Corpus ID: 220870731

Cross-Modal Hierarchical Modelling for Fine-Grained Sketch Based Image Retrieval

  title={Cross-Modal Hierarchical Modelling for Fine-Grained Sketch Based Image Retrieval},
  author={A. Sain and A. Bhunia and Yongxin Yang and Tao Xiang and Yi-Zhe Song},
  • A. Sain, A. Bhunia, +2 authors Yi-Zhe Song
  • Published 2020
  • Computer Science
  • ArXiv
  • Sketch as an image search query is an ideal alternative to text in capturing the finegrained visual details. Prior successes on fine-grained sketch-based image retrieval (FGSBIR) have demonstrated the importance of tackling the unique traits of sketches as opposed to photos, e.g., temporal vs. static, strokes vs. pixels, and abstract vs. pixelperfect. In this paper, we study a further trait of sketches that has been overlooked to date, that is, they are hierarchical in terms of the levels of… CONTINUE READING

    Figures and Tables from this paper.


    Publications referenced by this paper.
    Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval
    • 82
    • PDF
    Sketch Less for More: On-the-Fly Fine-Grained Sketch-Based Image Retrieval
    • 4
    • PDF
    Generalising Fine-Grained Sketch-Based Image Retrieval
    • 13
    • PDF
    Deep Manifold Alignment for Mid-Grain Sketch Based Image Retrieval
    • 4
    • PDF
    Sketch Me That Shoe
    • 191
    • PDF
    Sketch based Image Retrieval using Learned KeyShapes (LKS)
    • 55
    • PDF
    Doodle to Search: Practical Zero-Shot Sketch-Based Image Retrieval
    • 27
    • PDF
    Cross-domain Generative Learning for Fine-Grained Sketch-Based Image Retrieval
    • 25
    • PDF
    Learning to Sketch with Shortcut Cycle Consistency
    • 36
    • PDF
    Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-Based Image Retrieval
    • 30
    • PDF