Coder Social home page Coder Social logo

neumatch's Introduction

A Neural Multi-sequence Alignment TeCHnique (NeuMATCH)


YouTube Movie Summaries (YMS) Dataset Release

We are making the dataset YMS (YouTube Movie Summaries) with the annotations and the corresponding video URLs available for research purposes. If you would like to use the dataset for any other purposes please contact the authors.

Introduction

This dataset contains 94 movie summary videos from various YouTube channels. You can find the explanation of each file below:

YMS/movie_list.txt - the list of video titles with the corresponding numbering

YMS/url_list.txt - the list of video URLs with the corresponding numbering

YMS/annotations_sentences.txt - annotation of the narrator sentences

YMS/annotations_phrases.txt - annotation of the narrator phrases (if available)

YMS/clip_segmentation.txt - list of over-segmented clips that we used in our experiments

In the annotation files, the video parts with "UNMATCHED" annotation represent the clips that do not have any corresponding narrator phrase/sentence. If a video part has an annotation sentence/phrase which starts with "UNMATCHED:", that clip and the phrase/sentence do not have correspondances in the other medium.

Citing NeuMATCH

NeuMATCH was initially described in arXiv and was subsequently published in CVPR 2018.

If you find NeuMATCH useful in your research, or if you use the YMS dataset, please consider citing:

@inproceedings{Dogan18neumatch,
    author    = {Pelin Dogan and Boyang Li and Leonid Sigal and Markus Gross},
    title     = {A Neural Multi-sequence Alignment TeCHnique (NeuMATCH)},
    booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year      = {2018}
}

Contact

You can reach us via [email protected]

If you have any questions related to the dataset please let us know.

neumatch's People

Contributors

pelindogan avatar

Watchers

 avatar  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.