{
  "id": "liang2019vrrvg",
  "type": "paper-conference",
  "title": "VrR-VG: Refocusing Visually-Relevant Relationships",
  "author": [
    {
      "given": "Yuanzhi",
      "family": "Liang"
    },
    {
      "given": "Yalong",
      "family": "Bai"
    },
    {
      "given": "Wei",
      "family": "Zhang"
    },
    {
      "given": "Xueming",
      "family": "Qian"
    },
    {
      "given": "Li",
      "family": "Zhu"
    },
    {
      "given": "Tao",
      "family": "Mei"
    }
  ],
  "container-title": "2019 IEEE/CVF International Conference on Computer Vision (ICCV)",
  "issued": {
    "date-parts": [
      [
        2019
      ]
    ]
  },
  "URL": "https://doi.org/10.1109/ICCV.2019.01050",
  "abstract": "Relationships encode the interactions among individual instances and play a critical role in deep visual scene understanding. Suffering from the high predictability with non-visual information, relationship models tend to fit the statistical bias rather than \"learning\" to infer the relationships from images. To encourage further development in visual relationships, we propose a novel method to mine more valuable relationships by automatically pruning visually-irrelevant relationships. We construct a new scene graph dataset named Visually-Relevant Relationships Dataset (VrR-VG) based on Visual Genome. Compared with existing datasets, the performance gap between learnable and statistical method is more significant in VrR-VG, and frequency-based analysis does not work anymore. Moreover, we propose to learn a relationship-aware representation by jointly considering instances, attributes and relationships. By applying the representation-aware feature learned on VrR-VG, the performances of image captioning and visual question answering are systematically improved, which demonstrates the effectiveness of both our dataset and features embedding schema. Both our VrR-VG dataset and representation-aware features will be made publicly available soon.",
  "keyword": "visual relationships, scene graphs, dataset bias, Visual Genome, representation learning",
  "publisher": "IEEE",
  "DOI": "10.1109/ICCV.2019.01050",
  "page": "10402-10411"
}