Search: id:"swepub:oai:DiVA.org:liu-183945" >
Video Instance Segm...
Video Instance Segmentation with Recurrent Graph Neural Networks
-
- Johnander, Joakim, 1993- (author)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Zenseact, Gothenburg, Sweden
-
- Brissman, Emil (author)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Saab, Linköping, Sweden
-
- Danelljan, Martin, 1989- (author)
- Computer Vision Lab, ETH Zürich, Zürich, Switzerland
-
show more...
-
- Felsberg, Michael, 1974- (author)
- Linköpings universitet,Datorseende,Tekniska fakulteten,School of Engineering, University of KwaZulu-Natal, Durban, South Africa
-
show less...
-
(creator_code:org_t)
- 2022-01-13
- 2021
- English.
-
In: Pattern Recognition. - Cham : Springer. - 9783030926588 - 9783030926595 ; , s. 206-221
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Video instance segmentation is one of the core problems in computer vision. Formulating a purely learning-based method, which models the generic track management required to solve the video instance segmentation task, is a highly challenging problem. In this work, we propose a novel learning framework where the entire video instance segmentation problem is modeled jointly. To this end, we design a graph neural network that in each frame jointly processes all detections and a memory of previously seen tracks. Past information is considered and processed via a recurrent connection. We demonstrate the effectiveness of the proposed approach in comprehensive experiments. Our approach, operating at over 25 FPS, outperforms previous video real-time methods. We further conduct detailed ablative experiments that validate the different aspects of our approach.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
To the university's database