{
  "schema_version": 1,
  "slug": "vrr-vg",
  "canonical_url": "https://akira-l.github.io/publications/vrr-vg/",
  "language_urls": {
    "en": "https://akira-l.github.io/publications/vrr-vg/",
    "zh-CN": "https://akira-l.github.io/zh/publications/vrr-vg/"
  },
  "title": "VrR-VG: Refocusing Visually-Relevant Relationships",
  "short_title": "VrR-VG",
  "authors": [
    "Yuanzhi Liang",
    "Yalong Bai",
    "Wei Zhang",
    "Xueming Qian",
    "Li Zhu",
    "Tao Mei"
  ],
  "publication": {
    "kind": "conference",
    "venue": "IEEE/CVF International Conference on Computer Vision (ICCV 2019)",
    "citation_container_title": "2019 IEEE/CVF International Conference on Computer Vision (ICCV)",
    "status": "published",
    "year": 2019,
    "publication_date": "2019",
    "publisher": "IEEE",
    "pages": "10402-10411",
    "alternate_pagination": {
      "pages": "10403-10412",
      "version": "CVF open-access copy",
      "url": "https://openaccess.thecvf.com/content_ICCV_2019/html/Liang_VrR-VG_Refocusing_Visually-Relevant_Relationships_ICCV_2019_paper.html"
    }
  },
  "identifiers": {
    "doi": "10.1109/ICCV.2019.01050",
    "arxiv": "1902.00313",
    "arxiv_primary_class": "cs.CV"
  },
  "arxiv_dates": {
    "first_posted": "2019-02-01",
    "last_revised": "2019-08-26"
  },
  "keywords": [
    "visual relationships",
    "scene graphs",
    "dataset bias",
    "Visual Genome",
    "representation learning"
  ],
  "official_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.",
  "official_abstract_rights": "Excluded from the site's CC BY 4.0 license; original paper rights apply.",
  "primary_source": {
    "label": "IEEE version of record",
    "url": "https://doi.org/10.1109/ICCV.2019.01050",
    "version": "ICCV 2019 version of record; CVF open-access copy has alternate pagination 10403-10412; arXiv:1902.00313v2 cross-checked",
    "method_locator": "Abstract; visually-irrelevant relationship pruning and relationship-aware representation sections",
    "evidence_locator": "Abstract; scene-graph analysis, image captioning, and VQA experiments"
  },
  "source_checked": "2026-07-31",
  "verification_status": "author-verified",
  "author_verified_on": "2026-07-31",
  "commentary": {
    "license": "https://creativecommons.org/licenses/by/4.0/",
    "en": {
      "summary": "VrR-VG prunes relationships that can be predicted from non-visual statistics, builds a visually relevant scene-graph dataset from Visual Genome, and learns representations that jointly encode instances, attributes, and relationships.",
      "problem": "Visual-relationship models can exploit category and frequency biases to predict predicates without using image evidence, making benchmark performance a weak test of visual reasoning.",
      "contributions": [
        "Automatically identifies and removes visually irrelevant relationships from Visual Genome.",
        "Constructs the VrR-VG dataset so statistical shortcuts are less effective and visual evidence matters more.",
        "Learns a relationship-aware representation over instances, attributes, and relations for downstream tasks."
      ],
      "evidence": "The paper analyzes the gap between learnable and statistical methods on VrR-VG and reports systematic improvements in image captioning and visual question answering using the learned features. Exact margins belong to the ICCV tables.",
      "limitations": "Pruning is tied to the paper's definition and detector of visual irrelevance; some relationships can legitimately combine visual and contextual knowledge. Dataset debiasing does not eliminate every possible shortcut.",
      "positioning": "VrR-VG is both a dataset-refocusing and representation-learning contribution. It operationalizes a useful debiasing idea: first detect what can be guessed without pixels, then construct an evaluation set where image evidence is more necessary.",
      "citation_ready": "Liang et al. construct VrR-VG by pruning visually irrelevant relationships from Visual Genome and learn relationship-aware features that jointly model instances, attributes, and relations."
    },
    "zh-CN": {
      "summary": "VrR-VG 剪除仅凭非视觉统计就能预测的关系，从 Visual Genome 构建更强调视觉证据的 scene-graph 数据集，并联合编码实例、属性与关系来学习表示。",
      "problem": "视觉关系模型可能利用类别与频率偏差，在几乎不看图像证据的情况下预测 predicate，使 benchmark 分数无法真实反映视觉推理。",
      "contributions": [
        "自动识别并移除 Visual Genome 中 visually irrelevant 的关系。",
        "构建 VrR-VG，使统计捷径更难奏效、视觉证据更加必要。",
        "联合实例、属性和关系学习 relationship-aware representation，并用于下游任务。"
      ],
      "evidence": "论文分析 VrR-VG 上 learnable method 与 statistical method 的差异，并报告学习特征对 image captioning 和 visual question answering 的系统性改善；准确幅度应引用 ICCV 表格。",
      "limitations": "剪除过程依赖论文对视觉无关性的定义和检测方式，一些关系本来就会结合视觉与上下文知识；数据集去偏也不能消除所有潜在 shortcut。",
      "positioning": "VrR-VG 同时贡献数据集重构与关系表示学习。其通用去偏思路是：先检测哪些答案不用像素也能猜到，再构造更需要视觉证据的评测数据。",
      "citation_ready": "Liang 等从 Visual Genome 中剪除 visually irrelevant relationships 构建 VrR-VG，并联合建模实例、属性和关系来学习 relationship-aware feature。"
    }
  },
  "citation": {
    "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"
  },
  "resources": [
    {
      "label": "Version of record",
      "url": "https://doi.org/10.1109/ICCV.2019.01050"
    },
    {
      "label": "Open access",
      "url": "https://openaccess.thecvf.com/content_ICCV_2019/html/Liang_VrR-VG_Refocusing_Visually-Relevant_Relationships_ICCV_2019_paper.html"
    },
    {
      "label": "arXiv",
      "url": "https://arxiv.org/abs/1902.00313"
    },
    {
      "label": "PDF",
      "url": "https://openaccess.thecvf.com/content_ICCV_2019/papers/Liang_VrR-VG_Refocusing_Visually-Relevant_Relationships_ICCV_2019_paper.pdf"
    }
  ]
}