Composing Text and Image for Image Retrieval - An Empirical Odyssey

@article{Vo2018ComposingTA,
  title={Composing Text and Image for Image Retrieval - An Empirical Odyssey},
  author={Nam S. Vo and Lu Jiang and Chen Sun and Kevin Murphy and Li-Jia Li and Li Fei-Fei and James Hays},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.07119}
}
In this paper, we study the task of image retrieval, where the input query is specified in the form of an image plus some text that describes desired modifications to the input image. For example, we may present an image of the Eiffel tower, and ask the system to find images which are visually similar but are modified in small ways, such as being taken at nighttime instead of during the day. To tackle this task, we learn a similarity metric between a target image and a source image plus source… CONTINUE READING
4
Twitter Mentions

References

Publications referenced by this paper.
SHOWING 1-10 OF 59 REFERENCES

Automatic Spatially-Aware Fashion Concept Discovery

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

Discovering states and transformations in image collections

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Attributes as Operators

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

VQA: Visual Question Answering

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

From Red Wine to Red Tomato: Composition with Context

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Multimodal Residual Learning for Visual QA

  • NIPS
  • 2016
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Image Question Answering Using Convolutional Neural Network with Dynamic Parameter Prediction

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Dialog-based Interactive Image Retrieval

Xiaoxiao Guo
  • NeurIPS
  • 2018
VIEW 2 EXCERPTS