index.html

<!DOCTYPE html>
<html>

  <head>
    <meta charset='utf-8'>
    <meta http-equiv="X-UA-Compatible" content="chrome=1">
    <meta name="description" content="MVC : ">

    <link rel="stylesheet" type="text/css" media="screen" href="stylesheets/stylesheet.css">

    <title>MVC: A Dataset for View-Invariant Clothing Retrieval and Attribute Prediction</title>
  </head>

  <body>

    <!-- HEADER -->
    <div id="header_wrap" class="outer">
        <header class="inner">


          <h1 id="project_title">MVC: A Dataset for View-Invariant Clothing Retrieval and Attribute Prediction</h1>
          <h2 id="project_tagline"></h2>
            <h4>
            <a >Kuan-Hsien Liu,</a>, 
            <a >Ting-Yen Chen,</a>, 
            <a >Chu-Song Chen.</a>
            </h4>


        </header>
    </div>

    <!-- MAIN CONTENT -->
    <div id="main_content_wrap" class="outer">
      <section id="main_content" class="inner">
    <div class="row">
        <div class="col-md-5">
            <img src="MultiviewClothingImage.jpg" class="images"/>
        </div>
    </div>

        <h3>
<a id="welcome-to-mvc-pages" class="anchor" href="#welcome-to-mvc-pages" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Welcome to MVC Dataset.</h3>

<p>This webpage is the easiest way to get information on the MVC dataset for all of your research and projects.</p>

<h3>
<a id="abstract" class="anchor" href="#abstract" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Abstract</h3>

<p>Clothing retrieval and clothing style recognition are important and practical problems. 
They have drawn a lot of attention in recent years. 
However, the clothing photos collected in existing datasets are mostly of front- or near-front view. 
There are no datasets designed to study the influences of different viewing angles on clothing retrieval performance. 
To address view-invariant clothing retrieval problem properly, we construct a challenge clothing dataset, called Multi-View Clothing dataset. 
This dataset not only has four different views for each clothing item, but also provides 264 attributes for describing clothing appearance.
We adopt a state-of-the-art deep learning method to present baseline results for the attribute prediction and clothing retrieval performance. 
We also evaluate the method on a more difficult setting, cross-view exact clothing item retrieval.
This dataset can be used for further studies towards view-invariant clothing retrieval.</p>

<h3>
<a id="publication" class="anchor" href="#publication" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Publication</h3>

<p>Kuan-Hsien Liu, Ting-Yen Chen, and Chu-Song Chen. MVC: A Dataset for View-Invariant Clothing Retrieval and Attribute Prediction, ACM ICMR 2016.
[<a href="https://github.com/MVC-Datasets/MVC/blob/gh-pages/liu16icmr.pdf">Pdf</a>] </p>

<h3>
<a id="dataset" class="anchor" href="#dataset" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Dataset</h3>

<p>Please notice that this dataset is made available for academic research purpose only. 
All the images are collected from the Internet, and the copyright belongs to the original owners.</p>
        
<p>Here, we only provide 161,260 annotated images (1920 x 2240 resolutions) with 264 attribute labels (where the total images here are different to the paper).</p>

<h5>Matlab version</h5>
        
<ul>
            <li>The dataset images can be downloaded through their orignal links, which are provided in the mat file. [<a href="https://github.com/MVC-Datasets/MVC/blob/gh-pages/image_links.mat">right click to save the image_links.mat file</a>]</li>
            <li>The corresponding clothing attribute labels can be found in the excel file, which was formatted as a mat file here. [<a href="https://github.com/MVC-Datasets/MVC/blob/gh-pages/attribute_labels.mat">right click to save the attribute_labels.mat file</a>]</li>
            <li>The full information of mvc dataset can be found in [<a href="https://github.com/MVC-Datasets/MVC/blob/gh-pages/mvc_info.mat">right click to save the mvc_info.mat file</a>]
    
</ul>
        
<h5>JSON version</h5>
        
<ul> 
  <li>[<a href="https://drive.google.com/drive/folders/0B0oMjGuurWR4ZVZ1X19veUkxeU0?resourcekey=0-OGNzNY-DI4Tvg4ScQyaFBw&usp=sharing">json files</a>] for image_links, attribute_labels, mvc_info.</li>  
</ul>
            
<!--
<p>If you find the link of an image is not available for download, please notify <a href="mailto:timh20022002@iis.sinica.edu.tw">us</a>.
We would provide you with a link for downloading the unavailable image(s).</p>
-->
<h3>
<a id="authors" class="anchor" href="#authors" aria-hidden="true"><span aria-hidden="true" class="octicon octicon-link"></span></a>Contact Authors</h3>

<p>If you have any question regarding the MVC dataset, you can email us at <a href="mailto:timh20022002@gmail.com; khliu1212@gmail.com">here</a>.</p>

      </section>
    </div>

    <!-- FOOTER  -->
    <div id="footer_wrap" class="outer">
      <footer class="inner">
        <p class="copyright">MVC maintained by <a href="https://github.com/MVC-Datasets">MVC-Datasets</a></p>
        <p>Published with <a href="https://pages.github.com">GitHub Pages</a></p>
        <p> Updated: 2017/09/29
      </footer>
    </div>

    
  </body>
</html>