[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

MAL for cvpr765

DIVA IO Package: IO interfaces for the DIVA project.

MOT tracking using deepsort and yolov3 with pytorch

VMZ: Model Zoo for Video Modeling

A repositsory of common methods, datasets, and tasks for video research

3D ResNets for Action Recognition (CVPR 2018)

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Pytorch implementation of FlowNet by Dosovitskiy et al.

The pytorch implementation of the Min-Entropy Latent Model for Weakly Supervised Object Detection

Caffe2 is a lightweight, modular, and scalable deep learning framework.

Convolutional neural network model for video classification trained on the Kinetics dataset.

Non-local Neural Networks for Video Classification

PyTorch Implementations for DeeplabV3 and PSPNet

Deep Feature Flow for Video Recognition

Video classification tools using 3D ResNet

non local net based on caffe2

Spatiotemporal-separable 3D convolution network.

Jekyll 的中文翻译网站

一个基于 Editor.md 构建的为知笔记 Markdown 插件

Professor X Toolkit (previously known as the Princeton Vision and Robotics Toolkit)

source code for Finding Action Tubes, CVPR 2015

Machine Learning、Deep Learning、PostgreSQL、Distributed System、Node.Js、Golang

code RIP

code for Holistically-Nested Edge Detection

Caffe: a fast open framework for deep learning.

Piotr's Image & Video Matlab Toolbox