Completed
Quantitative Results - YoutubeVOS Dataset
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing
Automatically move to the next video in the Classroom when playback concludes
- 1 Overview
- 2 Introduction to Capsule Networks
- 3 Computer Graphics
- 4 Inverse Graphics
- 5 Different capsule formulations
- 6 What is capsule routing
- 7 Video Capsule Networks
- 8 Semi-Supervised Video Object Segmentation
- 9 Datasets
- 10 Example videos from DAVIS
- 11 VOS using Capsules
- 12 Video Encoder
- 13 Frame Encoder with Memory Module
- 14 Attention Routing
- 15 Conv Capsule Layer and Decoder Network
- 16 Objective Function
- 17 Quantitative Results - YoutubeVOS Dataset
- 18 Quantitative Results - Speed Analysis
- 19 Qualitative Results - Single Object
- 20 Qualitative Results - Multiple Objects
- 21 Effect of Memory Module
- 22 Effect of the Zooming Module
- 23 Effect of Zooming Module
- 24 CapsuleVOS Architecture
