Explorer Transductive Zero-Shot Action Recognition by Word-Vector Embedding

@inproceedings{Xu2017ExplorerTZ,
  title={Explorer Transductive Zero-Shot Action Recognition by Word-Vector Embedding},
  author={Xun Xu and Timothy M. Hospedales and Shaogang Gong},
  year={2017}
}
The number of categories for action recognition is growing rapidly and it has become increasingly hard to label sufficient training data for learning conventional models for all categories. Instead of collecting ever more data and labelling them exhaustively for all categories, an attractive alternative approach is “zero-shot learning” (ZSL). To that end… CONTINUE READING