Neural Motifs: Scene Graph Parsing with Global Context

@article{Zellers2018NeuralMS,
  title={Neural Motifs: Scene Graph Parsing with Global Context},
  author={Rowan Zellers and Mark Yatskar and Sam Thomson and Yejin Choi},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={5831-5840}
}
  • Rowan Zellers, Mark Yatskar, +1 author Yejin Choi
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • We investigate the problem of producing structured graph representations of visual scenes. [...] Key Method Our analysis motivates a new baseline: given object detections, predict the most frequent relation between object pairs with the given labels, as seen in the training set. This baseline improves on the previous state-of-the-art by an average of 3.6% relative improvement across evaluation settings.Expand Abstract

    Figures, Tables, and Topics from this paper.

    Visual Relationships as Functions:Enabling Few-Shot Scene Graph Prediction
    • 12
    • Highly Influenced
    • Open Access
    Scene Graph Prediction With Limited Labels
    • 15
    • Highly Influenced
    • Open Access
    Scene Graph Prediction with Limited Labels
    • 1
    • Highly Influenced
    • Open Access
    Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
    • 46
    • Highly Influenced
    • Open Access
    Attentive Relational Networks for Mapping Images to Scene Graphs
    • 30
    • Highly Influenced
    • Open Access
    Learning Latent Scene-Graph Representations for Referring Relationships
    • 2
    Memory-Based Network for Scene Graph with Unbalanced Relations
    LinkNet: Relational Embedding for Scene Graph
    • 40
    • Highly Influenced
    • Open Access

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 64 REFERENCES
    Scene Graph Generation from Objects, Phrases and Region Captions
    • 174
    • Highly Influential
    • Open Access
    Scene Graph Generation by Iterative Message Passing
    • 337
    • Highly Influential
    • Open Access
    Detecting Visual Relationships with Deep Relational Networks
    • 218
    • Open Access
    Graph-Structured Representations for Visual Question Answering
    • 155
    • Open Access
    Deep Variation-Structured Reinforcement Learning for Visual Relationship and Attribute Detection
    • 143
    • Open Access
    Pixels to Graphs by Associative Embedding
    • 92
    • Open Access
    Image retrieval using scene graphs
    • 416
    • Open Access
    Visual Relationship Detection with Language Priors
    • 443
    • Highly Influential
    • Open Access
    Deep visual-semantic alignments for generating image descriptions
    • 1,832
    • Open Access
    Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation
    • 140
    • Highly Influential
    • Open Access