CPARR: Category-Based Proposal Analysis for Referring Relationships

Abstract

The task of referring relationships is to localize subject and object entities in an image satisfying a relationship query, which is given in the form of . This requires simultaneous localization of the subject and object entities in a specified relationship. We introduce a simple yet effective proposal-based method for referring relationships. Different from the existing methods such as SSAS, our method can generate a high-resolution result while reducing its complexity and ambiguity. Our method is composed of two modules: a category-based proposal generation module to select the proposals related to the entities and a predicate analysis module to score the compatibility of pairs of selected proposals. We show state-of-the-art performance on the referring relationship task on two public datasets: Visual Relationship Detection and Visual Genome.

Cite

Text

He et al. "CPARR: Category-Based Proposal Analysis for Referring Relationships." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00482

Markdown

[He et al. "CPARR: Category-Based Proposal Analysis for Referring Relationships." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/he2020cvprw-cparr/) doi:10.1109/CVPRW50498.2020.00482

BibTeX

@inproceedings{he2020cvprw-cparr,
  title     = {{CPARR: Category-Based Proposal Analysis for Referring Relationships}},
  author    = {He, Chuanzi and Zhu, Haidong and Gao, Jiyang and Chen, Kan and Nevatia, Ram},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2020},
  pages     = {4074-4083},
  doi       = {10.1109/CVPRW50498.2020.00482},
  url       = {https://mlanthology.org/cvprw/2020/he2020cvprw-cparr/}
}