Embodied Object Representation Learning and Recognition
Scene understanding and decomposition is a crucial challenge for intelligent systems, whether it is for object manipulation, navigation, or any other task. Although current machine and deep learning approaches for object detection and classification obtain high accuracy, they typically do not levera...
Main Authors: | Çatal, O. (Author), Dhoedt, B. (Author), Van de Maele, T. (Author), Verbelen, T. (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022
|
Subjects: | |
Online Access: | View Fulltext in Publisher |
Similar Items
-
Active Vision for Robot Manipulators Using the Free Energy Principle
by: Toon Van de Maele, et al.
Published: (2021-03-01) -
Learning Generative State Space Models for Active Inference
by: Ozan Çatal, et al.
Published: (2020-11-01) -
Model Reduction Through Progressive Latent Space Pruning in Deep Active Inference
by: Çatal, O., et al.
Published: (2022) -
Hierarchical Open-Set Object Detection in Unseen Data
by: Yeong Hyeon Kim, et al.
Published: (2019-10-01) -
Review of Deep Reinforcement Learning-Based Object Grasping: Techniques, Open Challenges, and Recommendations
by: Marwan Qaid Mohammed, et al.
Published: (2020-01-01)