GithubHelp home page GithubHelp logo

bityangke / deep-action-proposals Goto Github PK

View Code? Open in Web Editor NEW

This project forked from escorciav/deep-action-proposals

0.0 1.0 0.0 539 KB

Action Proposals generated by deep models

License: MIT License

Shell 4.44% Python 95.56%

deep-action-proposals's Introduction

Deep Action Proposals (DAPs) for Videos

Temporal Action Proposals for long untrimmed videos.

DAPs architecture allows to retrieve segments from long videos where it is likely to find actions with high recall very quickly.

Citation

If you find any piece of code valuable for your research please cite this work:

@Inbook{Escorcia2016,
author="Escorcia, Victor and Caba Heilbron, Fabian and Niebles, Juan Carlos and Ghanem, Bernard",
editor="Leibe, Bastian and Matas, Jiri and Sebe, Nicu and Welling, Max",
title="DAPs: Deep Action Proposals for Action Understanding",
bookTitle="Computer Vision -- ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III",
year="2016",
publisher="Springer International Publishing",
address="Cham",
pages="768--784",
isbn="978-3-319-46487-9",
doi="10.1007/978-3-319-46487-9_47",
url="http://dx.doi.org/10.1007/978-3-319-46487-9_47"
}

If you like this project, give us a โญ in the github banner ๐Ÿ˜‰.

What is this?

This repo complements our repo with the training pipeline used for our ECCV-2016 work.

I want to use it, Where can I start?

You can find a complete example of our project here. It covers data pre-processing, training and inference.

After training, you can plug-in a model trained here in our clean and simplified inference project.

Installation and Usage

Install

We use conda for deployment. You can create an evironment for this project with the environment-proto-linux-x64.yml.

Dependencies: gcc, CUDA, conda.

Are you a bash user? Take a look at our install.sh script.

Usage

Once all the dependencies are installed, you are ready to go.

  • Most of the scripts and tools should be executed from the project folder.

  • You can add the project dir to your PYTHONPATH and use our modules as standard python package.

Are you bash & modules-env user? Take a look at our activate.sh script.

What is not here?

This repo does not extract the C3D feature vector representation of your videos. However, we try to alleviate your pain installing and assembling all the cumulus of data such that you do not start from scratch.

  • Take a look of this branch for help to install C3D.

  • Do you want to extract C3D from frames? Take a look at this tool to simplify your life extracting frames from videos.

  • Extract C3D for frames without modifying prototxt manually. Take a look at this

deep-action-proposals's People

Contributors

cabaf avatar escorciav avatar

Watchers

 avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.