Image to Video Domain Adaptation Using Web Supervision

  title={Image to Video Domain Adaptation Using Web Supervision},
  author={Andrew Kae and Yale Song},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  • Andrew Kae, Yale Song
  • Published 2020
  • Computer Science
  • 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • Training deep neural networks typically requires large amounts of labeled data which may be scarce or expensive to obtain for a particular target domain. As an alternative, we can leverage webly-supervised data (i.e. results from a public search engine) which are relatively plentiful but may contain noisy results. In this work, we propose a novel two-stage approach to learn a video classifier using webly-supervised data. We argue that learning appearance features and temporal features… CONTINUE READING

    Figures, Tables, and Topics from this paper.


    Publications referenced by this paper.
    Deep Residual Learning for Image Recognition
    • 49,669
    • Highly Influential
    • Open Access
    Generative Adversarial Nets
    • 17,545
    • Highly Influential
    • Open Access
    Gradient-based learning applied to document recognition
    • 24,117
    • Open Access
    Neural Machine Translation by Jointly Learning to Align and Translate
    • 12,758
    • Open Access
    ImageNet: A large-scale hierarchical image database
    • 12,066
    • Highly Influential
    • Open Access
    Learning Spatiotemporal Features with 3D Convolutional Networks
    • 3,405
    • Open Access
    Visualizing Data using t-SNE
    • 13,568
    • Open Access
    Adversarial Discriminative Domain Adaptation
    • 1,482
    • Open Access