Главная
Study mode:
on
1
Intro
2
Overview of Capsule Networks
3
Computer Graphics
4
Inverse Graphics
5
Capsules
6
Conventional Convolutional Layers
7
Convolutional Capsule Layers
8
Two Simplification
9
Capsule Pooling
10
Current Video Action Detection Network
11
VideoCapsuleNet Architecture
12
Encoder
13
VideoCapsuleNet Training
14
Action Localization Accuracy
15
Qualitative Results - Entire Videos
16
Effects of Capsule Masking
17
Ablations: Coordinate Addition
18
Ablations: Extra Skip Connections
19
Ablations: # of Convolutional Layers
20
Ablations: Losses and Reconstruction
21
Synthetic Dataset Experiments
Description:
Explore a simplified network for action detection in this 22-minute lecture on VideoCapsuleNet. Delve into the fundamentals of Capsule Networks, computer graphics, and inverse graphics before examining the architecture of VideoCapsuleNet. Learn about convolutional capsule layers, capsule pooling, and the encoder structure. Analyze the training process, action localization accuracy, and qualitative results for entire videos. Investigate the effects of capsule masking and various ablation studies, including coordinate addition, skip connections, convolutional layers, losses, and reconstruction. Conclude with insights from synthetic dataset experiments to gain a comprehensive understanding of this innovative approach to video action detection.

VideoCapsuleNet - A Simplified Network for Action Detection

University of Central Florida
Add to list
0:00 / 0:00