Graph Edit Distance Reward: Learning to Edit Scene Graph

Lichang Chen, Guosheng Lin, Shijie Wang, Qingyao Wu

ECCV 2020

doi:10.1007/978-3-030-58529-7_32 /eccv/2020/chen2020eccv-graph/

Abstract

Scene Graph, as a vital tool to bridge the gap between the language domain and image domain, has been widely adopted in the cross-modality task like VQA. In this paper, we propose a new method to edit the scene graph according to the user instructions, which has never been explored. To be specific, based on the Policy Gradient and Graph Matching algorithm, we propose a Graph Edit Distance Reward to optimize neural symbolic model, in order to learn editing scene graphs as the semantics given by texts. In the context of text-editing image retrieval, we validate the effectiveness of our method in CSS and CRIR dataset. Besides, CRIR is a new synthetic dataset generated by us, and we will publish it soon for future use.

PDF ECCV Semantic Scholar

Cite

Text

Chen et al. "Graph Edit Distance Reward: Learning to Edit Scene Graph." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58529-7_32

Markdown

[Chen et al. "Graph Edit Distance Reward: Learning to Edit Scene Graph." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/chen2020eccv-graph/) doi:10.1007/978-3-030-58529-7_32

BibTeX

@inproceedings{chen2020eccv-graph,
  title     = {{Graph Edit Distance Reward: Learning to Edit Scene Graph}},
  author    = {Chen, Lichang and Lin, Guosheng and Wang, Shijie and Wu, Qingyao},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58529-7_32},
  url       = {https://mlanthology.org/eccv/2020/chen2020eccv-graph/}
}