Exploiting Multi-Layer Features Using a CNN-RNN Approach for RGB-D Object Recognition

Abstract

This paper proposes an approach for RGB-D object recognition by integrating a CNN model with recursive neural networks. It first employs a pre-trained CNN model as the underlying feature extractor to get visual features at different layers for RGB and depth modalities. Then, a deep recursive model is applied to map these features into high-level representations. Finally, multi-level information is fused to produce a strong global representation of the entire object image. In order to utilize the CNN model trained on large-scale RGB datasets for depth domain, depth images are converted to a representation similar to RGB images. Experimental results on the Washington RGB-D Object dataset show that the proposed approach outperforms previous approaches.

Cite

Text

Caglayan and Can. "Exploiting Multi-Layer Features Using a CNN-RNN Approach for RGB-D Object Recognition." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11015-4_51

Markdown

[Caglayan and Can. "Exploiting Multi-Layer Features Using a CNN-RNN Approach for RGB-D Object Recognition." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/caglayan2018eccvw-exploiting/) doi:10.1007/978-3-030-11015-4_51

BibTeX

@inproceedings{caglayan2018eccvw-exploiting,
  title     = {{Exploiting Multi-Layer Features Using a CNN-RNN Approach for RGB-D Object Recognition}},
  author    = {Caglayan, Ali and Can, Ahmet Burak},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {675-688},
  doi       = {10.1007/978-3-030-11015-4_51},
  url       = {https://mlanthology.org/eccvw/2018/caglayan2018eccvw-exploiting/}
}