MMAudio / docs /video_vgg.html
Rex Cheng
initial commit
dbac20f
<!DOCTYPE html>
<html lang="en">
<head>
<!-- Google tag (gtag.js) -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-0JKBJ3WRJZ"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'G-0JKBJ3WRJZ');
</script>
<link href='https://fonts.googleapis.com/css?family=Source+Sans+Pro' rel='stylesheet' type='text/css'>
<meta charset="UTF-8">
<title>MMAudio</title>
<meta name="viewport" content="width=device-width, initial-scale=1">
<!-- CSS only -->
<link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="stylesheet"
integrity="sha384-+0n0xVW2eSR5OomGNYDnhzAbDsOXxcvSN1TPprVMTNDbiYZCxYbOOl7+AMvyTG2x" crossorigin="anonymous">
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<link rel="stylesheet" href="style_videos.css">
</head>
<body>
<div id="vgg1">
<h2 style="text-align: center;">Comparisons with state-of-the-art methods in VGGSound</h2>
<p style="overflow: hidden;">
Example 1: Wolf howling.
<span style="float:right;"><a href="#index">Back to index</a></span>
</p>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Ground-truth</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/9J_V74gqMUA"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Ours</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/P6O8IpjErPc"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V2A-Mapper</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/w-5eyqepvTk"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">FoleyCrafter</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/VOLfoZlRkzo"></iframe>
</div>
</div>
</div>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Frieren</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/49owKyA5Pa8"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">VATT</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/QVtrFgbeGDM"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V-AURA</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/8r0uEfSNjvI"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Seeing and Hearing</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/bn-sLg2qulk"></iframe>
</div>
</div>
</div>
</div>
<div id="vgg2">
<h2 style="text-align: center;">Comparisons with state-of-the-art methods in VGGSound</h2>
<p style="overflow: hidden;">
Example 2: Striking a golf ball.
<span style="float:right;"><a href="#index">Back to index</a></span>
</p>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Ground-truth</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/1hwSu42kkho"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Ours</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/kZibDoDCNxI"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V2A-Mapper</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/jgKfLBLhh7Y"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">FoleyCrafter</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/Lfsx8mOPcJo"></iframe>
</div>
</div>
</div>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Frieren</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/tz-LpbB0MBc"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">VATT</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/RTDUHMi08n4"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V-AURA</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/N-3TDOsPnZQ"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Seeing and Hearing</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/QnsHnLn4gB0"></iframe>
</div>
</div>
</div>
</div>
<div id="vgg3">
<h2 style="text-align: center;">Comparisons with state-of-the-art methods in VGGSound</h2>
<p style="overflow: hidden;">
Example 3: Hitting a drum.
<span style="float:right;"><a href="#index">Back to index</a></span>
</p>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Ground-truth</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/0oeIwq77w0Q"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Ours</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/-UtPV9ohuIM"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V2A-Mapper</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/9yivkgN-zwc"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">FoleyCrafter</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/kkCsXPOlBvY"></iframe>
</div>
</div>
</div>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Frieren</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/MbNKsVsuvig"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">VATT</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/2yYviBjrpBw"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V-AURA</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/9yivkgN-zwc"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Seeing and Hearing</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/6dnyQt4Fuhs"></iframe>
</div>
</div>
</div>
</div>
</div>
<div id="vgg4">
<h2 style="text-align: center;">Comparisons with state-of-the-art methods in VGGSound</h2>
<p style="overflow: hidden;">
Example 4: Dog barking.
<span style="float:right;"><a href="#index">Back to index</a></span>
</p>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Ground-truth</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/ckaqvTyMYAw"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Ours</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/_aRndFZzZ-I"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V2A-Mapper</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/mNCISP3LBl0"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">FoleyCrafter</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/phZBQ3L7foE"></iframe>
</div>
</div>
</div>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Frieren</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/Sb5Mg1-ORao"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">VATT</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/eHmAGOmtDDg"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V-AURA</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/NEGa3krBrm0"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Seeing and Hearing</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/aO0EAXlwE7A"></iframe>
</div>
</div>
</div>
</div>
<div id="vgg5">
<h2 style="text-align: center;">Comparisons with state-of-the-art methods in VGGSound</h2>
<p style="overflow: hidden;">
Example 5: Playing a string instrument.
<span style="float:right;"><a href="#index">Back to index</a></span>
</p>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Ground-truth</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/KP1QhWauIOc"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Ours</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/ovaJhWSquYE"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V2A-Mapper</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/N723FS9lcy8"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">FoleyCrafter</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/t0N4ZAAXo58"></iframe>
</div>
</div>
</div>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Frieren</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/8YSRs03QNNA"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">VATT</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/vOpMz55J1kY"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V-AURA</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/9JHC75vr9h0"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Seeing and Hearing</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/9w0JckNzXmY"></iframe>
</div>
</div>
</div>
</div>
<div id="vgg6">
<h2 style="text-align: center;">Comparisons with state-of-the-art methods in VGGSound</h2>
<p style="overflow: hidden;">
Example 6: A group of people playing tambourines.
<span style="float:right;"><a href="#index">Back to index</a></span>
</p>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Ground-truth</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/mx6JLxzUkRc"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Ours</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/oLirHhP9Su8"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V2A-Mapper</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/HkLkHMqptv0"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">FoleyCrafter</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/rpHiiODjmNU"></iframe>
</div>
</div>
</div>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Frieren</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/1mVD3fJ0LpM"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">VATT</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/yjVFnJiEJlw"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">V-AURA</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/neVeMSWtRkU"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Seeing and Hearing</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/EUE7YwyVWz8"></iframe>
</div>
</div>
</div>
</div>
<div id="vgg_extra">
<h2 style="text-align: center;">Comparisons with state-of-the-art methods in VGGSound</h2>
<p style="overflow: hidden;">
<span style="float:right;"><a href="#index">Back to index</a></span>
</p>
<div class="row g-1">
<div class="col-sm-3">
<div class="video-header">Moving train</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/Ta6H45rBzJc"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Water splashing</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/hl6AtgHXpb4"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Skateboarding</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/n4sCNi_9buI"></iframe>
</div>
</div>
<div class="col-sm-3">
<div class="video-header">Synchronized clapping</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/oxexfpLn7FE"></iframe>
</div>
</div>
</div>
<br><br>
<div id="extra-failure">
<h2 style="text-align: center;">Failure cases</h2>
<p style="overflow: hidden;">
<span style="float:right;"><a href="#index">Back to index</a></span>
</p>
<div class="row g-1">
<div class="col-sm-6">
<div class="video-header">Human speech</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/nx0CyrDu70Y"></iframe>
</div>
</div>
<div class="col-sm-6">
<div class="video-header">Unfamiliar vision input</div>
<div class="video-container">
<iframe src="https://youtube.com/embed/hfnAqmK3X7w"></iframe>
</div>
</div>
</div>
</div>
</div>
</body>
</html>