APEX: Unsupervised, object-centric scene segmentation and tracking for robot manipulation
Recent advances in unsupervised learning for object detection, segmentation, and tracking hold significant promise for applications in robotics. A common approach is to frame these tasks as inference in probabilistic latent-variable models. In this paper, however, we show that the current state-of-t...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Jezik: | English |
| Izdano: |
Institute of Electrical and Electronics Engineers
2021
|