BROWSE
Detail
Conference Paper
Occluded Video Instance Segmentation with Set Prediction Approach
- Authors
- Heechul Bae, Soonyong Song, Junhee Park
- Issue Date
- 2021-10
- Citation
- International Conference on Computer Vision Workshops (ICCVW) 2021, pp.3850-3853
- Language
- English
- Type
- Conference Paper
- Abstract
- Occluded Video Instance Segmentation (OVIS) is a multi-task problem performing detection, segmentation, and tracking simultaneously under severe occlusions. We propose an extended model for the OVIS task based on the real-time one-stage instance segmentation method. The proposed model was applied to the OVIS dataset hold by the ICCV 2021 - Occluded Video Instance Segmentation Workshop 2021. We also show that the occlusions can be handled efficiently through one-stage approaches.
- KSP Keywords
- Extended Model, One-stage, Proposed model, Real-time, multi-task, prediction approach, segmentation method