en-de
en-es
en-fr
en-pt
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
A tutorial on deep and unsupervised feature learning for activity recognition
Published on 2011-08-2412229 Views
Recognition of human activity from video data is a challenging problem that has received an increasing amount of attention from the computer vision community in recent years. Currently the best perfor
Related categories
Presentation
Deep Learning for Activity Recognition00:00
Exixting Pipeline for Activity Recognition00:24
Deep Leraning02:09
Motivations04:08
Popular Deep Learning Architectures06:42
Outline08:55
Convolutional Networks09:23
Biologically - Inspired10:28
3D Convnets for Activity Recognition11:00
3D CNN Architecture12:20
3D CONVNET: Discussion14:15
Learning Features for Video Understanding14:50
Gated Restricted Boltzmann Machines16:03
Convolutional GRBM18:30
Visualizing Features Through Analogy - 119:11
Visualizing Features Through Analogy - 219:21
Visualizing Features Through Analogy - 319:23
Visualizing Features Through Analogy - 419:25
Visualizing Features Through Analogy - 519:36
Human Activity: KTH Actions Dataset20:41
Activity Recognition: KTH21:46
Activity Recognition: Hollywood 222:10
Space - Time Deep Belief Networks22:29
ST-DBN - 123:57
ST-DBN - 224:51
Measuring Invariance25:42
Denoising and Reconstruction27:02
Stacked Convolutional Independent Subspace Analysis27:33
Scaling Up28:02
Learning Spatio-Temporal Features28:03
Velocity and Orientation Selectivity28:04
Summary28:05
Conclusion28:26