Search: (WFRF:(Johnander Joakim)) >
Recurrent Graph Neu...
Recurrent Graph Neural Networks for Video Instance Segmentation
-
- Brissman, Emil, 1987- (author)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Saab, Linkoping, Sweden
-
- Johnander, Joakim, 1993- (author)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Zenseact, Sweden
-
- Danelljan, Martin (author)
- Swiss Fed Inst Technol, Switzerland
-
show more...
-
- Felsberg, Michael, 1974- (author)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Univ KwaZulu Natal, South Africa
-
show less...
-
(creator_code:org_t)
- 2022-11-18
- 2023
- English.
-
In: International Journal of Computer Vision. - : Springer. - 0920-5691 .- 1573-1405. ; 131, s. 471-495
- Related links:
-
https://liu.diva-por... (primary) (Raw object)
-
show more...
-
https://urn.kb.se/re...
-
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 operates online at over 25 FPS and obtains 16.3 AP on the challenging OVIS benchmark, setting a new state-of-the-art. We further conduct detailed ablative experiments that validate the different aspects of our approach. Code is available at https://github.com/emibr948/RGNNVIS-PlusPlus.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Keyword
- Detection; Tracking; Segmentation; Video
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
To the university's database