Completed
Common Principle
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Collaborators
- 3 Why Object-Centric Learning? Explicit object representation
- 4 Tracking by Detection
- 5 Unsupervised Object-Centric Learning
- 6 Common Principle
- 7 Categorization of Approaches
- 8 VIMON: Attention Network
- 9 VIMON: Next-Frame Prediction
- 10 TBA Tracker Array
- 11 TBA Mid-Level Representation
- 12 TBA Spatial Transformation
- 13 Spatial Mixture Models: OP3
- 14 OP3 Dynamics Network
- 15 CLEAR MOT Metrics
- 16 Datasets
- 17 Results on SpMOT
- 18 How Well Do Models Accumulate Evidence Over Time?
- 19 Dependency of Performance on Number of Objects
- 20 Challenging Cases
- 21 VMDS Challenge Sets
- 22 Out-of-Distribution Test Sets
- 23 Runtime Analysis Runtime on Single RTX 2080 TI GPU
- 24 Conclusions
- 25 2D Annotations