Reviews: Hierarchical Object Representation for Open-Ended Object Category Learning and Recognition

In the "Introduction" section, the authors point out the neurophysiological evidences that a human brain has a hierarchical structure for the object recognition, and that the learning and recognition of objects occurs concurrently in a human brain. Then, they briefly explained how they built their 3D object recognition model that concurrently learns and recognizes the objects that works in the similar way to the human brain. The authors talk about conventional approaches for the object recognition problem in the "Related work" section. They mention about the probabilistic latent semantic indexing (pLSI), latent Dirichlet allocation (LDA) and its variations, etc. And they point out that none of these conventional models can learn and recognize objects in an open-ended manner.