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}
}
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
266 Citations
Visual Relationships as Functions:Enabling Few-Shot Scene Graph Prediction
  • 19
  • Highly Influenced
  • PDF
Scene Graph Prediction With Limited Labels
  • 26
  • Highly Influenced
  • PDF
Scene Graph Prediction with Limited Labels
  • 8
  • Highly Influenced
Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
  • 59
  • Highly Influenced
  • PDF
Attentive Relational Networks for Mapping Images to Scene Graphs
  • 46
  • Highly Influenced
  • PDF
Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score
  • Highly Influenced
  • PDF
Learning Latent Scene-Graph Representations for Referring Relationships
  • 2
Memory-Based Network for Scene Graph with Unbalanced Relations
  • Highly Influenced
LinkNet: Relational Embedding for Scene Graph
  • 51
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 63 REFERENCES
Scene Graph Generation from Objects, Phrases and Region Captions
  • 217
  • Highly Influential
  • PDF
Scene Graph Generation by Iterative Message Passing
  • 411
  • Highly Influential
  • PDF
Detecting Visual Relationships with Deep Relational Networks
  • Bo Dai, Yuqi Zhang, D. Lin
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
  • 262
  • PDF
Graph-Structured Representations for Visual Question Answering
  • 189
  • PDF
Deep Variation-Structured Reinforcement Learning for Visual Relationship and Attribute Detection
  • 171
  • PDF
Pixels to Graphs by Associative Embedding
  • 123
  • PDF
Image retrieval using scene graphs
  • 481
  • PDF
Visual Relationship Detection with Language Priors
  • 514
  • Highly Influential
  • PDF
Deep visual-semantic alignments for generating image descriptions
  • 1,896
Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation
  • 169
  • Highly Influential
  • PDF
...
1
2
3
4
5
...