Ambient Sound Provides Supervision for Visual Learning thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Ambient Sound Provides Supervision for Visual Learning

Published on Oct 24, 20161758 Views

The sound of crashing waves, the roar of fast-moving cars -- sound conveys important information about the objects in our surroundings. In this work, we show that ambient sounds can be used as a super

Related categories

Chapter list

Ambient Sound Provides Supervision for Visual Learning00:00
Self-supervised learning - 100:56
Self-supervised learning - 201:11
Self-supervised learning with sound - 101:19
Self-supervised learning with sound - 201:24
Audio is invariant to many visual transformations - 101:47
Audio is invariant to many visual transformations - 201:57
Audio is invariant to many visual transformations - 302:00
Audio is invariant to many visual transformations - 402:03
Audio is invariant to many visual transformations - 502:20
Audio is invariant to many visual transformations - 602:34
Audio is invariant to many visual transformations - 703:05
Audio is invariant to many visual transformations - 803:20
Sound prediction and audio-visual learning - 103:39
Video Example : Caffe04:06
Representing ambient sound - 104:34
Representing ambient sound - 204:59
Representing ambient sound - 305:33
Representing ambient sound - 405:37
Representing ambient sound - 505:41
Representing ambient sound - 605:48
Representing ambient sound - 705:49
Representing ambient sound - 805:54
Predicting sound - 106:06
Predicting sound - 206:30
Predicting sound - 306:43
Predicting sound - 406:53
Audio clips in clusters - 107:13
Audio clips in clusters - 208:23
PASCAL VOC Classification - 109:28
PASCAL VOC Classification - 209:49
PASCAL VOC Classification - 309:55
SUN397 Scene Recognition10:14
What did the network learn? - 311:07
What did the network learn? - 411:15
Unit visualizations - 111:23
Unit visualizations - 211:41
Unit visualizations - 311:47
Unit visualizations - 412:02
Unit visualizations - 512:11
Unit visualizations - 612:14
Learning visual models from sound - 112:52
Ambient Sound Provides Supervision for Visual Learning13:26