutorial-style implementation of CapsNet in PyTorch

Classify UCF101 videos using one frame at a time with a CNN(InceptionV3)

Program for audio-to-audio and audio-to-midi alignment