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

Ali Caglayan, Ahmet Burak Can; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0

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 highlevel 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.

Related Material


[pdf]
[bibtex]
@InProceedings{Caglayan_2018_ECCV_Workshops,
author = {Caglayan, Ali and Burak Can, Ahmet},
title = {Exploiting Multi-Layer Features Using a CNN-RNN Approach for RGB-D Object Recognition},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
month = {September},
year = {2018}
}