RGB-D Scene Recognition Based on Object-Scene Relation (Student Abstract)

AAAI 2021 pp. 15787-15788

doi:10.1609/AAAI.V35I18.17890 /aaai/2021/guo2021aaai-rgb/

Abstract

We develop a RGB-D scene recognition model based on object-scene relation(RSBR). First learning a Semantic Network in the semantic domain that classifies the label of a scene on the basis of the labels of all object types. Then, we design an Appearance Network in the appearance domain that recognizes the scene according to local captions. We enforce the Semantic Network to guide the Appearance Network in the learning procedure. Based on the proposed RSBR model, we obtain the state-of-the-art results of RGB-D scene recognition on SUN RGB-D and NYUD2 datasets.

PDF AAAI Semantic Scholar

Cite

Text

Guo and Liang. "RGB-D Scene Recognition Based on Object-Scene Relation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17890

Markdown

[Guo and Liang. "RGB-D Scene Recognition Based on Object-Scene Relation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/guo2021aaai-rgb/) doi:10.1609/AAAI.V35I18.17890

BibTeX

@inproceedings{guo2021aaai-rgb,
  title     = {{RGB-D Scene Recognition Based on Object-Scene Relation (Student Abstract)}},
  author    = {Guo, Yuhui and Liang, Xun},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15787-15788},
  doi       = {10.1609/AAAI.V35I18.17890},
  url       = {https://mlanthology.org/aaai/2021/guo2021aaai-rgb/}
}