Video Object Segmentation

In this meetup we will talk about Video Object Segmentation. Our discussion will start with a definition of the problem, along with its main challenges and then we will analyze three recent approaches for this task, all published at CVPR 2019:

1. "See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks"
2. "RVOS: End-to-End Recurrent Network for Video Object Segmentation"
3. "A Generative Appearance Model for End-to-end Video Object Segmentation"

Presentation will be held in Romanian.

Speaker: Emanuela Haller

Location: EC101 - in the old building of the Faculty of Automatic Control and Computers (Iuliu Maniu entrance), UPB.