Compact Scene Graphs for Layout Composition and Patch Retrieval

@article{Tripathi2019CompactSG,
  title={Compact Scene Graphs for Layout Composition and Patch Retrieval},
  author={Subarna Tripathi and S. N. Sridhar and Sairam Sundaresan and Hanlin Tang},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2019},
  pages={676-683}
}
  • Subarna Tripathi, S. N. Sridhar, +1 author Hanlin Tang
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • Structured representations such as scene graphs serve as an efficient and compact representation that can be used for downstream rendering or retrieval tasks. [...] Key Method First, we enhance the scene graph representation with heuristic-based relations, which add minimal storage overhead. Second, we use extreme points representation to supervise the learning of the scene composition network. These methods achieve significantly higher performance over existing work (69.0% vs 51.2% in relation score metric…Expand Abstract
    Triplet-Aware Scene Graph Embeddings
    • 5
    • PDF
    Structured Query-Based Image Retrieval Using Scene Graphs
    • 1
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES
    Microsoft COCO: Common Objects in Context
    • 10,278
    • PDF
    Adam: A Method for Stochastic Optimization
    • 49,659
    • PDF
    Image retrieval using scene graphs
    • 418
    • PDF
    Scene Graph Generation by Iterative Message Passing
    • 337
    • PDF
    Generative Adversarial Text to Image Synthesis
    • 1,509
    • PDF
    Progressive Growing of GANs for Improved Quality, Stability, and Variation
    • 2,070
    • PDF
    Image Generation from Scene Graphs
    • 234
    • PDF
    Photographic Image Synthesis with Cascaded Refinement Networks
    • 471
    • PDF
    Semantic Image Synthesis With Spatially-Adaptive Normalization
    • 399
    • PDF
    Stacked Hourglass Networks for Human Pose Estimation
    • 1,918
    • PDF