Giter Club home page Giter Club logo

videodg's Introduction

VideoDG: Generalizing Temporal Relations in Videos to Novel Domains

A PyTorch implementation of APN, a differentiable framework named adversarial pyramid network is a new deep architecture thatimproves the generalizability of video features by capturing the local-relation, global-relation, and cross-relation features progressively. Based on these pyramid features, we also propose a new adversarial data augmentation approach that can enhance the diversity and qualityof the augmented data to bridge different video domains.

This paper is accepted by TPAMI2021.

Get Started

  1. Install Python 3.7, PyTorch 1.3, and OpenCV 3.4.

  2. Train the model. You can use the following bash script to train the model.

sh train.sh

Contact

You may send email to [email protected], [email protected] or [email protected].

videodg's People

Contributors

yaozy15 avatar

Stargazers

avatar avatar avatar avatar Mingyuan Luo avatar cyberPanda avatar avatar avatar Kaiyang avatar avatar avatar Captain_David avatar Rui Shao avatar Bingchen Zhao avatar Xu Chen avatar avatar ZhangRuipeng avatar sofia avatar avatar Yunbo Wang avatar

Watchers

James Cloos avatar Bo Fu avatar Huang Chao avatar avatar

Forkers

simplexsigil wzml khm159

videodg's Issues

SyntaxError

Hi,
I already installed the requirements, when I run the command "sh train.sh", it raise the syntax error :

File "main_val.py", line 48
target = target.cuda(async=True)
^
SyntaxError: invalid syntax

Could you help me ?

what criteria did you make a video list?

Based on what criteria did you make a video list?
I confirmed that in this repo, the video sample name shown like this : video001, video002, ...
So I don't know the actual sample name....
Could you explain more information about this issue?

Could you provide the code for preprocessing?

Hi,
After downloading the UCF101 and HMDB51 benchmark, I notice that the raw data isn't consist with the files requiring in './data_list/*.txt', could you please show me how to process the raw data? Thank you very much!

How can we run HMDB??

In the data list folder the HMDB train and val txt file the name of the video clips are organize in Video_0000 style, how can we preprocess our txt file to make the same?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.