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
Figures, Tables, and Topics from this paper
266 Citations
Visual Relationships as Functions:Enabling Few-Shot Scene Graph Prediction
- Computer Science
- 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
- 2019
- 19
- Highly Influenced
- PDF
Scene Graph Prediction With Limited Labels
- Computer Science, Medicine
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- 2019
- 26
- Highly Influenced
- PDF
Scene Graph Prediction with Limited Labels
- Computer Science
- 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
- 2019
- 8
- Highly Influenced
Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
- Computer Science, Mathematics
- NeurIPS
- 2018
- 59
- Highly Influenced
- PDF
Attentive Relational Networks for Mapping Images to Scene Graphs
- Computer Science
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2019
- 46
- Highly Influenced
- PDF
Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score
- Computer Science
- ACCV
- 2020
- Highly Influenced
- PDF
Memory-Based Network for Scene Graph with Unbalanced Relations
- Computer Science
- ACM Multimedia
- 2020
- Highly Influenced
References
SHOWING 1-10 OF 63 REFERENCES
Scene Graph Generation from Objects, Phrases and Region Captions
- Computer Science
- 2017 IEEE International Conference on Computer Vision (ICCV)
- 2017
- 217
- Highly Influential
- PDF
Scene Graph Generation by Iterative Message Passing
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 411
- Highly Influential
- PDF
Detecting Visual Relationships with Deep Relational Networks
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 262
- PDF
Graph-Structured Representations for Visual Question Answering
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 189
- PDF
Deep Variation-Structured Reinforcement Learning for Visual Relationship and Attribute Detection
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 171
- PDF
Image retrieval using scene graphs
- Computer Science
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2015
- 481
- PDF
Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation
- Computer Science
- 2017 IEEE International Conference on Computer Vision (ICCV)
- 2017
- 169
- Highly Influential
- PDF