<!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/bootstrap@5.0.1/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>