videodnn's repositories
X-Temporal
A general video understanding codebase from SenseTime X-Lab
bLVNet-TAM
The official Codes for NeurIPS 2019 paper. Quanfu Fan, Ricarhd Chen, Hilde Kuehne, Marco Pistoia, David Cox, "More Is Less: Learning Efficient Video Representations by Temporal Aggregation Modules"
google-research
Google AI Research
ffmpeg-python
Python bindings for FFmpeg - with complex filtering support
arctic-capgen-vid
automatic video description generation with GPU training
MMGCN
MMGCN: Multi-modal Graph Convolution Network forPersonalized Recommendation of Micro-video
Realtime-Action-Recognition
Multi-person real-time recognition (classification) of 9 actions based on human skeleton from OpenPose and a 0.5-second window.
STVEN_rPPGNet
Main code of "Remote Heart Rate Measurement from Highly Compressed Facial Videos: an End-to-end Deep Learning Solution with Video Enhancement"
cpnet
Learning Video Representations from Correspondence Proposals (CVPR 2019 Oral)
SlowFast
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
moments_models
The pretrained models trained on Moments in Time Dataset
deephar
Deep human action recognition and pose estimation
awesome-action-recognition
A curated list of action recognition and related area resources
3D-ResNets-PyTorch
3D ResNets for Action Recognition (CVPR 2018)
two-stream-action-recognition
Using two stream architecture to implement a classic action recognition method on UCF101 dataset
HACS-dataset
HACS: Human Action Clips and Segments Dataset
gpu_flow
GPU based optical flow extraction in OpenCV
kinetics-i3d
Convolutional neural network model for video classification trained on the Kinetics dataset.
VideoPose3D
Efficient 3D human pose estimation in video using 2D keypoint trajectories
two-stream-action-recognition-keras
Two-stream CNNs for video action recognition implemented in Keras
VideoClassification
Video Action Recognition using Youtube Action Classification Dataset ( http://www.cs.ucf.edu/~liujg/YouTube_Action_dataset.html​ )
C3D-tensorflow
C3D is a modified version of BVLC tensorflow to support 3D ConvNets.
temporal-segment-networks
Code & Models for Temporal Segment Networks (TSN) in ECCV 2016
local-and-global-diffusion-networks
Learning Spatio-Temporal Representation with Local and Global Diffusion
five-video-classification-methods
Code that accompanies my blog post outlining five video classification methods in Keras and TensorFlow
video-long-term-feature-banks
Long-Term Feature Banks for Detailed Video Understanding
Online-Realtime-Action-Recognition-based-on-OpenPose
A skeleton-based real-time online action recognition project, classifying and recognizing base on framewise joints, which can be used for safety surveilence.
ActionRecognition
Explore Action Recognition