| Full name | Multi-task learner |
| Description | We advocate multi-task learning as a way to improve scene recognition, building on the fact that the scene type is highly correlated with the objects in the scene, and therefore with its semantic segmentation into different object classes. |
| Publication title | Indoor Scene Recognition in 3D |
| Publication authors | Shengyu Huang, Mikhail Usvyatsov, Konrad Schindler |
| Publication venue | IROS 2020 |
| Publication URL | https://arxiv.org/abs/2002.12819 |
| Input Data Types | Uses Color,Uses Geometry Uses 3D |
| Programming language(s) | PyTorch |
| Hardware | GeForce 1080Ti |
| Source code or download URL | https://github.com/ShengyuH/Scene-Recognition-in-3D |
| Submission creation date | 18 Sep, 2019 |
| Last edited | 25 Aug, 2020 |
| Last uploaded | 6 Nov, 2019 |
