Skip to content

Commit

Permalink
update
Browse files Browse the repository at this point in the history
  • Loading branch information
Murphy committed Mar 4, 2024
1 parent 799e290 commit bebfa59
Show file tree
Hide file tree
Showing 27 changed files with 3,395 additions and 1 deletion.
6 changes: 5 additions & 1 deletion README.md
View file
Original file line number Diff line number Diff line change
@@ -1 +1,5 @@
# MovieLLM
# MovieLLM

This is the repository that contains source code for the [MovieLLM website](https://deaddawn.github.io/MovieLLM/).


307 changes: 307 additions & 0 deletions index.html
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,307 @@
<!DOCTYPE html>
<html>

<head>
<meta charset="utf-8">
<meta name="description" content="Enhancing Long Video Understanding with AI-Generated Movies">
<meta name="keywords" content="LLM, Video Understanding, AI-Generated">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>MovieLLM: Enhancing Long Video Understanding with AI-Generated Movies</title>


<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">

<link rel="stylesheet" href="./static/css/bulma.min.css">
<link rel="stylesheet" href="./static/css/bulma-carousel.min.css">
<link rel="stylesheet" href="./static/css/bulma-slider.min.css">
<link rel="stylesheet" href="./static/css/fontawesome.all.min.css">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
<link rel="stylesheet" href="./static/css/index.css">
<link rel="icon" href="./static/images/icon.png">

<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<script defer src="./static/js/fontawesome.all.min.js"></script>
<script src="./static/js/bulma-carousel.min.js"></script>
<script src="./static/js/bulma-slider.min.js"></script>
<script src="./static/js/index.js"></script>
</head>

<body>



<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title">MovieLLM: Enhancing Long Video Understanding with AI-Generated
Movies</h1>
<div class="is-size-5 publication-authors">
<span class="author-block">
<a href="https://github.com/Deaddawn">Zhende Song</a><sup>1</sup>,</span>
<span class="author-block">
<a href="https://github.com/doctorlightt">Chenchen Wang</a><sup>1</sup>,</span>
<span class="author-block">
<a href="https://github.com/sjmFDU">Jiamu Sheng</a><sup>1</sup>,
</span>
<span class="author-block">
<a href="https://icoz69.github.io/">Chi Zhang</a><sup>2</sup>,
</span>
<span class="author-block">
<a
href="https://scholar.google.com/citations?hl=en&user=BJdigYsAAAAJ&view_op=list_works&sortby=pubdate">Gang
Yu</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?hl=zh-CN&user=gsLd2ccAAAAJ">Jiayuan Fan</a><sup>1</sup>,
</span>
<span class="author-block">
<a href="https://eetchen.github.io/">Tao Chen</a><sup>1</sup>
</span>
</div>

<div class="is-size-5 publication-authors">
<span class="author-block"><sup>1</sup>Fudan University,</span>
<span class="author-block"><sup>2</sup>Tencent PCG</span>
</div>

<div class="column has-text-centered">
<div class="publication-links">
<!-- PDF Link. -->
<span class="link-block">
<a href="" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Paper</span>
</a>
</span>
<span class="link-block">
<a href="" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="ai ai-arxiv"></i>
</span>
<span>arXiv</span>
</a>
</span>
<!-- Video Link. -->

<!-- Code Link. -->
<span class="link-block">
<a href="https://github.com/Deaddawn/MovieLLM-code"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Code</span>
</a>
</span>
<!-- Dataset Link. -->
<span class="link-block">
<a href="https://github.com/google/nerfies/releases/tag/0.1"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="far fa-images"></i>
</span>
<span>Data(coming soon)</span>
</a>
</div>

</div>
</div>
</div>
</div>
</div>
</section>





<section class="hero teaser">

<div class="container is-max-desktop">
<div class="hero-body">
<h2 class="title is-3 has-text-centered">
<span class="dnerf"><img src="./static/images/icon.png" alt="Icon"
style="width: 48px; height: 48px; vertical-align: middle;">Consistent Key Frames From MovieLLM</span>
</h2>
<video id="teaser" autoplay muted loop playsinline height="100%">
<source src="./static/videos/cat0.mp4" type="video/mp4">
</video>
<video id="teaser" autoplay muted loop playsinline height="100%">
<source src="./static/videos/cat4.mp4" type="video/mp4">
</video>
<video id="teaser" autoplay muted loop playsinline height="100%">
<source src="./static/videos/cat7.mp4" type="video/mp4">
</video>
<video id="teaser" autoplay muted loop playsinline height="100%">
<source src="./static/videos/cat14.mp4" type="video/mp4">
</video>
<video id="teaser" autoplay muted loop playsinline height="100%">
<source src="./static/videos/cat93.mp4" type="video/mp4">
</video>
<video id="teaser" autoplay muted loop playsinline height="100%">
<source src="./static/videos/cat106.mp4" type="video/mp4">
</video>
<h2 class="subtitle has-text-centered">
<span class="dnerf">MovieLLM</span> generate consistent key frames with immobilized style on various scenes
</h2>
</div>
</div>
</section>

<section class="section">
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="column ">
<div class="publication-video">
<video id="teaser" controls loop playsinline height="100%">
<source src="./static/videos/MovieLLM.mp4" type="video/mp4">
</video>
</div>
</div>
</div>
</section>



<section class="section">
<div class="container is-max-desktop">
<!-- Teaser. -->
<div class="columns is-centered has-text-centered">
<div class="column">
<div class="content has-text-justified">
<div class="center-image">
<figure>
<img src="./static/images/fig1.png" class="interpolation-image"
alt="Interpolate start reference image." />
<figcaption>
<strong>Examples of generated long video instruction data.</strong> We use GPT-4 and guided
text-to-image generation models
to generate consistent key frames of move-level video with reasonable lines and corresponding
question-answer pairs.
These data are used to train multimodal large language models on video understanding.
</figcaption>
</figure>
</div>
</div>
</div>
</div>
</div>
</section>

<section class="section">
<div class="container is-max-desktop">
<!-- Abstract. -->
<div class="columns is-centered has-text-centered">
<div class="column">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
The development of multimodal models has marked a significant step forward in how machines understand
videos. These models have shown promise in analyzing short video clips. However, when it comes to longer
formats like movies, they often fall short. The main hurdles are the lack of high-quality, diverse video
data and the intensive work required to collect or annotate such data. In the face of these challenges, we
propose MovieLLM, a novel framework designed to create synthetic, high-quality data for long videos. This
framework leverages the power of GPT-4 and text-to-image models to generate detailed scripts and
corresponding visuals. Our approach stands out for its flexibility and scalability, making it a superior
alternative to traditional data collection methods.
Our extensive experiments validate that the data produced by MovieLLM significantly improves the
performance of multimodal models in understanding complex video narratives, overcoming the limitations of
existing datasets regarding scarcity and bias.
</p>
</div>
</div>
</div>
<!-- framework. -->
<div class="columns is-centered has-text-centered">
<div class="column ">
<h2 class="title is-3">Pipeline</h2>
<div class="content has-text-justified">
<img src="./static/images/PIPELINE.png" class="framework" />
<p>The overall pipeline of our MovieLLM. (a) Rather than limiting plot generation to conventional data
sources such as the web or existing datasets, we harness the power of GPT-4 to produce synthesized data.
By providing specific elements such as themes, overview, and styles, we guide GPT-4 to produce movie-level
key frame descriptions tailored to the latter generation process.
(b) By adeptly employing textual inversion, we immobilize the style descriptions generated from the script
onto the latent space of the diffusion model. This approach guides the model to generate scenes in a fixed
style while maintaining diversity under a unified aesthetic.
(c) By integrating the powerful generative capabilities of GPT-4 with the developed style-guided diffusion
model, we produce style-consistent key frames and corresponding QA pairs, resulting in a comprehensive
instruction tuning corpus, combining the visual data with QA pairs.</p>
</div>
</div>
</div>
<!-- Paper video. -->
<!-- <div class="columns is-centered has-text-centered">
<div class="column ">
<h2 class="title is-3">Video</h2>
<div class="publication-video">
<video id="teaser" controls loop playsinline height="100%">
<source src="./static/videos/MovieLLM.mp4" type="video/mp4">
</video>
</div>
</div>
</div> -->
<div class="columns is-centered has-text-centered">
<div class="column ">
<h2 class="title is-3">More Results</h2>
<div class="content has-text-justified">
<img src="./static/images/appendix6-1.png" class="appendix" />
<img src="./static/images/appendix1-1.png" class="appendix" />
<img src="./static/images/appendix2-1.png" class="appendix" />
</div>
</div>
</div>
<!--/ Paper video. -->

</section>





<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title">BibTeX</h2>
<pre><code>@article</code></pre>
</div>
</section>


<footer class="footer">
<div class="container">
<div class="content has-text-centered">
<a class="icon-link" href="">
<i class="fas fa-file-pdf"></i>
</a>
<a class="icon-link" href="https://github.com/Deaddawn/MovieLLM-code" class="external-link" disabled>
<i class="fab fa-github"></i>
</a>
</div>
<div class="columns is-centered">
<div class="column is-8">
<div class="content">
<p>
This website is licensed under a <a rel="license"
href="http://creativecommons.org/licenses/by-sa/4.0/">Creative
Commons Attribution-ShareAlike 4.0 International License</a>.
</p>
<p>
This means you are free to borrow the <a href="https://github.com/nerfies/nerfies.github.io">source
code</a> of this website,
we just ask that you link back to this page in the footer.
Please remember to remove the analytics code included in the header of the website which
you do not want on your website.
</p>
</div>
</div>
</div>
</div>
</footer>

</body>

</html>
1 change: 1 addition & 0 deletions static/css/bulma-carousel.min.css
View file

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading

0 comments on commit bebfa59

Please sign in to comment.