Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval

  title={Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval},
  author={Jifei Song and Qian Yu and Yi-Zhe Song and Tao Xiang and Timothy M. Hospedales},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
Human sketches are unique in being able to capture both the spatial topology of a visual object, as well as its subtle appearance details. Fine-grained sketch-based image retrieval (FG-SBIR) importantly leverages on such fine-grained characteristics of sketches to conduct instance-level retrieval of photos. Nevertheless, human sketches are often highly abstract and iconic, resulting in severe misalignments with candidate photos which in turn make subtle visual detail matching difficult… CONTINUE READING
Highly Cited
This paper has 24 citations. REVIEW CITATIONS
18 Citations
51 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 51 references

Similar Papers

Loading similar papers…