Speaker: Dr Jordi Pont-Tuset, Post-Doctoral Researcher at ETHZ
Venue: Large Conference Room, O’Reilly Institute
Date & Time: Monday 24th April at 11:30am
Title: One-Shot Video Object Segmentation
Abstract: In this talk I’ll present our recent work on semi-supervised video object segmentation, i.e., the separation of an object from the background in a video, given the mask of the first frame. We present One-Shot Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Although all frames are processed independently, the results are temporally coherent and stable. We perform experiments on three annotated video segmentation databases, which show that OSVOS is fast and improves the state of the art by a significant margin (79.8% vs 68.0%).
Speaker Bio: Jordi Pont-Tuset is a post-doctoral researcher at ETHZ, Switzerland, in Prof Luc Van Gool’s Computer Vision Lab (since 2015). He received the degree in Mathematics in 2008, the degree in Electrical Engineering in 2008, the M.Sc. in Research on Information and Communication Technologies in 2010, and the Ph.D. with honours in 2014; from the Universitat Politècnica de Catalunya, BarcelonaTech (UPC). He worked at Disney Research, Zürich (2014). More info: http://jponttuset.cat.